Analysis-by-synthesis for source separation and speech recognition
|
|
|
- Asher Jordan
- 5 years ago
- Views:
Transcription
1 Analysis-by-synthesis for source separation and speech recognition Michael I Mandel mim@mr-pc.org Brooklyn College (CUNY) Joint work with Young Suk Cho and Arun Narayanan (Ohio State) Columbia Neural Network Seminar Series September 8, 2015 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
2 Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
3 Motivation: need for noise robustness Outline 1 Motivation: need for noise robustness Need for better mobile voice quality Need for noise robust automatic speech recognition (ASR) Main challenge 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
4 Motivation: need for noise robustness Need for better mobile voice quality Outline 1 Motivation: need for noise robustness Need for better mobile voice quality Need for noise robust automatic speech recognition (ASR) Main challenge 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
5 Motivation: need for noise robustness Need for better mobile voice quality Need for better mobile voice quality There are now more mobile devices than humans on earth 1 But recording conditions for these devices leave much to be desired Can we recover high quality speech from noisy & degraded recordings? 1 there-are-officially-more-mobile-devices-than-people-in-the-world html Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
6 Motivation: need for noise robustness Need for better mobile voice quality Why mobile voice quality stinks 2 2 Je Hecht. Why mobile voice quality still stinks and how to fix it. IEEE Spectrum, September2014 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
7 Motivation: need for noise robustness Need for better mobile voice quality Why mobile voice quality stinks 2 2 Je Hecht. Why mobile voice quality still stinks and how to fix it. IEEE Spectrum, September2014 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
8 Motivation: need for noise robustness Need for noise robust automatic speech recognition (ASR) Outline 1 Motivation: need for noise robustness Need for better mobile voice quality Need for noise robust automatic speech recognition (ASR) Main challenge 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
9 Motivation: need for noise robustness Need for noise robust automatic speech recognition (ASR) Conversational mobile software agents Source: Tom Vanleenhove Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
10 Motivation: need for noise robustness Need for noise robust automatic speech recognition (ASR) Conversational mobile software agents need to work in Source: Flickr user rickihuang Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
11 Motivation: need for noise robustness Need for noise robust automatic speech recognition (ASR) Conversational mobile software agents need to work in Source: Flickr user retorta net Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
12 Motivation: need for noise robustness Need for noise robust automatic speech recognition (ASR) Conversational mobile software agents need to work in Source: Flickr user Brian Indrelunas Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
13 Motivation: need for noise robustness Need for noise robust automatic speech recognition (ASR) But automatic speech recognition doesn t work there 3 3 Amit Juneja. A comparison of automatic and human speech recognition in null grammar. The Journal of the Acoustical Society of America, 131(3):EL256 EL261,February2012 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
14 Motivation: need for noise robustness Main challenge Outline 1 Motivation: need for noise robustness Need for better mobile voice quality Need for noise robust automatic speech recognition (ASR) Main challenge 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
15 Motivation: need for noise robustness Main challenge Main challenge Speech is a rich signal, it requires rich models Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
16 Motivation: need for noise robustness Main challenge Main challenge Speech is a rich signal, it requires rich models Synthesis models are rich enough to represent almost all speech Non-parametric synthesis models for high quality DNN as non-linear distance function Parametric synthesis models for e cient representation e cient gradient-based optimization of input (not model) Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
17 Non-parametric synthesis for speech enhancement Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement Overview Deep neural network as nonlinear distance function Using this DNN for speech enhancement Noise suppression experiments Audio super-resolution experiments Summary 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
18 Non-parametric synthesis for speech enhancement Overview Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement Overview Deep neural network as nonlinear distance function Using this DNN for speech enhancement Noise suppression experiments Audio super-resolution experiments Summary 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
19 Non-parametric synthesis for speech enhancement Overview Concatenative resynthesis for speech enhancement 4,5 Standard approaches try to modify noisy recordings We instead resynthesize a clean version of the same speech Should produce infinite suppression and high speech quality 4 Michael I Mandel, Young-Suk Cho, and Yuxuan Wang. Learning a concatenative resynthesis system for noise suppression. In Proc. IEEE GlobalSIP, Michael I Mandel and Young Suk Cho. Audio super-resolution using concatenative resynthesis. In Proc. IEEE WASPAA, To appear Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
20 Non-parametric synthesis for speech enhancement Overview Motivating example Your phone records your voice in quiet, close-talk conditions Uses those recordings to replace your voice in noisy, far-talk conditions Resynthesizes your speech from previous high-quality recordings Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
21 Non-parametric synthesis for speech enhancement Overview Concatenative resynthesis Use a large dictionary of 200 ms chunks of audio Learn DNN-based a nity between dictionary & mixture chunks Perform concatenative synthesis of signal from dictionary General robust supervised nonlinear signal mapping framework Task Map from To Noise suppression Noisy Clean Audio super-resolution Reverberated, compressed Clean Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
22 Non-parametric synthesis for speech enhancement Deep neural network as nonlinear distance function Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement Overview Deep neural network as nonlinear distance function Using this DNN for speech enhancement Noise suppression experiments Audio super-resolution experiments Summary 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
23 Non-parametric synthesis for speech enhancement Deep neural network as nonlinear distance function Deep neural network as nonlinear distance function 6 Generative Discriminative Dictionary-based Data-intensive training Moderate training data Data-e cient training Hard to adapt Hard to adapt Very adaptable 6 Michael I Mandel, Young-Suk Cho, and Yuxuan Wang. Learning a concatenative resynthesis system for noise suppression. In Proc. IEEE GlobalSIP, 2014 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
24 Non-parametric synthesis for speech enhancement Deep neural network as nonlinear distance function Train DNN on correctly and incorrectly paired chunks Noise suppression Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
25 Non-parametric synthesis for speech enhancement Deep neural network as nonlinear distance function Train DNN on correctly and incorrectly paired chunks Audio super-resolution Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
