On the Formation of Phoneme Categories in DNN Acoustic Models
|
|
|
- Melinda Carroll
- 6 years ago
- Views:
Transcription
1 On the Formation of Phoneme Categories in DNN Acoustic Models Tasha Nagamine Department of Electrical Engineering, Columbia University T. Nagamine
2 Motivation Large performance gap between humans and state- of- the- art ASR systems Computational principles of DNNs remain elusive; they are analytically intractable Improving these models requires a better understanding of their transformations T. Nagamine
3 Introduction to acoustic models acous&c model Dahl et al., IEEE Transactions on Audio, Speech, and Signal Processing 2012
4 Introduction to acoustic models acous&c model Dahl et al., IEEE Transactions on Audio, Speech, and Signal Processing 2012
5 Phonemes Smallest contrastive unit in language e.g., k vs. b in cat/bat ~40-60 in English Output target in acoustic modeling T. Nagamine
6 Phonetic Features Manner of articulation Place of articulation Voicing T. Nagamine
7 Phonetic Features Manner of articulation Place of articulation Voicing T. Nagamine
8 Phonetic Features Manner of articulation same manner (plosive) same place (labial) Place of articulation Voicing /k/ /g/ /p/ /b/ /m/ T. Nagamine
9 Phonetic Features Manner of articulation Place of articulation Voicing /s/ = unvoiced same manner (frica&ve) same place (alveolar) /z/ = voiced T. Nagamine
10 Phonetic Features Dis$nc$ve Features Chomsky, Halle, Stevens T. Nagamine
11 Distinctive Features T. Nagamine
12 Phonemes and phones Phoneme Smallest contrastive unit in language. Abstract idea. Phone Instances of phonemes in actual utterances. Physical segments. Example: pat vs. bat 4 phonemes 6 phones T. Nagamine
13
14 2nd temporal derivative 1st temporal derivative log Mel filterbank coefficients Input Hidden Layers t uw ah dh er k ey s ih z sil ao t uw ah dh er Output k ey s ih z sil ao aa ae ah ao aw ax ay b ch d dh eh er ey f g hh ih iy jh k l m n ng ow oy p r s sh sil t th uh uw v w y z zh Predicted Label Actual Label Feed- forward series of nonlinear transforma&ons
15 2nd temporal derivative 1st temporal derivative log Mel filterbank coefficients Input Hidden Layers t uw ah dh er k ey s ih z sil ao t uw ah dh er Output k ey s ih z sil ao aa ae ah ao aw ax ay b ch d dh eh er ey f g hh ih iy jh k l m n ng ow oy p r s sh sil t th uh uw v w y z zh Predicted Label Actual Label?
16 2nd temporal derivative 1st temporal derivative log Mel filterbank coefficients Input Hidden Layers t uw ah dh er k ey s ih z sil ao t uw ah dh er Output k ey s ih z sil ao aa ae ah ao aw ax ay b ch d dh eh er ey f g hh ih iy jh k l m n ng ow oy p r s sh sil t th uh uw v w y z zh Predicted Label Actual Label?
