The Munich 2011 CHiME Challenge Contribution: BLSTM-NMF Speech Enhancement and Recognition for Reverberated Multisource Environments
|
|
|
- Darleen Perkins
- 6 years ago
- Views:
Transcription
1 The Munich 2011 CHiME Challenge Contribution: BLSTM-NMF Speech Enhancement and Recognition for Reverberated Multisource Environments Felix Weninger, Jürgen Geiger, Martin Wöllmer, Björn Schuller, Gerhard Rigoll Institute for Human-Machine Communication, Technische Universität München September 1 st, 2011
2 +Gerhard Rigoll September 1st, 2011 CHiME
3 Outline Motivation Our ASR Architectures: Speech Enhancement by Convolutive NMF BLSTM Speech Recognition Single- and Multi-Stream Recognisers Development Results Our Final Challenge Result Outlook September 1st, 2011 CHiME
4 ASR in Noisy Conditions Noisy speech Feature extractor MFCC HMM Transcr. September 1st, 2011 CHiME
5 Solution 1: Front-End Enhancement Noisy speech Source separation + Increases SNR - Imperfect: Noise suppression vs. information loss Enhanced speech Feature extractor MFCC HMM Transcr. September 1st, 2011 CHiME
6 Solution 2: Robust Back-Ends Multi-condition training MAP adaptation Noisy speech Feature extractor MFCC HMM Transcr. September 1st, 2011 CHiME
7 Solution 2: Robust Back-Ends BLSTM-RNN Word prediction Noisy speech Feature extractor MFCC Multi-stream HMM Transcr. September 1st, 2011 CHiME
8 Proposed ASR Architecture Noisy speech BLSTM NMF Word prediction Enhanced speech Feature extractor MFCC Multi-stream HMM Transcr. September 1st, 2011 CHiME
9 Speech Enhancement: Convolutive NMF Assumption of additive noise Observed magnitude spectrogram = Convolution of Speech and noise spectrograms P = ms frame size, 16 ms shift = 256 ms Non-negative activations Dictionaries (`bases ) of speech and noise computed from training data September 1st, 2011 CHiME
10 Convolutive signal model Modelling of true speech spectrogram: Modelling of true noise spectrogram: R (s), R (n) = 51 (102 NMF components ) September 1st, 2011 CHiME
11 Speech Enhancement: Convolutive NMF Matrix formulation: Determine H (s), H (n) by multiplicative updates Minimize KL divergence d(v, Λ (s) +Λ (n) ) Estimate (soft masking) September 1st, 2011 CHiME
12 Convolutive Speech and Noise Bases Speaker-dependent speech bases: Convolutive NMF on training set for speakers k and words w, Build General noise base: Sub-sample training noise Build by convolutive NMF September 1st, 2011 CHiME
13 Back-End: Multi-stream Tandem BLSTM-HMM September 1st, 2011 CHiME
14 Context Modelling in Neural Networks MLP Feature frame stacking RNN Persistent memory LSTM-RNN BLSTM-RNN Bidirectional context September 1st, 2011 CHiME
15 Word Predictions by BLSTM-RNNs Bi-directionally context-sensitive prediction Amount of context learned automatically during training Superior to (R)NN feature frame stacking [Woellmer, 2011] September 1st, 2011 CHiME
16 BLSTM Training and Classification Dimension: 39 input units (one per feature) 3 hidden layers per direction (78 / 150 / 51 LSTM units) 51 output units (one per word) Training: Frame-wise word targets by forced alignment Early stopping strategy (use best network on development set) Classification: Input: (NMF-enhanced) speech Output: Index of output unit with highest activation September 1st, 2011 CHiME
17 Multi-Stream Hidden Markov Modelling GMM (M=7 mixtures) for MFCCs x t CPT for discrete BLSTM word prediction b t Mitigate BLSTM misclassifications by Viterbi decoding HMM emission probability in state s t : MFCC stream weight a = 1.3 (tuned on devel. set) Superior to GMM feature fusion [Woellmer, 2011] September 1st, 2011 CHiME