26 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement Overview Deep neural network as nonlinear distance function Using this DNN for speech enhancement Noise suppression experiments Audio super-resolution experiments Summary 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
27 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Find optimal sequence of clean chunks x = {x t } T t=0 input sequence of noisy chunks ẑ = {z t } T t=0 best sequence of corresponding dictionary chunks Y ẑ = argmax z t Y = argmax z i p(z t = j x t ) p(z t = j z t 1 = i) g(z j, x i ) T ij Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
28 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Find optimal sequence of clean chunks x = {x t } T t=0 input sequence of noisy chunks ẑ = {z t } T t=0 best sequence of corresponding dictionary chunks A nity between clean and noisy chunks Y ẑ = argmax z t Y = argmax z i p(z t = j x t ) p(z t = j z t 1 = i) g(z j, x i ) T ij Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
29 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Find optimal sequence of clean chunks x = {x t } T t=0 input sequence of noisy chunks ẑ = {z t } T t=0 best sequence of corresponding dictionary chunks A nity between clean and noisy chunks Transition a nity between clean chunks Y ẑ = argmax z t Y = argmax z i p(z t = j x t ) p(z t = j z t 1 = i) g(z j, x i ) T ij Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
30 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Compare all pairs of noisy and clean chunks Observed mixture D1 D2 D3... Clean dictionary M1 M1 M1... Similarity DNN Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
31 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Compare all pairs of noisy and clean chunks Observed mixture D1 D2 D3... Clean dictionary M2 M2 M2... Similarity DNN Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
32 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Compare all pairs of noisy and clean chunks Observed mixture D1 D2 D3... Clean dictionary M3 M3 M3... Similarity DNN Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
33 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Compare all pairs of noisy and clean chunks Observed mixture D1 D2 D3... Clean dictionary M4 M4 M4... Similarity DNN Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
34 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Compare all pairs of noisy and clean chunks Observed mixture D1 D2 D3... Clean dictionary M5 M5 M5... Similarity DNN Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
35 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Compare all pairs of noisy and clean chunks Observed mixture D1 D2 D3... Clean dictionary MN MN MN... Similarity DNN Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
36 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Standard Viterbi algorithm for to find optimal sequence Observed mixture D1 D2 D3... Clean dictionary MN MN MN... Similarity DNN Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
37 Non-parametric synthesis for speech enhancement Using this DNN for speech enhancement Standard Viterbi algorithm for to find optimal sequence Observed mixture D1 D2 D3... Clean dictionary MN MN MN... Similarity DNN Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
38 Non-parametric synthesis for speech enhancement Noise suppression experiments Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement Overview Deep neural network as nonlinear distance function Using this DNN for speech enhancement Noise suppression experiments Audio super-resolution experiments Summary 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
39 Non-parametric synthesis for speech enhancement Noise suppression experiments Original clean speech Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
40 Non-parametric synthesis for speech enhancement Noise suppression experiments Noisy speech Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
41 Non-parametric synthesis for speech enhancement Noise suppression experiments Traditional mask-based separation Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
42 Non-parametric synthesis for speech enhancement Noise suppression experiments Concatenative resynthesis output Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
43 Non-parametric synthesis for speech enhancement Noise suppression experiments Original clean speech Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
44 Non-parametric synthesis for speech enhancement Noise suppression experiments Subjective quality is high Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
45 Non-parametric synthesis for speech enhancement Noise suppression experiments Subjective quality is high Clean Concat Speech Noise Sup Overall IRM NN Noisy Quality (higher better) Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
46 Non-parametric synthesis for speech enhancement Noise suppression experiments Subjective intelligibility is ok Clean Concat IRM NN Noisy Keywords All words Words correctly identified (%) Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
47 Non-parametric synthesis for speech enhancement Audio super-resolution experiments Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement Overview Deep neural network as nonlinear distance function Using this DNN for speech enhancement Noise suppression experiments Audio super-resolution experiments Summary 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
48 Non-parametric synthesis for speech enhancement Audio super-resolution experiments Original clean speech Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
49 Non-parametric synthesis for speech enhancement Audio super-resolution experiments Reverberated, compressed, 20% packet loss Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
50 Non-parametric synthesis for speech enhancement Audio super-resolution experiments NMF-based bandwidth expansion output Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
51 Non-parametric synthesis for speech enhancement Audio super-resolution experiments Concatenative resynthesis output Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
52 Non-parametric synthesis for speech enhancement Audio super-resolution experiments Original clean speech Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
53 Non-parametric synthesis for speech enhancement Audio super-resolution experiments Subjective quality is high Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
54 Non-parametric synthesis for speech enhancement Audio super-resolution experiments Subjective quality is high MUSHRA Score Clean Clean (hid) Rev Rev 8kHz RevOpusL20 RevOpusL20 (hid) Input NMF Concat CleanAmr RevAmr RevOpusL20 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
55 Non-parametric synthesis for speech enhancement Audio super-resolution experiments Subjective intelligibility is good Correct words (%) Clean Rev Rev 8kHz RevOpusL20 Input NMF Concat CleanAmr RevAmr RevOpusL20 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
56 Non-parametric synthesis for speech enhancement Summary Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement Overview Deep neural network as nonlinear distance function Using this DNN for speech enhancement Noise suppression experiments Audio super-resolution experiments Summary 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
57 Non-parametric synthesis for speech enhancement Summary Summary Concatenative synthesizer, DNN as noise-robust selection function Instead of modifying noisy speech, replace it completely eliminates noise, except for synthesis errors produces high quality, natural-sounding speech General robust supervised nonlinear signal mapping framework Data-e cient to train and adaptable to new talkers Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