17 DNN Architecture Input layer 11 frames of 24- dimensional log Mel Xilter bank coefxicients + deltas 2nd temporal derivative 1st temporal derivative log Mel filterbank coefficients Input Hidden Layers t uw ah dh er k ey s ih z sil ao t uw ah dh er Output k ey s ih z sil ao aa ae ah ao aw ax ay b ch d dh eh er ey f g hh ih iy jh k l m n ng ow oy p r s sh sil t th uh uw v w y z zh Predicted Label Actual Label
18 DNN Architecture Input layer 11 frames of 24- dimensional log Mel Xilter bank coefxicients + deltas 5 sigmoid hidden layers 256 nodes each; fully connected feed- forward 2nd temporal derivative 1st temporal derivative log Mel filterbank coefficients Input Hidden Layers t uw ah dh er k ey s ih z sil ao t uw ah dh er Output k ey s ih z sil ao aa ae ah ao aw ax ay b ch d dh eh er ey f g hh ih iy jh k l m n ng ow oy p r s sh sil t th uh uw v w y z zh Predicted Label Actual Label
19 DNN Architecture Input layer 11 frames of 24- dimensional log Mel Xilter bank coefxicients + deltas 5 sigmoid hidden layers 256 nodes each; fully connected feed- forward Softmax output layer 41 nodes for 40 phonemes and silence; context independent 2nd temporal derivative 1st temporal derivative log Mel filterbank coefficients Input Hidden Layers t uw ah dh er k ey s ih z sil ao t uw ah dh er Output k ey s ih z sil ao aa ae ah ao aw ax ay b ch d dh eh er ey f g hh ih iy jh k l m n ng ow oy p r s sh sil t th uh uw v w y z zh Predicted Label Actual Label
20 Speech stimuli & DNN activations Input HL 1-3 Hidden 4 Layer Activation HL 5 Output (label) t uw ah dh er k ey s ih z sil ao Actual Label
21 Speech stimuli & DNN activations Input HL 1-3 Hidden 4 Layer Activation HL 5 Output (label) response to t t uw ah dh er k ey s ih z sil ao Actual Label
22 Speech stimuli & DNN activations Input HL 1-3 Hidden 4 Layer Activation HL 5 Output (label) response to z t uw ah dh er k ey s ih z sil ao Actual Label
23 Summary of Xindings 1. Nodes are selective to phonetic features at the individual and population level
24 = phoneme onset
25 manner of ar0cula0on (closure) ch, jh, g, k b, p d, t
26 manner of ar0cula0on (closure) + unvoiced ch k p t
27 place of ar0cula0on (labial) f, v b, p m
28 Phoneme Selec0vity Index (PSI)
29 Hidden Layer 1 nodes
30 Hidden Layer 1 phonemes
31 Hidden Layer 1
32 Hidden Layer 1
33 Hidden Layer 1 Hidden Layer 5
34 Neural responses to speech in human superior temporal gyrus (STG) o Mesgarani et al., Science 2014
35 Examples of average phoneme responses in STG Plosives! Fricatives! Low vowels! High vowels! Nasals! Phoneme selec&vity index Diversity of responses: Strong preference at various STG sites to specixic phoneme groups with shared attributes Mesgarani et al., Science 2014
36 Clustering the PSI vectors Global structures (population) Local structures (single electrode) Place Manner Mesgarani et al., Science 2014
37 Summary of Xindings 1. Single nodes and populations of nodes in a layer are selective to phonetic features 2. Phonetic feature encoding becomes more explicit in deeper layers
38
39
40 Summary of Xindings 1. Single nodes and populations of nodes in a layer are selective to phonetic features 2. Node selectivity to phonetic features becomes more explicit in deeper layers 3. Network invariance is learned through explicit representation of sources of variability
41 phoneme = t example selec0vity for three nodes (N1, N2, N3)
42 phoneme = t example selec0vity for three nodes (N1, N2, N3) t
43 phoneme = t example selec0vity for three nodes (N1, N2, N3) phoneme instances t clustering
44 phoneme = t example selec0vity for three nodes (N1, N2, N3) nodes t clustering
45
46
47
48 Summary of Xindings 1. Single nodes and populations of nodes in a layer are selective to phonetic features 2. Node selectivity to phonetic features becomes more explicit in deeper layers 3. Network invariance is learned through explicit representation of sources of variability
49 Questions?
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,
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,
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,
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
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
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
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
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,
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
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
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,
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
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 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,
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
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
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
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
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
Speaker Identification by Comparison of Smart Methods. Abstract
Journal of mathematics and computer science 10 (2014), 61-71 Speaker Identification by Comparison of Smart Methods Ali Mahdavi Meimand Amin Asadi Majid Mohamadi Department of Electrical Department of Computer
The ABCs of O-G. Materials Catalog. Skills Workbook. Lesson Plans for Teaching The Orton-Gillingham Approach in Reading and Spelling
2008 Intermediate Level Skills Workbook Group 2 Groups 1 & 2 The ABCs of O-G The Flynn System by Emi Flynn Lesson Plans for Teaching The Orton-Gillingham Approach in Reading and Spelling The ABCs of O-G
Books Effective Literacy Y5-8 Learning Through Talk Y4-8 Switch onto Spelling Spelling Under Scrutiny
By the End of Year 8 All Essential words lists 1-7 290 words Commonly Misspelt Words-55 working out more complex, irregular, and/or ambiguous words by using strategies such as inferring the unknown from
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
Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures
Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures Alex Graves and Jürgen Schmidhuber IDSIA, Galleria 2, 6928 Manno-Lugano, Switzerland TU Munich, Boltzmannstr.