18 Results [Development Set] CHiME baseline: -6 db -3 db 0 db 3 db 6 db 9 db Mean Noisy speech Feature extractor MFCC HMM Keywords September 1st, 2011 CHiME
19 Results [Development Set] With MAP speaker adaptation: -6 db -3 db 0 db 3 db 6 db 9 db Mean Noisy speech Feature extractor MFCC HMM + MAP Keywords September 1st, 2011 CHiME
20 Results [Development Set] With MAP and multi-condition training: -6 db -3 db 0 db 3 db 6 db 9 db Mean Noise-free training set overlaid with CHiME training noise Select random segments to provide various SNRs Include noise in MAP Noisy speech Feature extractor MFCC HMM + MAP + MCT Keywords September 1st, 2011 CHiME
21 Results [Development Set] Multi-stream HMM recogniser: -6 db -3 db 0 db 3 db 6 db 9 db Mean MCT BLSTM Word pred. Noisy speech Feature extractor MFCC MS- HMM + MAP + MCT Keywords September 1st, 2011 CHiME
22 What about Speech Enhancement? September 1st, 2011 CHiME
23 Results [Development Set] Baseline recogniser: -6 db -3 db 0 db 3 db 6 db 9 db Mean w/o NMF w/ NMF Noisy speech NMF Feature extractor MFCC HMM Enhanced speech Keywords September 1st, 2011 CHiME
24 Results [Development Set] With MAP+MCT: -6 db -3 db 0 db 3 db 6 db 9 db Mean w/o NMF w/ NMF Noisy speech NMF Feature extractor MFCC HMM Enhanced speech + MAP + MCT Keywords September 1st, 2011 CHiME
25 Results [Development Set] Multi-Stream Recogniser: -6 db -3 db 0 db 3 db 6 db 9 db Mean w/o NMF w/ NMF Noisy speech + MCT BLSTM Word pred. NMF Feature extractor MFCC MS-HMM Enhanced speech + MAP + MCT Keywords September 1st, 2011 CHiME
26 Noise-Adaptive Speech Enhancement Noise dictionary context noise utterance September 1st, 2011 CHiME
27 Noise-Adaptive Speech Enhancement Noise dictionary context noise T utterance Replace T dictionary entries with a) Minimum KL divergence b) Maximum KL divergence d(context noise dictionary) September 1st, 2011 CHiME
28 SNR [db] Technische Universität München Noise-Adaptive Speech Enhancement: Results [Development Set] Keyword accuracy [%] avg max, T=10 min, T=10 max, T=5 min, T=5 non-adaptive MAP+MCT recogniser September 1st, 2011 CHiME
29 TUM Challenge Results [Test Set] Multi-stream HMM recogniser, MCT + MAP -6 db -3 db 0 db 3 db 6 db 9 db Mean w/o NMF w/ NMF w/ ANMF % accuracy in full realism 87.9% using oracle for VAD September 1st, 2011 CHiME
30 Conclusions Reduction of KW error rate: 44.1% (baseline) 15.6% (single-stream) 12.7% (multi-stream) Front-end enhancement and refined back-ends: Complementary approaches to ASR robustness September 1st, 2011 CHiME
31 Outlook Speaker-dependent BLSTM First results on test (non-adaptive NMF): -6 db -3 db 0 db 3 db 6 db 9 db Mean Pure BLSTM modelling Multi-stream modelling of (sparse) NMF activations NMF dictionary optimization September 1st, 2011 CHiME
32 Do it Yourself! cnmf enhancement by openblissart [Weninger, 2011] Feature extraction: opensmile [Eyben, 2010] Multi-stream HMM: HTK BLSTM implemented using RNNLIB by Alex Graves September 1st, 2011 CHiME
33 Thank you. September 1st, 2011 CHiME
8ch test data Dereverberation GMM 1ch test data 1ch MCT training data double-stream HMM recognition result LSTM Fig. 1: System overview: a double-stre
REVERB Workshop 2014 THE TUM SYSTEM FOR THE REVERB CHALLENGE: RECOGNITION OF REVERBERATED SPEECH USING MULTI-CHANNEL CORRELATION SHAPING DEREVERBERATION AND BLSTM RECURRENT NEURAL NETWORKS Jürgen T. Geiger,