58 Non-parametric synthesis for speech enhancement Summary Future applications Generalize to audio-visual speech recognition Label dictionary elements ahead of time to enable noise-robust non-parametric speech recognition noise-robust pitch tracking noise-robust speaker identification Incorporate language model into transition cost Develop e cient search mechanisms for large-vocabulary dictionaries Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
59 Parametric synthesis for speech recognition Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition Overview Algorithm Results Summary 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
60 Parametric synthesis for speech recognition Overview Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition Overview Algorithm Results Summary 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
61 Parametric synthesis for speech recognition Overview Mask-based source separation: Noisy Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
62 Parametric synthesis for speech recognition Overview Mask-based source separation: Masked Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
63 Parametric synthesis for speech recognition Overview Disrupts speech features: Noisy MFCCs He said such products would be marketed by other companies with experience him at this month. Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
64 Parametric synthesis for speech recognition Overview Disrupts speech features: Masked MFCCs He said such products would be marketed by other companies with experience him at this month. Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
65 Parametric synthesis for speech recognition Overview Disrupts speech features: Clean MFCCs He said such products would be marketed by other companies with experience in that business. Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
66 Parametric synthesis for speech recognition Overview Estimate better features using a strong prior model He said such products would be marketed by other companies with experience in that business. Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
67 Parametric synthesis for speech recognition Overview Our approach: Analysis-by-synthesis Synthesize speech signal so that it looks like the observation looks like speech Itakura-Saito divergence compares prediction with noisy observation Recognizer gives likelihood of speech-ness Both easy to optimize using gradient descent Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
68 Parametric synthesis for speech recognition Overview Speech recognizer includes lots of information Large vocabulary continuous speech recognizer captures: Acoustics of speech sounds The e ect of neighboring speech sounds Pronunciation of words Order of words Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
69 Parametric synthesis for speech recognition Algorithm Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition Overview Algorithm Results Summary 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
70 Parametric synthesis for speech recognition Algorithm Optimization over speech features x: optimization state: MFCCs, 10,000 dimensions y(x): ASR features derived from x M: mask provided a priori by another source separator min x n o L(x; M) =min (1 ) L I (x; M) + L H (y(x)) x Total cost Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
71 Parametric synthesis for speech recognition Algorithm Optimization over speech features x: optimization state: MFCCs, 10,000 dimensions y(x): ASR features derived from x M: mask provided a priori by another source separator min x n o L(x; M) =min (1 ) L I (x; M) + L H (y(x)) x Total cost Distance to noisy observation Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
72 Parametric synthesis for speech recognition Algorithm Optimization over speech features x: optimization state: MFCCs, 10,000 dimensions y(x): ASR features derived from x M: mask provided a priori by another source separator min x n o L(x; M) =min (1 ) L I (x; M) + L H (y(x)) x Total cost Distance to noisy observation Negative log likelihood under recognizer Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
73 Parametric synthesis for speech recognition Algorithm Analysis of audio meets resynthesis of MFCCs at mask Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
74 Parametric synthesis for speech recognition Algorithm L I (x; M): Distance to noisy observation Resynthesize MFCCs to power spectrum, where mask was computed Do mask-aware comparison in that domain: weighted Itakura-Saito between resynthesis, S!t (x), and noisy observation, S weighted by mask, M L I (x; M) =D M (S k S) = X!,t M!t S!t S!t (x) Does not require modeling speech excitation Numerically di erentiable with respect to x log S!t S!t (x) 1 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
75 Parametric synthesis for speech recognition Algorithm L H (y(x)): Likelihood under recognizer Large vocabulary continuous speech recognizer big hidden Markov model (HMM) approximated by the lattice of likely paths Closed form gradient with respect to x Serves as a model of clean MFCC sequences Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
76 Parametric synthesis for speech recognition Algorithm L H (y(x)): Likelihood under recognizer Large vocabulary continuous speech recognizer big hidden Markov model (HMM) approximated by the lattice of likely paths Closed form gradient with respect to x Serves as a model of clean MFCC sequences Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
77 Parametric synthesis for speech recognition Algorithm Optimization State space of approximately ,000 dimensions Quasi-Newton optimization, BFGS gradient plus approximate second-order information Closed form gradient of HMM likelihood using a forward-backward algorithm Numerical gradient of IS divergence independent costs and gradients for each frame Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
78 Parametric synthesis for speech recognition Results Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition Overview Algorithm Results Summary 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
79 Parametric synthesis for speech recognition Results Experiment AURORA4 corpus read Wall Street Journal sentences (5000 word vocabulary) six environmental noise types SNRs between 5 and 15 db Masks from ideal binary mask and estimated ratio mask 7 7 Arun Narayanan and DeLiang Wang. Ideal ratio mask estimation using deep neural networks for robust speech recognition. In Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on, pages IEEE, May 2013 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
80 Parametric synthesis for speech recognition Results Recognition results Word error rate (%) averaged across noise type Mask Direct A-by-S Noisy Estimated Oracle Clean 9.54 Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
81 Parametric synthesis for speech recognition Results Reconstruction results Itakura-Saito divergence between resynthesized speech and original Mask Direct A-by-S Noisy Estimated Oracle Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
82 Parametric synthesis for speech recognition Results Resynthesis gets closer to reliable regions Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
83 Parametric synthesis for speech recognition Results Resynthesis gets closer to reliable regions Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
84 Parametric synthesis for speech recognition Results Resynthesis gets closer to reliable regions Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
85 Parametric synthesis for speech recognition Results Resynthesis gets closer to reliable regions Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
86 Parametric synthesis for speech recognition Summary Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition Overview Algorithm Results Summary 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
87 Parametric synthesis for speech recognition Summary Summary Use a full recognizer as a prior model for clean speech Synthesize from MFCCs to the domain of the mask Adjust synthesis of speech signal so that it looks like the observation looks like speech Reduces recognition errors, distance to clean utterance Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