SARDNET: A Self-Organizing Feature Map for Sequences
SARDNET: A Self-Organizing Feature Map for Sequences Daniel L. James and Risto Miikkulainen Department of Computer Sciences The University of Texas at Austin Austin, TX 78712 dljames,risto~cs.utexas.edu
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,
Richardson, J., The Next Step in Guided Writing, Ohio Literacy Conference, 2010
1 Procedures and Expectations for Guided Writing Procedures Context: Students write a brief response to the story they read during guided reading. At emergent levels, use dictated sentences that include
Characterizing and Processing Robot-Directed Speech
Characterizing and Processing Robot-Directed Speech Paulina Varchavskaia, Paul Fitzpatrick, Cynthia Breazeal AI Lab, MIT, Cambridge, USA [paulina,paulfitz,cynthia]@ai.mit.edu Abstract. Speech directed
Vowel mispronunciation detection using DNN acoustic models with cross-lingual training
INTERSPEECH 2015 Vowel mispronunciation detection using DNN acoustic models with cross-lingual training Shrikant Joshi, Nachiket Deo, Preeti Rao Department of Electrical Engineering, Indian Institute of
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
Proceedings of Meetings on Acoustics
Proceedings of Meetings on Acoustics Volume 19, 2013 http://acousticalsociety.org/ ICA 2013 Montreal Montreal, Canada 2-7 June 2013 Speech Communication Session 2aSC: Linking Perception and Production
Phonetics. The Sound of Language
Phonetics. The Sound of Language 1 The Description of Sounds Fromkin & Rodman: An Introduction to Language. Fort Worth etc., Harcourt Brace Jovanovich Read: Chapter 5, (p. 176ff.) (or the corresponding
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
The Perception of Nasalized Vowels in American English: An Investigation of On-line Use of Vowel Nasalization in Lexical Access
The Perception of Nasalized Vowels in American English: An Investigation of On-line Use of Vowel Nasalization in Lexical Access Joyce McDonough 1, Heike Lenhert-LeHouiller 1, Neil Bardhan 2 1 Linguistics
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;
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,
Speaker Recognition. Speaker Diarization and Identification
Speaker Recognition Speaker Diarization and Identification A dissertation submitted to the University of Manchester for the degree of Master of Science in the Faculty of Engineering and Physical Sciences
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
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
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
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
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
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
Stages of Literacy Ros Lugg
Beginning readers in the USA Stages of Literacy Ros Lugg Looked at predictors of reading success or failure Pre-readers readers aged 3-53 5 yrs Looked at variety of abilities IQ Speech and language abilities
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.
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
A Deep Bag-of-Features Model for Music Auto-Tagging
1 A Deep Bag-of-Features Model for Music Auto-Tagging Juhan Nam, Member, IEEE, Jorge Herrera, and Kyogu Lee, Senior Member, IEEE latter is often referred to as music annotation and retrieval, or simply
Phonology Revisited: Sor3ng Out the PH Factors in Reading and Spelling Development. Indiana, November, 2015
Phonology Revisited: Sor3ng Out the PH Factors in Reading and Spelling Development Indiana, November, 2015 Louisa C. Moats, Ed.D. (louisa.moats@gmail.com) meaning (semantics) discourse structure morphology
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
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.
On Developing Acoustic Models Using HTK. M.A. Spaans BSc.