Using RASTA in task independent TANDEM feature extraction
R E S E A R C H R E P O R T I D I A P Using RASTA in task independent TANDEM feature extraction Guillermo Aradilla a John Dines a Sunil Sivadas a b IDIAP RR 04-22 April 2004 D a l l e M o l l e I n s t
Applications of Music Processing
Lecture Music Processing Applications of Music Processing Christian Dittmar International Audio Laboratories Erlangen christian.dittmar@audiolabs-erlangen.de Singing Voice Detection Important pre-requisite
Mikko Myllymäki and Tuomas Virtanen
NON-STATIONARY NOISE MODEL COMPENSATION IN VOICE ACTIVITY DETECTION Mikko Myllymäki and Tuomas Virtanen Department of Signal Processing, Tampere University of Technology Korkeakoulunkatu 1, 3370, Tampere,
A Correlation-Maximization Denoising Filter Used as An Enhancement Frontend for Noise Robust Bird Call Classification
A Correlation-Maximization Denoising Filter Used as An Enhancement Frontend for Noise Robust Bird Call Classification Wei Chu and Abeer Alwan Speech Processing and Auditory Perception Laboratory Department
Robustness (cont.); End-to-end systems
Robustness (cont.); End-to-end systems Steve Renals Automatic Speech Recognition ASR Lecture 18 27 March 2017 ASR Lecture 18 Robustness (cont.); End-to-end systems 1 Robust Speech Recognition ASR Lecture
CNMF-BASED ACOUSTIC FEATURES FOR NOISE-ROBUST ASR
CNMF-BASED ACOUSTIC FEATURES FOR NOISE-ROBUST ASR Colin Vaz 1, Dimitrios Dimitriadis 2, Samuel Thomas 2, and Shrikanth Narayanan 1 1 Signal Analysis and Interpretation Lab, University of Southern California,
FEATURE COMBINATION AND STACKING OF RECURRENT AND NON-RECURRENT NEURAL NETWORKS FOR LVCSR
FEATURE COMBINATION AND STACKING OF RECURRENT AND NON-RECURRENT NEURAL NETWORKS FOR LVCSR Christian Plahl 1, Michael Kozielski 1, Ralf Schlüter 1 and Hermann Ney 1,2 1 Human Language Technology and Pattern
Voice Activity Detection
Voice Activity Detection Speech Processing Tom Bäckström Aalto University October 2015 Introduction Voice activity detection (VAD) (or speech activity detection, or speech detection) refers to a class
Automatic Text-Independent. Speaker. Recognition Approaches Using Binaural Inputs
Automatic Text-Independent Speaker Recognition Approaches Using Binaural Inputs Karim Youssef, Sylvain Argentieri and Jean-Luc Zarader 1 Outline Automatic speaker recognition: introduction Designed systems
Artificial Bandwidth Extension Using Deep Neural Networks for Spectral Envelope Estimation
Platzhalter für Bild, Bild auf Titelfolie hinter das Logo einsetzen Artificial Bandwidth Extension Using Deep Neural Networks for Spectral Envelope Estimation Johannes Abel and Tim Fingscheidt Institute
Recurrent neural networks Modelling sequential data. MLP Lecture 9 / 13 November 2018 Recurrent Neural Networks 1: Modelling sequential data 1
Recurrent neural networks Modelling sequential data MLP Lecture 9 / 13 November 2018 Recurrent Neural Networks 1: Modelling sequential data 1 Recurrent Neural Networks 1: Modelling sequential data Steve
ROBUST ISOLATED SPEECH RECOGNITION USING BINARY MASKS
ROBUST ISOLATED SPEECH RECOGNITION USING BINARY MASKS Seliz Gülsen Karado gan 1, Jan Larsen 1, Michael Syskind Pedersen 2, Jesper Bünsow Boldt 2 1) Informatics and Mathematical Modelling, Technical University
Deep Learning for Acoustic Echo Cancellation in Noisy and Double-Talk Scenarios
Interspeech 218 2-6 September 218, Hyderabad Deep Learning for Acoustic Echo Cancellation in Noisy and Double-Talk Scenarios Hao Zhang 1, DeLiang Wang 1,2,3 1 Department of Computer Science and Engineering,