88 Parametric synthesis for speech recognition Summary Future directions Apply to DNN-based acoustic models Model speech excitation for full resynthesis of clean speech Model multiple simultaneous speakers and estimate masks jointly Combine with similar binaural model to include spatial clustering Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
89 Summary Outline 1 Motivation: need for noise robustness 2 Non-parametric synthesis for speech enhancement 3 Parametric synthesis for speech recognition 4 Summary Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
90 Summary Summary Synthesizers provide strong prior information Non-parametric synthesis models for high quality learned nonlinear matching function for perceptually motivated features Parametric synthesis models for e cient representation strong, di erentiable prior model of speech Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
91 Summary Summary Synthesizers provide strong prior information Non-parametric synthesis models for high quality learned nonlinear matching function for perceptually motivated features Parametric synthesis models for e cient representation strong, di erentiable prior model of speech Thanks! Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
92 Summary Summary Synthesizers provide strong prior information Non-parametric synthesis models for high quality learned nonlinear matching function for perceptually motivated features Parametric synthesis models for e cient representation strong, di erentiable prior model of speech Thanks! Any questions? Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 73
93 Parametric synthesis for separation Outline 5 Parametric synthesis for separation Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 3
94 Parametric synthesis for separation Re-estimate mask using resynthesis: Original Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 3
95 Parametric synthesis for separation Re-estimate mask using resynthesis: Re-estimate Michael Mandel (Brooklyn College) Analysis-by-synthesis Sept 8, / 3
ADVANCES IN DEEP NEURAL NETWORK APPROACHES TO SPEAKER RECOGNITION
ADVANCES IN DEEP NEURAL NETWORK APPROACHES TO SPEAKER RECOGNITION Mitchell McLaren 1, Yun Lei 1, Luciana Ferrer 2 1 Speech Technology and Research Laboratory, SRI International, California, USA 2 Departamento
Robust Speech Recognition using DNN-HMM Acoustic Model Combining Noise-aware training with Spectral Subtraction
INTERSPEECH 2015 Robust Speech Recognition using DNN-HMM Acoustic Model Combining Noise-aware training with Spectral Subtraction Akihiro Abe, Kazumasa Yamamoto, Seiichi Nakagawa Department of Computer
Speech Recognition at ICSI: Broadcast News and beyond
Speech Recognition at ICSI: Broadcast News and beyond Dan Ellis International Computer Science Institute, Berkeley CA Outline 1 2 3 The DARPA Broadcast News task Aspects of ICSI
A study of speaker adaptation for DNN-based speech synthesis
A study of speaker adaptation for DNN-based speech synthesis Zhizheng Wu, Pawel Swietojanski, Christophe Veaux, Steve Renals, Simon King The Centre for Speech Technology Research (CSTR) University of Edinburgh,
Eli Yamamoto, Satoshi Nakamura, Kiyohiro Shikano. Graduate School of Information Science, Nara Institute of Science & Technology
ISCA Archive SUBJECTIVE EVALUATION FOR HMM-BASED SPEECH-TO-LIP MOVEMENT SYNTHESIS Eli Yamamoto, Satoshi Nakamura, Kiyohiro Shikano Graduate School of Information Science, Nara Institute of Science & Technology
Modeling function word errors in DNN-HMM based LVCSR systems
Modeling function word errors in DNN-HMM based LVCSR systems Melvin Jose Johnson Premkumar, Ankur Bapna and Sree Avinash Parchuri Department of Computer Science Department of Electrical Engineering Stanford
A New Perspective on Combining GMM and DNN Frameworks for Speaker Adaptation
A New Perspective on Combining GMM and DNN Frameworks for Speaker Adaptation SLSP-2016 October 11-12 Natalia Tomashenko 1,2,3 natalia.tomashenko@univ-lemans.fr Yuri Khokhlov 3 khokhlov@speechpro.com Yannick
Speech Emotion Recognition Using Support Vector Machine
Speech Emotion Recognition Using Support Vector Machine Yixiong Pan, Peipei Shen and Liping Shen Department of Computer Technology Shanghai JiaoTong University, Shanghai, China panyixiong@sjtu.edu.cn,
WHEN THERE IS A mismatch between the acoustic
808 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 14, NO. 3, MAY 2006 Optimization of Temporal Filters for Constructing Robust Features in Speech Recognition Jeih-Weih Hung, Member,
Semi-Supervised GMM and DNN Acoustic Model Training with Multi-system Combination and Confidence Re-calibration
INTERSPEECH 2013 Semi-Supervised GMM and DNN Acoustic Model Training with Multi-system Combination and Confidence Re-calibration Yan Huang, Dong Yu, Yifan Gong, and Chaojun Liu Microsoft Corporation, One
Segregation of Unvoiced Speech from Nonspeech Interference
Technical Report OSU-CISRC-8/7-TR63 Department of Computer Science and Engineering The Ohio State University Columbus, OH 4321-1277 FTP site: ftp.cse.ohio-state.edu Login: anonymous Directory: pub/tech-report/27
Modeling function word errors in DNN-HMM based LVCSR systems
Modeling function word errors in DNN-HMM based LVCSR systems Melvin Jose Johnson Premkumar, Ankur Bapna and Sree Avinash Parchuri Department of Computer Science Department of Electrical Engineering Stanford
Calibration of Confidence Measures in Speech Recognition
Submitted to IEEE Trans on Audio, Speech, and Language, July 2010 1 Calibration of Confidence Measures in Speech Recognition Dong Yu, Senior Member, IEEE, Jinyu Li, Member, IEEE, Li Deng, Fellow, IEEE
Likelihood-Maximizing Beamforming for Robust Hands-Free Speech Recognition
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Likelihood-Maximizing Beamforming for Robust Hands-Free Speech Recognition Seltzer, M.L.; Raj, B.; Stern, R.M. TR2004-088 December 2004 Abstract
The NICT/ATR speech synthesis system for the Blizzard Challenge 2008
The NICT/ATR speech synthesis system for the Blizzard Challenge 2008 Ranniery Maia 1,2, Jinfu Ni 1,2, Shinsuke Sakai 1,2, Tomoki Toda 1,3, Keiichi Tokuda 1,4 Tohru Shimizu 1,2, Satoshi Nakamura 1,2 1 National
Learning Methods in Multilingual Speech Recognition
Learning Methods in Multilingual Speech Recognition Hui Lin Department of Electrical Engineering University of Washington Seattle, WA 98125 linhui@u.washington.edu Li Deng, Jasha Droppo, Dong Yu, and Alex
PREDICTING SPEECH RECOGNITION CONFIDENCE USING DEEP LEARNING WITH WORD IDENTITY AND SCORE FEATURES
PREDICTING SPEECH RECOGNITION CONFIDENCE USING DEEP LEARNING WITH WORD IDENTITY AND SCORE FEATURES Po-Sen Huang, Kshitiz Kumar, Chaojun Liu, Yifan Gong, Li Deng Department of Electrical and Computer Engineering,
Speech Segmentation Using Probabilistic Phonetic Feature Hierarchy and Support Vector Machines
Speech Segmentation Using Probabilistic Phonetic Feature Hierarchy and Support Vector Machines Amit Juneja and Carol Espy-Wilson Department of Electrical and Computer Engineering University of Maryland,
Lecture 1: Machine Learning Basics
1/69 Lecture 1: Machine Learning Basics Ali Harakeh University of Waterloo WAVE Lab ali.harakeh@uwaterloo.ca May 1, 2017 2/69 Overview 1 Learning Algorithms 2 Capacity, Overfitting, and Underfitting 3
Human Emotion Recognition From Speech
RESEARCH ARTICLE OPEN ACCESS Human Emotion Recognition From Speech Miss. Aparna P. Wanare*, Prof. Shankar N. Dandare *(Department of Electronics & Telecommunication Engineering, Sant Gadge Baba Amravati
A Comparison of DHMM and DTW for Isolated Digits Recognition System of Arabic Language
A Comparison of DHMM and DTW for Isolated Digits Recognition System of Arabic Language Z.HACHKAR 1,3, A. FARCHI 2, B.MOUNIR 1, J. EL ABBADI 3 1 Ecole Supérieure de Technologie, Safi, Morocco. zhachkar2000@yahoo.fr.