On Developing Acoustic Models Using HTK M.A. Spaans BSc. On Developing Acoustic Models Using HTK M.A. Spaans BSc. Delft, December 2004 Copyright c 2004 M.A. Spaans BSc. December, 2004. Faculty of Electrical
Journal of Phonetics
Journal of Phonetics 40 (2012) 595 607 Contents lists available at SciVerse ScienceDirect Journal of Phonetics journal homepage: www.elsevier.com/locate/phonetics How linguistic and probabilistic properties
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
1. REFLEXES: Ask questions about coughing, swallowing, of water as fast as possible (note! Not suitable for all
Human Communication Science Chandler House, 2 Wakefield Street London WC1N 1PF http://www.hcs.ucl.ac.uk/ ACOUSTICS OF SPEECH INTELLIGIBILITY IN DYSARTHRIA EUROPEAN MASTER S S IN CLINICAL LINGUISTICS UNIVERSITY
Quarterly Progress and Status Report. Voiced-voiceless distinction in alaryngeal speech - acoustic and articula
Dept. for Speech, Music and Hearing Quarterly Progress and Status Report Voiced-voiceless distinction in alaryngeal speech - acoustic and articula Nord, L. and Hammarberg, B. and Lundström, E. journal:
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
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,
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..................................................
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
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
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
Cultivating DNN Diversity for Large Scale Video Labelling
Cultivating DNN Diversity for Large Scale Video Labelling Mikel Bober-Irizar mikel@mxbi.net Sameed Husain sameed.husain@surrey.ac.uk Miroslaw Bober m.bober@surrey.ac.uk Eng-Jon Ong e.ong@surrey.ac.uk Abstract
Self-Supervised Acquisition of Vowels in American English
Self-Supervised Acquisition of Vowels in American English Michael H. Coen MIT Computer Science and Artificial Intelligence Laboratory 32 Vassar Street Cambridge, MA 2139 mhcoen@csail.mit.edu Abstract This
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,
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
SOUND STRUCTURE REPRESENTATION, REPAIR AND WELL-FORMEDNESS: GRAMMAR IN SPOKEN LANGUAGE PRODUCTION. Adam B. Buchwald
SOUND STRUCTURE REPRESENTATION, REPAIR AND WELL-FORMEDNESS: GRAMMAR IN SPOKEN LANGUAGE PRODUCTION by Adam B. Buchwald A dissertation submitted to The Johns Hopkins University in conformity with the requirements
Artificial Neural Networks written examination
1 (8) Institutionen för informationsteknologi Olle Gällmo Universitetsadjunkt Adress: Lägerhyddsvägen 2 Box 337 751 05 Uppsala Artificial Neural Networks written examination Monday, May 15, 2006 9 00-14
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
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,
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,
CS224d Deep Learning for Natural Language Processing. Richard Socher, PhD
CS224d Deep Learning for Natural Language Processing, PhD Welcome 1. CS224d logis7cs 2. Introduc7on to NLP, deep learning and their intersec7on 2 Course Logis>cs Instructor: (Stanford PhD, 2014; now Founder/CEO
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
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
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
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
Self-Supervised Acquisition of Vowels in American English
Self-Supervised cquisition of Vowels in merican English Michael H. Coen MIT Computer Science and rtificial Intelligence Laboratory 32 Vassar Street Cambridge, M 2139 mhcoen@csail.mit.edu bstract This paper
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
Quarterly Progress and Status Report. VCV-sequencies in a preliminary text-to-speech system for female speech
Dept. for Speech, Music and Hearing Quarterly Progress and Status Report VCV-sequencies in a preliminary text-to-speech system for female speech Karlsson, I. and Neovius, L. journal: STL-QPSR volume: 35
" 'rear,.': T OOM 36-41L v CHU A Corpus and Phonetic Dictionary for Tunisian Arabic Speech Recognition
A Corpus and Phonetic Dictionary for Tunisian Arabic Speech Recognition Abir Masmoudi 1,2, Mariem Ellouze Khemakhem 1,Yannick Estève 2, Lamia Hadrich Belguith 1 and Nizar Habash 3 (1) ANLP Research group,