Combining Pitch-Based Inference and Non-Negative Spectrogram Factorization in Separating Vocals from Polyphonic Music
Combining Pitch-Based Inference and Non-Negative Spectrogram Factorization in Separating Vocals from Polyphonic Music Tuomas Virtanen, Annamaria Mesaros, Matti Ryynänen Department of Signal Processing,
Recurrent neural networks Modelling sequential data. MLP Lecture 9 Recurrent Neural Networks 1: Modelling sequential data 1
Recurrent neural networks Modelling sequential data MLP Lecture 9 Recurrent Neural Networks 1: Modelling sequential data 1 Recurrent Neural Networks 1: Modelling sequential data Steve Renals Machine Learning
All-Neural Multi-Channel Speech Enhancement
Interspeech 2018 2-6 September 2018, Hyderabad All-Neural Multi-Channel Speech Enhancement Zhong-Qiu Wang 1, DeLiang Wang 1,2 1 Department of Computer Science and Engineering, The Ohio State University,
REVERBERATION-BASED FEATURE EXTRACTION FOR ACOUSTIC SCENE CLASSIFICATION. Miloš Marković, Jürgen Geiger
REVERBERATION-BASED FEATURE EXTRACTION FOR ACOUSTIC SCENE CLASSIFICATION Miloš Marković, Jürgen Geiger Huawei Technologies Düsseldorf GmbH, European Research Center, Munich, Germany ABSTRACT 1 We present
THE MERL/SRI SYSTEM FOR THE 3RD CHIME CHALLENGE USING BEAMFORMING, ROBUST FEATURE EXTRACTION, AND ADVANCED SPEECH RECOGNITION
THE MERL/SRI SYSTEM FOR THE 3RD CHIME CHALLENGE USING BEAMFORMING, ROBUST FEATURE EXTRACTION, AND ADVANCED SPEECH RECOGNITION Takaaki Hori 1, Zhuo Chen 1,2, Hakan Erdogan 1,3, John R. Hershey 1, Jonathan
RECURRENT NEURAL NETWORKS FOR POLYPHONIC SOUND EVENT DETECTION IN REAL LIFE RECORDINGS. Giambattista Parascandolo, Heikki Huttunen, Tuomas Virtanen
RECURRENT NEURAL NETWORKS FOR POLYPHONIC SOUND EVENT DETECTION IN REAL LIFE RECORDINGS Giambattista Parascandolo, Heikki Huttunen, Tuomas Virtanen Department of Signal Processing, Tampere University of
Speaker and Noise Independent Voice Activity Detection
Speaker and Noise Independent Voice Activity Detection François G. Germain, Dennis L. Sun,2, Gautham J. Mysore 3 Center for Computer Research in Music and Acoustics, Stanford University, CA 9435 2 Department
Deep learning architectures for music audio classification: a personal (re)view
Deep learning architectures for music audio classification: a personal (re)view Jordi Pons jordipons.me @jordiponsdotme Music Technology Group Universitat Pompeu Fabra, Barcelona Acronyms MLP: multi layer
Speech Enhancement in Presence of Noise using Spectral Subtraction and Wiener Filter
Speech Enhancement in Presence of Noise using Spectral Subtraction and Wiener Filter 1 Gupteswar Sahu, 2 D. Arun Kumar, 3 M. Bala Krishna and 4 Jami Venkata Suman Assistant Professor, Department of ECE,
I D I A P. On Factorizing Spectral Dynamics for Robust Speech Recognition R E S E A R C H R E P O R T. Iain McCowan a Hemant Misra a,b
R E S E A R C H R E P O R T I D I A P On Factorizing Spectral Dynamics for Robust Speech Recognition a Vivek Tyagi Hervé Bourlard a,b IDIAP RR 3-33 June 23 Iain McCowan a Hemant Misra a,b to appear in
POSSIBLY the most noticeable difference when performing
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 15, NO. 7, SEPTEMBER 2007 2011 Acoustic Beamforming for Speaker Diarization of Meetings Xavier Anguera, Associate Member, IEEE, Chuck Wooters,
A simple RNN-plus-highway network for statistical