Noise-Adaptive Perceptual Weighting in the AMR-WB Encoder for Increased Speech Loudness in Adverse Far-End Noise Conditions
26 24th European Signal Processing Conference (EUSIPCO) Noise-Adaptive Perceptual Weighting in the AMR-WB Encoder for Increased Speech Loudness in Adverse Far-End Noise Conditions Emma Jokinen Department
Autoregressive product of multi-frame predictions can improve the accuracy of hybrid models
Autoregressive product of multi-frame predictions can improve the accuracy of hybrid models Navdeep Jaitly 1, Vincent Vanhoucke 2, Geoffrey Hinton 1,2 1 University of Toronto 2 Google Inc. ndjaitly@cs.toronto.edu,
Segmental Conditional Random Fields with Deep Neural Networks as Acoustic Models for First-Pass Word Recognition
Segmental Conditional Random Fields with Deep Neural Networks as Acoustic Models for First-Pass Word Recognition Yanzhang He, Eric Fosler-Lussier Department of Computer Science and Engineering The hio
Speech Synthesis in Noisy Environment by Enhancing Strength of Excitation and Formant Prominence
INTERSPEECH September,, San Francisco, USA Speech Synthesis in Noisy Environment by Enhancing Strength of Excitation and Formant Prominence Bidisha Sharma and S. R. Mahadeva Prasanna Department of Electronics
Unsupervised Acoustic Model Training for Simultaneous Lecture Translation in Incremental and Batch Mode
Unsupervised Acoustic Model Training for Simultaneous Lecture Translation in Incremental and Batch Mode Diploma Thesis of Michael Heck At the Department of Informatics Karlsruhe Institute of Technology
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 17, NO. 3, MARCH
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 17, NO. 3, MARCH 2009 423 Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition George
AUTOMATIC DETECTION OF PROLONGED FRICATIVE PHONEMES WITH THE HIDDEN MARKOV MODELS APPROACH 1. INTRODUCTION
JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 11/2007, ISSN 1642-6037 Marek WIŚNIEWSKI *, Wiesława KUNISZYK-JÓŹKOWIAK *, Elżbieta SMOŁKA *, Waldemar SUSZYŃSKI * HMM, recognition, speech, disorders
Learning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models
Learning Structural Correspondences Across Different Linguistic Domains with Synchronous Neural Language Models Stephan Gouws and GJ van Rooyen MIH Medialab, Stellenbosch University SOUTH AFRICA {stephan,gvrooyen}@ml.sun.ac.za
On the Formation of Phoneme Categories in DNN Acoustic Models
On the Formation of Phoneme Categories in DNN Acoustic Models Tasha Nagamine Department of Electrical Engineering, Columbia University T. Nagamine Motivation Large performance gap between humans and state-
A NOVEL SCHEME FOR SPEAKER RECOGNITION USING A PHONETICALLY-AWARE DEEP NEURAL NETWORK. Yun Lei Nicolas Scheffer Luciana Ferrer Mitchell McLaren
A NOVEL SCHEME FOR SPEAKER RECOGNITION USING A PHONETICALLY-AWARE DEEP NEURAL NETWORK Yun Lei Nicolas Scheffer Luciana Ferrer Mitchell McLaren Speech Technology and Research Laboratory, SRI International,
Analysis of Emotion Recognition System through Speech Signal Using KNN & GMM Classifier
IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) e-issn: 2278-2834,p- ISSN: 2278-8735.Volume 10, Issue 2, Ver.1 (Mar - Apr.2015), PP 55-61 www.iosrjournals.org Analysis of Emotion
STUDIES WITH FABRICATED SWITCHBOARD DATA: EXPLORING SOURCES OF MODEL-DATA MISMATCH
STUDIES WITH FABRICATED SWITCHBOARD DATA: EXPLORING SOURCES OF MODEL-DATA MISMATCH Don McAllaster, Larry Gillick, Francesco Scattone, Mike Newman Dragon Systems, Inc. 320 Nevada Street Newton, MA 02160
have to be modeled) or isolated words. Output of the system is a grapheme-tophoneme conversion system which takes as its input the spelling of words,
A Language-Independent, Data-Oriented Architecture for Grapheme-to-Phoneme Conversion Walter Daelemans and Antal van den Bosch Proceedings ESCA-IEEE speech synthesis conference, New York, September 1994
Word Segmentation of Off-line Handwritten Documents
Word Segmentation of Off-line Handwritten Documents Chen Huang and Sargur N. Srihari {chuang5, srihari}@cedar.buffalo.edu Center of Excellence for Document Analysis and Recognition (CEDAR), Department
INVESTIGATION OF UNSUPERVISED ADAPTATION OF DNN ACOUSTIC MODELS WITH FILTER BANK INPUT
INVESTIGATION OF UNSUPERVISED ADAPTATION OF DNN ACOUSTIC MODELS WITH FILTER BANK INPUT Takuya Yoshioka,, Anton Ragni, Mark J. F. Gales Cambridge University Engineering Department, Cambridge, UK NTT Communication
Module 12. Machine Learning. Version 2 CSE IIT, Kharagpur
Module 12 Machine Learning 12.1 Instructional Objective The students should understand the concept of learning systems Students should learn about different aspects of a learning system Students should
Deep Neural Network Language Models
Deep Neural Network Language Models Ebru Arısoy, Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran IBM T.J. Watson Research Center Yorktown Heights, NY, 10598, USA {earisoy, tsainath, bedk, bhuvana}@us.ibm.com
UNIDIRECTIONAL LONG SHORT-TERM MEMORY RECURRENT NEURAL NETWORK WITH RECURRENT OUTPUT LAYER FOR LOW-LATENCY SPEECH SYNTHESIS. Heiga Zen, Haşim Sak