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
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,
Softprop: Softmax Neural Network Backpropagation Learning
Softprop: Softmax Neural Networ Bacpropagation Learning Michael Rimer Computer Science Department Brigham Young University Provo, UT 84602, USA E-mail: mrimer@axon.cs.byu.edu Tony Martinez Computer Science
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,
Training a Neural Network to Answer 8th Grade Science Questions Steven Hewitt, An Ju, Katherine Stasaski
Training a Neural Network to Answer 8th Grade Science Questions Steven Hewitt, An Ju, Katherine Stasaski Problem Statement and Background Given a collection of 8th grade science questions, possible answer
Evolutive Neural Net Fuzzy Filtering: Basic Description
Journal of Intelligent Learning Systems and Applications, 2010, 2: 12-18 doi:10.4236/jilsa.2010.21002 Published Online February 2010 (http://www.scirp.org/journal/jilsa) Evolutive Neural Net Fuzzy Filtering:
Consonants: articulation and transcription
Phonology 1: Handout January 20, 2005 Consonants: articulation and transcription 1 Orientation phonetics [G. Phonetik]: the study of the physical and physiological aspects of human sound production and
Automatic English-Chinese name transliteration for development of multilingual resources
Automatic English-Chinese name transliteration for development of multilingual resources Stephen Wan and Cornelia Maria Verspoor Microsoft Research Institute Macquarie University Sydney NSW 2109, Australia
Annotation and Taxonomy of Gestures in Lecture Videos
Annotation and Taxonomy of Gestures in Lecture Videos John R. Zhang Kuangye Guo Cipta Herwana John R. Kender Columbia University New York, NY 10027, USA {jrzhang@cs., kg2372@, cjh2148@, jrk@cs.}columbia.edu
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,
SEGMENTAL FEATURES IN SPONTANEOUS AND READ-ALOUD FINNISH
SEGMENTAL FEATURES IN SPONTANEOUS AND READ-ALOUD FINNISH Mietta Lennes Most of the phonetic knowledge that is currently available on spoken Finnish is based on clearly pronounced speech: either readaloud
DEVELOPMENT OF LINGUAL MOTOR CONTROL IN CHILDREN AND ADOLESCENTS
DEVELOPMENT OF LINGUAL MOTOR CONTROL IN CHILDREN AND ADOLESCENTS Natalia Zharkova 1, William J. Hardcastle 1, Fiona E. Gibbon 2 & Robin J. Lickley 1 1 CASL Research Centre, Queen Margaret University, Edinburgh
1 st Quarter (September, October, November) August/September Strand Topic Standard Notes Reading for Literature
1 st Grade Curriculum Map Common Core Standards Language Arts 2013 2014 1 st Quarter (September, October, November) August/September Strand Topic Standard Notes Reading for Literature Key Ideas and Details
Pobrane z czasopisma New Horizons in English Studies Data: 18/11/ :52:20. New Horizons in English Studies 1/2016
LANGUAGE Maria Curie-Skłodowska University () in Lublin k.laidler.umcs@gmail.com Online Adaptation of Word-initial Ukrainian CC Consonant Clusters by Native Speakers of English Abstract. The phenomenon
Letter-based speech synthesis
Letter-based speech synthesis Oliver Watts, Junichi Yamagishi, Simon King Centre for Speech Technology Research, University of Edinburgh, UK O.S.Watts@sms.ed.ac.uk jyamagis@inf.ed.ac.uk Simon.King@ed.ac.uk
Effect of Word Complexity on L2 Vocabulary Learning
Effect of Word Complexity on L2 Vocabulary Learning Kevin Dela Rosa Language Technologies Institute Carnegie Mellon University 5000 Forbes Ave. Pittsburgh, PA kdelaros@cs.cmu.edu Maxine Eskenazi Language
Universal contrastive analysis as a learning principle in CAPT
Universal contrastive analysis as a learning principle in CAPT Jacques Koreman, Preben Wik, Olaf Husby, Egil Albertsen Department of Language and Communication Studies, NTNU, Trondheim, Norway jacques.koreman@ntnu.no,
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
Role of Pausing in Text-to-Speech Synthesis for Simultaneous Interpretation
Role of Pausing in Text-to-Speech Synthesis for Simultaneous Interpretation Vivek Kumar Rangarajan Sridhar, John Chen, Srinivas Bangalore, Alistair Conkie AT&T abs - Research 180 Park Avenue, Florham Park,