ISSN 1346-5597 NII Technical Report A simple RNN-plus-highway network for statistical parametric speech synthesis Xin Wang, Shinji Takaki, Junichi Yamagishi NII-2017-003E Apr. 2017 A simple RNN-plus-highway
24 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 17, NO. 1, JANUARY /$ IEEE
24 IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 17, NO. 1, JANUARY 2009 Speech Enhancement, Gain, and Noise Spectrum Adaptation Using Approximate Bayesian Estimation Jiucang Hao, Hagai
Performance analysis of voice activity detection algorithm for robust speech recognition system under different noisy environment
BABU et al: VOICE ACTIVITY DETECTION ALGORITHM FOR ROBUST SPEECH RECOGNITION SYSTEM Journal of Scientific & Industrial Research Vol. 69, July 2010, pp. 515-522 515 Performance analysis of voice activity
IMPROVEMENTS TO THE IBM SPEECH ACTIVITY DETECTION SYSTEM FOR THE DARPA RATS PROGRAM
IMPROVEMENTS TO THE IBM SPEECH ACTIVITY DETECTION SYSTEM FOR THE DARPA RATS PROGRAM Samuel Thomas 1, George Saon 1, Maarten Van Segbroeck 2 and Shrikanth S. Narayanan 2 1 IBM T.J. Watson Research Center,
LIMITING NUMERICAL PRECISION OF NEURAL NETWORKS TO ACHIEVE REAL- TIME VOICE ACTIVITY DETECTION
LIMITING NUMERICAL PRECISION OF NEURAL NETWORKS TO ACHIEVE REAL- TIME VOICE ACTIVITY DETECTION Jong Hwan Ko *, Josh Fromm, Matthai Philipose, Ivan Tashev, and Shuayb Zarar * School of Electrical and Computer
Learning to Unlearn and Relearn Speech Signal Processing using Neural Networks: current and future perspectives
Learning to Unlearn and Relearn Speech Signal Processing using Neural Networks: current and future perspectives Mathew Magimai Doss Collaborators: Vinayak Abrol, Selen Hande Kabil, Hannah Muckenhirn, Dimitri
IMPROVING WIDEBAND SPEECH RECOGNITION USING MIXED-BANDWIDTH TRAINING DATA IN CD-DNN-HMM
IMPROVING WIDEBAND SPEECH RECOGNITION USING MIXED-BANDWIDTH TRAINING DATA IN CD-DNN-HMM Jinyu Li, Dong Yu, Jui-Ting Huang, and Yifan Gong Microsoft Corporation, One Microsoft Way, Redmond, WA 98052 ABSTRACT
CP-JKU SUBMISSIONS FOR DCASE-2016: A HYBRID APPROACH USING BINAURAL I-VECTORS AND DEEP CONVOLUTIONAL NEURAL NETWORKS
CP-JKU SUBMISSIONS FOR DCASE-2016: A HYBRID APPROACH USING BINAURAL I-VECTORS AND DEEP CONVOLUTIONAL NEURAL NETWORKS Hamid Eghbal-Zadeh Bernhard Lehner Matthias Dorfer Gerhard Widmer Department of Computational
Single Channel Speaker Segregation using Sinusoidal Residual Modeling
NCC 2009, January 16-18, IIT Guwahati 294 Single Channel Speaker Segregation using Sinusoidal Residual Modeling Rajesh M Hegde and A. Srinivas Dept. of Electrical Engineering Indian Institute of Technology
AN ANALYSIS OF SPEECH RECOGNITION PERFORMANCE BASED UPON NETWORK LAYERS AND TRANSFER FUNCTIONS
AN ANALYSIS OF SPEECH RECOGNITION PERFORMANCE BASED UPON NETWORK LAYERS AND TRANSFER FUNCTIONS Kuldeep Kumar 1, R. K. Aggarwal 1 and Ankita Jain 2 1 Department of Computer Engineering, National Institute
Spectral Reconstruction and Noise Model Estimation based on a Masking Model for Noise-Robust Speech Recognition
Circuits, Systems, and Signal Processing manuscript No. (will be inserted by the editor) Spectral Reconstruction and Noise Model Estimation based on a Masking Model for Noise-Robust Speech Recognition
MULTI-MICROPHONE FUSION FOR DETECTION OF SPEECH AND ACOUSTIC EVENTS IN SMART SPACES
MULTI-MICROPHONE FUSION FOR DETECTION OF SPEECH AND ACOUSTIC EVENTS IN SMART SPACES Panagiotis Giannoulis 1,3, Gerasimos Potamianos 2,3, Athanasios Katsamanis 1,3, Petros Maragos 1,3 1 School of Electr.