UNIDIRECTIONAL LONG SHORT-TERM MEMORY RECURRENT NEURAL NETWORK WITH RECURRENT OUTPUT LAYER FOR LOW-LATENCY SPEECH SYNTHESIS Heiga Zen, Haşim Sak Google fheigazen,hasimg@google.com ABSTRACT Long short-term
BUILDING CONTEXT-DEPENDENT DNN ACOUSTIC MODELS USING KULLBACK-LEIBLER DIVERGENCE-BASED STATE TYING
BUILDING CONTEXT-DEPENDENT DNN ACOUSTIC MODELS USING KULLBACK-LEIBLER DIVERGENCE-BASED STATE TYING Gábor Gosztolya 1, Tamás Grósz 1, László Tóth 1, David Imseng 2 1 MTA-SZTE Research Group on Artificial
Python Machine Learning
Python Machine Learning Unlock deeper insights into machine learning with this vital guide to cuttingedge predictive analytics Sebastian Raschka [ PUBLISHING 1 open source I community experience distilled
Design Of An Automatic Speaker Recognition System Using MFCC, Vector Quantization And LBG Algorithm
Design Of An Automatic Speaker Recognition System Using MFCC, Vector Quantization And LBG Algorithm Prof. Ch.Srinivasa Kumar Prof. and Head of department. Electronics and communication Nalanda Institute
International Journal of Computational Intelligence and Informatics, Vol. 1 : No. 4, January - March 2012
Text-independent Mono and Cross-lingual Speaker Identification with the Constraint of Limited Data Nagaraja B G and H S Jayanna Department of Information Science and Engineering Siddaganga Institute of
CSL465/603 - Machine Learning
CSL465/603 - Machine Learning Fall 2016 Narayanan C Krishnan ckn@iitrpr.ac.in Introduction CSL465/603 - Machine Learning 1 Administrative Trivia Course Structure 3-0-2 Lecture Timings Monday 9.55-10.45am
DIRECT ADAPTATION OF HYBRID DNN/HMM MODEL FOR FAST SPEAKER ADAPTATION IN LVCSR BASED ON SPEAKER CODE
2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) DIRECT ADAPTATION OF HYBRID DNN/HMM MODEL FOR FAST SPEAKER ADAPTATION IN LVCSR BASED ON SPEAKER CODE Shaofei Xue 1
Improvements to the Pruning Behavior of DNN Acoustic Models
Improvements to the Pruning Behavior of DNN Acoustic Models Matthias Paulik Apple Inc., Infinite Loop, Cupertino, CA 954 mpaulik@apple.com Abstract This paper examines two strategies that positively influence
A Neural Network GUI Tested on Text-To-Phoneme Mapping
A Neural Network GUI Tested on Text-To-Phoneme Mapping MAARTEN TROMPPER Universiteit Utrecht m.f.a.trompper@students.uu.nl Abstract Text-to-phoneme (T2P) mapping is a necessary step in any speech synthesis
SEMI-SUPERVISED ENSEMBLE DNN ACOUSTIC MODEL TRAINING
SEMI-SUPERVISED ENSEMBLE DNN ACOUSTIC MODEL TRAINING Sheng Li 1, Xugang Lu 2, Shinsuke Sakai 1, Masato Mimura 1 and Tatsuya Kawahara 1 1 School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501,
Investigation on Mandarin Broadcast News Speech Recognition
Investigation on Mandarin Broadcast News Speech Recognition Mei-Yuh Hwang 1, Xin Lei 1, Wen Wang 2, Takahiro Shinozaki 1 1 Univ. of Washington, Dept. of Electrical Engineering, Seattle, WA 98195 USA 2
Analysis of Speech Recognition Models for Real Time Captioning and Post Lecture Transcription
Analysis of Speech Recognition Models for Real Time Captioning and Post Lecture Transcription Wilny Wilson.P M.Tech Computer Science Student Thejus Engineering College Thrissur, India. Sindhu.S Computer
BAUM-WELCH TRAINING FOR SEGMENT-BASED SPEECH RECOGNITION. Han Shu, I. Lee Hetherington, and James Glass
BAUM-WELCH TRAINING FOR SEGMENT-BASED SPEECH RECOGNITION Han Shu, I. Lee Hetherington, and James Glass Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge,
The Good Judgment Project: A large scale test of different methods of combining expert predictions
The Good Judgment Project: A large scale test of different methods of combining expert predictions Lyle Ungar, Barb Mellors, Jon Baron, Phil Tetlock, Jaime Ramos, Sam Swift The University of Pennsylvania
OCR for Arabic using SIFT Descriptors With Online Failure Prediction
OCR for Arabic using SIFT Descriptors With Online Failure Prediction Andrey Stolyarenko, Nachum Dershowitz The Blavatnik School of Computer Science Tel Aviv University Tel Aviv, Israel Email: stloyare@tau.ac.il,
arxiv: v1 [cs.lg] 7 Apr 2015
![arxiv: v1 [cs.lg] 7 Apr 2015](/thumbs/71/66174892.jpg "arxiv: v1 [cs.lg] 7 Apr 2015")
Transferring Knowledge from a RNN to a DNN William Chan 1, Nan Rosemary Ke 1, Ian Lane 1,2 Carnegie Mellon University 1 Electrical and Computer Engineering, 2 Language Technologies Institute Equal contribution
THE world surrounding us involves multiple modalities
1 Multimodal Machine Learning: A Survey and Taxonomy Tadas Baltrušaitis, Chaitanya Ahuja, and Louis-Philippe Morency arxiv:1705.09406v2 [cs.lg] 1 Aug 2017 Abstract Our experience of the world is multimodal
Phonetic- and Speaker-Discriminant Features for Speaker Recognition. Research Project
Phonetic- and Speaker-Discriminant Features for Speaker Recognition by Lara Stoll Research Project Submitted to the Department of Electrical Engineering and Computer Sciences, University of California
QuickStroke: An Incremental On-line Chinese Handwriting Recognition System
QuickStroke: An Incremental On-line Chinese Handwriting Recognition System Nada P. Matić John C. Platt Λ Tony Wang y Synaptics, Inc. 2381 Bering Drive San Jose, CA 95131, USA Abstract This paper presents
Speech Recognition using Acoustic Landmarks and Binary Phonetic Feature Classifiers