Joint recognition and direction-of-arrival estimation of simultaneous meetingroom acoustic events
INTERSPEECH 2013 Joint recognition and direction-of-arrival estimation of simultaneous meetingroom acoustic events Rupayan Chakraborty and Climent Nadeu TALP Research Centre, Department of Signal Theory
Audio Imputation Using the Non-negative Hidden Markov Model
Audio Imputation Using the Non-negative Hidden Markov Model Jinyu Han 1,, Gautham J. Mysore 2, and Bryan Pardo 1 1 EECS Department, Northwestern University 2 Advanced Technology Labs, Adobe Systems Inc.
Training neural network acoustic models on (multichannel) waveforms
View this talk on YouTube: https://youtu.be/si_8ea_ha8 Training neural network acoustic models on (multichannel) waveforms Ron Weiss in SANE 215 215-1-22 Joint work with Tara Sainath, Kevin Wilson, Andrew
Simultaneous Recognition of Speech Commands by a Robot using a Small Microphone Array
2012 2nd International Conference on Computer Design and Engineering (ICCDE 2012) IPCSIT vol. 49 (2012) (2012) IACSIT Press, Singapore DOI: 10.7763/IPCSIT.2012.V49.14 Simultaneous Recognition of Speech
Dimension Reduction of the Modulation Spectrogram for Speaker Verification
Dimension Reduction of the Modulation Spectrogram for Speaker Verification Tomi Kinnunen Speech and Image Processing Unit Department of Computer Science University of Joensuu, Finland Kong Aik Lee and
Effective post-processing for single-channel frequency-domain speech enhancement Weifeng Li a
R E S E A R C H R E P O R T I D I A P Effective post-processing for single-channel frequency-domain speech enhancement Weifeng Li a IDIAP RR 7-7 January 8 submitted for publication a IDIAP Research Institute,
Performance Analysiss of Speech Enhancement Algorithm for Robust Speech Recognition System
Performance Analysiss of Speech Enhancement Algorithm for Robust Speech Recognition System C.GANESH BABU 1, Dr.P..T.VANATHI 2 R.RAMACHANDRAN 3, M.SENTHIL RAJAA 3, R.VENGATESH 3 1 Research Scholar (PSGCT)
SONG RETRIEVAL SYSTEM USING HIDDEN MARKOV MODELS
SONG RETRIEVAL SYSTEM USING HIDDEN MARKOV MODELS AKSHAY CHANDRASHEKARAN ANOOP RAMAKRISHNA akshayc@cmu.edu anoopr@andrew.cmu.edu ABHISHEK JAIN GE YANG ajain2@andrew.cmu.edu younger@cmu.edu NIDHI KOHLI R
Chapter 4 SPEECH ENHANCEMENT
44 Chapter 4 SPEECH ENHANCEMENT 4.1 INTRODUCTION: Enhancement is defined as improvement in the value or Quality of something. Speech enhancement is defined as the improvement in intelligibility and/or
IMPROVING MICROPHONE ARRAY SPEECH RECOGNITION WITH COCHLEAR IMPLANT-LIKE SPECTRALLY REDUCED SPEECH
RESEARCH REPORT IDIAP IMPROVING MICROPHONE ARRAY SPEECH RECOGNITION WITH COCHLEAR IMPLANT-LIKE SPECTRALLY REDUCED SPEECH Cong-Thanh Do Mohammad J. Taghizadeh Philip N. Garner Idiap-RR-40-2011 DECEMBER
Discriminative Training for Automatic Speech Recognition
Discriminative Training for Automatic Speech Recognition 22 nd April 2013 Advanced Signal Processing Seminar Article Heigold, G.; Ney, H.; Schluter, R.; Wiesler, S. Signal Processing Magazine, IEEE, vol.29,
Power Normalized Cepstral Coefficient for Speaker Diarization and Acoustic Echo Cancellation
Power Normalized Cepstral Coefficient for Speaker Diarization and Acoustic Echo Cancellation Sherbin Kanattil Kassim P.G Scholar, Department of ECE, Engineering College, Edathala, Ernakulam, India sherbin_kassim@yahoo.co.in
Deep Neural Network Architectures for Modulation Classification
Deep Neural Network Architectures for Modulation Classification Xiaoyu Liu, Diyu Yang, and Aly El Gamal School of Electrical and Computer Engineering Purdue University Email: {liu1962, yang1467, elgamala}@purdue.edu
PERFORMANCE COMPARISON OF GMM, HMM AND DNN BASED APPROACHES FOR ACOUSTIC EVENT DETECTION WITHIN TASK 3 OF THE DCASE 2016 CHALLENGE
PERFORMANCE COMPARISON OF GMM, HMM AND DNN BASED APPROACHES FOR ACOUSTIC EVENT DETECTION WITHIN TASK 3 OF THE DCASE 206 CHALLENGE Jens Schröder,3, Jörn Anemüller 2,3, Stefan Goetze,3 Fraunhofer Institute
Auditory Based Feature Vectors for Speech Recognition Systems
Auditory Based Feature Vectors for Speech Recognition Systems Dr. Waleed H. Abdulla Electrical & Computer Engineering Department The University of Auckland, New Zealand [w.abdulla@auckland.ac.nz] 1 Outlines
Modulation Spectrum Power-law Expansion for Robust Speech Recognition
Modulation Spectrum Power-law Expansion for Robust Speech Recognition Hao-Teng Fan, Zi-Hao Ye and Jeih-weih Hung Department of Electrical Engineering, National Chi Nan University, Nantou, Taiwan E-mail:
Progress in the BBN Keyword Search System for the DARPA RATS Program
INTERSPEECH 2014 Progress in the BBN Keyword Search System for the DARPA RATS Program Tim Ng 1, Roger Hsiao 1, Le Zhang 1, Damianos Karakos 1, Sri Harish Mallidi 2, Martin Karafiát 3,KarelVeselý 3, Igor
VQ Source Models: Perceptual & Phase Issues
VQ Source Models: Perceptual & Phase Issues Dan Ellis & Ron Weiss Laboratory for Recognition and Organization of Speech and Audio Dept. Electrical Eng., Columbia Univ., NY USA {dpwe,ronw}@ee.columbia.edu
SOUND SOURCE RECOGNITION AND MODELING
SOUND SOURCE RECOGNITION AND MODELING CASA seminar, summer 2000 Antti Eronen antti.eronen@tut.fi Contents: Basics of human sound source recognition Timbre Voice recognition Recognition of environmental
Robust Low-Resource Sound Localization in Correlated Noise
INTERSPEECH 2014 Robust Low-Resource Sound Localization in Correlated Noise Lorin Netsch, Jacek Stachurski Texas Instruments, Inc. netsch@ti.com, jacek@ti.com Abstract In this paper we address the problem
Singing Voice Detection. Applications of Music Processing. Singing Voice Detection. Singing Voice Detection. Singing Voice Detection
Detection Lecture usic Processing Applications of usic Processing Christian Dittmar International Audio Laboratories Erlangen christian.dittmar@audiolabs-erlangen.de Important pre-requisite for: usic segmentation
CHiME Challenge: Approaches to Robustness using Beamforming and Uncertainty-of-Observation Techniques
CHiME Challenge: Approaches to Robustness using Beamforming and Uncertainty-of-Observation Techniques Dorothea Kolossa 1, Ramón Fernandez Astudillo 2, Alberto Abad 2, Steffen Zeiler 1, Rahim Saeidi 3,
Recurrent neural networks Modelling sequential data. MLP Lecture 9 Recurrent Networks 1
Recurrent neural networks Modelling sequential data MLP Lecture 9 Recurrent Networks 1 Recurrent Networks Steve Renals Machine Learning Practical MLP Lecture 9 16 November 2016 MLP Lecture 9 Recurrent
Endpoint Detection using Grid Long Short-Term Memory Networks for Streaming Speech Recognition
INTERSPEECH 2017 August 20 24, 2017, Stockholm, Sweden Endpoint Detection using Grid Long Short-Term Memory Networks for Streaming Speech Recognition Shuo-Yiin Chang, Bo Li, Tara N. Sainath, Gabor Simko,
An Efficient Extraction of Vocal Portion from Music Accompaniment Using Trend Estimation
An Efficient Extraction of Vocal Portion from Music Accompaniment Using Trend Estimation Aisvarya V 1, Suganthy M 2 PG Student [Comm. Systems], Dept. of ECE, Sree Sastha Institute of Engg. & Tech., Chennai,
Calibration of Microphone Arrays for Improved Speech Recognition