Speech Recognition using Acoustic Landmarks and Binary Phonetic Feature Classifiers October 31, 2003 Amit Juneja Department of Electrical and Computer Engineering University of Maryland, College Park,
Evolution of Symbolisation in Chimpanzees and Neural Nets
Evolution of Symbolisation in Chimpanzees and Neural Nets Angelo Cangelosi Centre for Neural and Adaptive Systems University of Plymouth (UK) a.cangelosi@plymouth.ac.uk Introduction Animal communication
Radius STEM Readiness TM
Curriculum Guide Radius STEM Readiness TM While today s teens are surrounded by technology, we face a stark and imminent shortage of graduates pursuing careers in Science, Technology, Engineering, and
ACOUSTIC EVENT DETECTION IN REAL LIFE RECORDINGS
ACOUSTIC EVENT DETECTION IN REAL LIFE RECORDINGS Annamaria Mesaros 1, Toni Heittola 1, Antti Eronen 2, Tuomas Virtanen 1 1 Department of Signal Processing Tampere University of Technology Korkeakoulunkatu
Automatic Pronunciation Checker
Institut für Technische Informatik und Kommunikationsnetze Eidgenössische Technische Hochschule Zürich Swiss Federal Institute of Technology Zurich Ecole polytechnique fédérale de Zurich Politecnico federale
INPE São José dos Campos
INPE-5479 PRE/1778 MONLINEAR ASPECTS OF DATA INTEGRATION FOR LAND COVER CLASSIFICATION IN A NEDRAL NETWORK ENVIRONNENT Maria Suelena S. Barros Valter Rodrigues INPE São José dos Campos 1993 SECRETARIA
Malicious User Suppression for Cooperative Spectrum Sensing in Cognitive Radio Networks using Dixon s Outlier Detection Method
Malicious User Suppression for Cooperative Spectrum Sensing in Cognitive Radio Networks using Dixon s Outlier Detection Method Sanket S. Kalamkar and Adrish Banerjee Department of Electrical Engineering
Author's personal copy
Speech Communication 49 (2007) 588 601 www.elsevier.com/locate/specom Abstract Subjective comparison and evaluation of speech enhancement Yi Hu, Philipos C. Loizou * Department of Electrical Engineering,
The IRISA Text-To-Speech System for the Blizzard Challenge 2017
The IRISA Text-To-Speech System for the Blizzard Challenge 2017 Pierre Alain, Nelly Barbot, Jonathan Chevelu, Gwénolé Lecorvé, Damien Lolive, Claude Simon, Marie Tahon IRISA, University of Rennes 1 (ENSSAT),
UTD-CRSS Systems for 2012 NIST Speaker Recognition Evaluation
UTD-CRSS Systems for 2012 NIST Speaker Recognition Evaluation Taufiq Hasan Gang Liu Seyed Omid Sadjadi Navid Shokouhi The CRSS SRE Team John H.L. Hansen Keith W. Godin Abhinav Misra Ali Ziaei Hynek Bořil
Distributed Learning of Multilingual DNN Feature Extractors using GPUs
Distributed Learning of Multilingual DNN Feature Extractors using GPUs Yajie Miao, Hao Zhang, Florian Metze Language Technologies Institute, School of Computer Science, Carnegie Mellon University Pittsburgh,
LOW-RANK AND SPARSE SOFT TARGETS TO LEARN BETTER DNN ACOUSTIC MODELS
LOW-RANK AND SPARSE SOFT TARGETS TO LEARN BETTER DNN ACOUSTIC MODELS Pranay Dighe Afsaneh Asaei Hervé Bourlard Idiap Research Institute, Martigny, Switzerland École Polytechnique Fédérale de Lausanne (EPFL),
Lip reading: Japanese vowel recognition by tracking temporal changes of lip shape
Lip reading: Japanese vowel recognition by tracking temporal changes of lip shape Koshi Odagiri 1, and Yoichi Muraoka 1 1 Graduate School of Fundamental/Computer Science and Engineering, Waseda University,
Master s Programme in Computer, Communication and Information Sciences, Study guide , ELEC Majors
Master s Programme in Computer, Communication and Information Sciences, Study guide 2015-2016, ELEC Majors Sisällysluettelo PS=pääsivu, AS=alasivu PS: 1 Acoustics and Audio Technology... 4 Objectives...
An Online Handwriting Recognition System For Turkish
An Online Handwriting Recognition System For Turkish Esra Vural, Hakan Erdogan, Kemal Oflazer, Berrin Yanikoglu Sabanci University, Tuzla, Istanbul, Turkey 34956 ABSTRACT Despite recent developments in
Unsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model
Unsupervised Learning of Word Semantic Embedding using the Deep Structured Semantic Model Xinying Song, Xiaodong He, Jianfeng Gao, Li Deng Microsoft Research, One Microsoft Way, Redmond, WA 98052, U.S.A.
Lecture 9: Speech Recognition
EE E6820: Speech & Audio Processing & Recognition Lecture 9: Speech Recognition 1 Recognizing speech 2 Feature calculation Dan Ellis Michael Mandel 3 Sequence
Generative models and adversarial training
Day 4 Lecture 1 Generative models and adversarial training Kevin McGuinness kevin.mcguinness@dcu.ie Research Fellow Insight Centre for Data Analytics Dublin City University What is a generative model?
Body-Conducted Speech Recognition and its Application to Speech Support System
Body-Conducted Speech Recognition and its Application to Speech Support System 4 Shunsuke Ishimitsu Hiroshima City University Japan 1. Introduction In recent years, speech recognition systems have been
Digital Signal Processing: Speaker Recognition Final Report (Complete Version)
Digital Signal Processing: Speaker Recognition Final Report (Complete Version) Xinyu Zhou, Yuxin Wu, and Tiezheng Li Tsinghua University Contents 1 Introduction 1 2 Algorithms 2 2.1 VAD..................................................
Class-Discriminative Weighted Distortion Measure for VQ-Based Speaker Identification
Class-Discriminative Weighted Distortion Measure for VQ-Based Speaker Identification Tomi Kinnunen and Ismo Kärkkäinen University of Joensuu, Department of Computer Science, P.O. Box 111, 80101 JOENSUU,
OPTIMIZATINON OF TRAINING SETS FOR HEBBIAN-LEARNING- BASED CLASSIFIERS
OPTIMIZATINON OF TRAINING SETS FOR HEBBIAN-LEARNING- BASED CLASSIFIERS Václav Kocian, Eva Volná, Michal Janošek, Martin Kotyrba University of Ostrava Department of Informatics and Computers Dvořákova 7,
A Reinforcement Learning Variant for Control Scheduling
A Reinforcement Learning Variant for Control Scheduling Aloke Guha Honeywell Sensor and System Development Center 3660 Technology Drive Minneapolis MN 55417 Abstract We present an algorithm based on reinforcement
(Sub)Gradient Descent
(Sub)Gradient Descent CMSC 422 MARINE CARPUAT marine@cs.umd.edu Figures credit: Piyush Rai Logistics Midterm is on Thursday 3/24 during class time closed book/internet/etc, one page of notes. will include
Edinburgh Research Explorer
Edinburgh Research Explorer Personalising speech-to-speech translation Citation for published version: Dines, J, Liang, H, Saheer, L, Gibson, M, Byrne, W, Oura, K, Tokuda, K, Yamagishi, J, King, S, Wester,
Using Articulatory Features and Inferred Phonological Segments in Zero Resource Speech Processing
Using Articulatory Features and Inferred Phonological Segments in Zero Resource Speech Processing Pallavi Baljekar, Sunayana Sitaram, Prasanna Kumar Muthukumar, and Alan W Black Carnegie Mellon University,
Unvoiced Landmark Detection for Segment-based Mandarin Continuous Speech Recognition
Unvoiced Landmark Detection for Segment-based Mandarin Continuous Speech Recognition Hua Zhang, Yun Tang, Wenju Liu and Bo Xu National Laboratory of Pattern Recognition Institute of Automation, Chinese
A comparison of spectral smoothing methods for segment concatenation based speech synthesis
D.T. Chappell, J.H.L. Hansen, "Spectral Smoothing for Speech Segment Concatenation, Speech Communication, Volume 36, Issues 3-4, March 2002, Pages 343-373. A comparison of spectral smoothing methods for
DNN ACOUSTIC MODELING WITH MODULAR MULTI-LINGUAL FEATURE EXTRACTION NETWORKS
DNN ACOUSTIC MODELING WITH MODULAR MULTI-LINGUAL FEATURE EXTRACTION NETWORKS Jonas Gehring 1 Quoc Bao Nguyen 1 Florian Metze 2 Alex Waibel 1,2 1 Interactive Systems Lab, Karlsruhe Institute of Technology;
Model Ensemble for Click Prediction in Bing Search Ads
Model Ensemble for Click Prediction in Bing Search Ads Xiaoliang Ling Microsoft Bing xiaoling@microsoft.com Hucheng Zhou Microsoft Research huzho@microsoft.com Weiwei Deng Microsoft Bing dedeng@microsoft.com
International Journal of Advanced Networking Applications (IJANA) ISSN No. :
International Journal of Advanced Networking Applications (IJANA) ISSN No. : 0975-0290 34 A Review on Dysarthric Speech Recognition Megha Rughani Department of Electronics and Communication, Marwadi Educational
Voice conversion through vector quantization
J. Acoust. Soc. Jpn.(E)11, 2 (1990) Voice conversion through vector quantization Masanobu Abe, Satoshi Nakamura, Kiyohiro Shikano, and Hisao Kuwabara A TR Interpreting Telephony Research Laboratories,
Attributed Social Network Embedding
JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, MAY 2017 1 Attributed Social Network Embedding arxiv:1705.04969v1 [cs.si] 14 May 2017 Lizi Liao, Xiangnan He, Hanwang Zhang, and Tat-Seng Chua Abstract Embedding
Voiceless Stop Consonant Modelling and Synthesis Framework Based on MISO Dynamic System
ARCHIVES OF ACOUSTICS Vol. 42, No. 3, pp. 375 383 (2017) Copyright c 2017 by PAN IPPT DOI: 10.1515/aoa-2017-0039 Voiceless Stop Consonant Modelling and Synthesis Framework Based on MISO Dynamic System
Course Outline. Course Grading. Where to go for help. Academic Integrity. EE-589 Introduction to Neural Networks NN 1 EE
EE-589 Introduction to Neural Assistant Prof. Dr. Turgay IBRIKCI Room # 305 (322) 338 6868 / 139 Wensdays 9:00-12:00 Course Outline The course is divided in two parts: theory and practice. 1. Theory covers
Learning Methods for Fuzzy Systems
Learning Methods for Fuzzy Systems Rudolf Kruse and Andreas Nürnberger Department of Computer Science, University of Magdeburg Universitätsplatz, D-396 Magdeburg, Germany Phone : +49.39.67.876, Fax : +49.39.67.8
Non intrusive multi-biometrics on a mobile device: a comparison of fusion techniques
Non intrusive multi-biometrics on a mobile device: a comparison of fusion techniques Lorene Allano 1*1, Andrew C. Morris 2, Harin Sellahewa 3, Sonia Garcia-Salicetti 1, Jacques Koreman 2, Sabah Jassim
Atypical Prosodic Structure as an Indicator of Reading Level and Text Difficulty
Atypical Prosodic Structure as an Indicator of Reading Level and Text Difficulty Julie Medero and Mari Ostendorf Electrical Engineering Department University of Washington Seattle, WA 98195 USA {jmedero,ostendor}@uw.edu
DOMAIN MISMATCH COMPENSATION FOR SPEAKER RECOGNITION USING A LIBRARY OF WHITENERS. Elliot Singer and Douglas Reynolds
DOMAIN MISMATCH COMPENSATION FOR SPEAKER RECOGNITION USING A LIBRARY OF WHITENERS Elliot Singer and Douglas Reynolds Massachusetts Institute of Technology Lincoln Laboratory {es,dar}@ll.mit.edu ABSTRACT
/$ IEEE
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 17, NO. 8, NOVEMBER 2009 1567 Modeling the Expressivity of Input Text Semantics for Chinese Text-to-Speech Synthesis in a Spoken Dialog
Cross Language Information Retrieval
Cross Language Information Retrieval RAFFAELLA BERNARDI UNIVERSITÀ DEGLI STUDI DI TRENTO P.ZZA VENEZIA, ROOM: 2.05, E-MAIL: BERNARDI@DISI.UNITN.IT Contents 1 Acknowledgment.............................................
Rule Learning With Negation: Issues Regarding Effectiveness
Rule Learning With Negation: Issues Regarding Effectiveness S. Chua, F. Coenen, G. Malcolm University of Liverpool Department of Computer Science, Ashton Building, Ashton Street, L69 3BX Liverpool, United
Speaker recognition using universal background model on YOHO database
Aalborg University Master Thesis project Speaker recognition using universal background model on YOHO database Author: Alexandre Majetniak Supervisor: Zheng-Hua Tan May 31, 2011 The Faculties of Engineering,