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Calibration of Microphone Arrays for Improved Speech Recognition Michael L. Seltzer, Bhiksha Raj TR-2001-43 December 2001 Abstract We present
Detecting Road Surface Wetness from Audio: A Deep Learning Approach
1 Detecting Road Surface Wetness from Audio: A Deep Learning Approach Irman Abdić, Lex Fridman, Erik Marchi, Student Member, IEEE, Daniel E. Brown, William Angell, Bryan Reimer, Björn Schuller, Senior
Spectral Noise Tracking for Improved Nonstationary Noise Robust ASR
11. ITG Fachtagung Sprachkommunikation Spectral Noise Tracking for Improved Nonstationary Noise Robust ASR Aleksej Chinaev, Marc Puels, Reinhold Haeb-Umbach Department of Communications Engineering University
ROTATIONAL RESET STRATEGY FOR ONLINE SEMI-SUPERVISED NMF-BASED SPEECH ENHANCEMENT FOR LONG RECORDINGS
ROTATIONAL RESET STRATEGY FOR ONLINE SEMI-SUPERVISED NMF-BASED SPEECH ENHANCEMENT FOR LONG RECORDINGS Jun Zhou Southwest University Dept. of Computer Science Beibei, Chongqing 47, China zhouj@swu.edu.cn
Discriminative Enhancement for Single Channel Audio Source Separation using Deep Neural Networks
Discriminative Enhancement for Single Channel Audio Source Separation using Deep Neural Networks Emad M. Grais, Gerard Roma, Andrew J.R. Simpson, and Mark D. Plumbley Centre for Vision, Speech and Signal
SINGING-VOICE SEPARATION FROM MONAURAL RECORDINGS USING DEEP RECURRENT NEURAL NETWORKS
SINGING-VOICE SEPARATION FROM MONAURAL RECORDINGS USING DEEP RECURRENT NEURAL NETWORKS Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis Department of Electrical and Computer Engineering,
A Tutorial on Distributed Speech Recognition for Wireless Mobile Devices
1 A Tutorial on Distributed Speech Recognition for Wireless Mobile Devices Dale Isaacs, A/Professor Daniel J. Mashao Speech Technology and Research Group (STAR) Department of Electrical Engineering University
DNN-based Amplitude and Phase Feature Enhancement for Noise Robust Speaker Identification
INTERSPEECH 2016 September 8 12, 2016, San Francisco, USA DNN-based Amplitude and Phase Feature Enhancement for Noise Robust Speaker Identification Zeyan Oo 1, Yuta Kawakami 1, Longbiao Wang 1, Seiichi
CS 188: Artificial Intelligence Spring Speech in an Hour
CS 188: Artificial Intelligence Spring 2006 Lecture 19: Speech Recognition 3/23/2006 Dan Klein UC Berkeley Many slides from Dan Jurafsky Speech in an Hour Speech input is an acoustic wave form s p ee ch
On Single-Channel Speech Enhancement and On Non-Linear Modulation-Domain Kalman Filtering
1 On Single-Channel Speech Enhancement and On Non-Linear Modulation-Domain Kalman Filtering Nikolaos Dionelis, https://www.commsp.ee.ic.ac.uk/~sap/people-nikolaos-dionelis/ nikolaos.dionelis11@imperial.ac.uk,
Convolutional Neural Networks for Small-footprint Keyword Spotting
INTERSPEECH 2015 Convolutional Neural Networks for Small-footprint Keyword Spotting Tara N. Sainath, Carolina Parada Google, Inc. New York, NY, U.S.A {tsainath, carolinap}@google.com Abstract We explore
Mel Spectrum Analysis of Speech Recognition using Single Microphone
International Journal of Engineering Research in Electronics and Communication Mel Spectrum Analysis of Speech Recognition using Single Microphone [1] Lakshmi S.A, [2] Cholavendan M [1] PG Scholar, Sree
ANALYSIS-BY-SYNTHESIS FEATURE ESTIMATION FOR ROBUST AUTOMATIC SPEECH RECOGNITION USING SPECTRAL MASKS. Michael I Mandel and Arun Narayanan
ANALYSIS-BY-SYNTHESIS FEATURE ESTIMATION FOR ROBUST AUTOMATIC SPEECH RECOGNITION USING SPECTRAL MASKS Michael I Mandel and Arun Narayanan The Ohio State University, Computer Science and Engineering {mandelm,narayaar}@cse.osu.edu
A HYBRID APPROACH TO COMBINING CONVENTIONAL AND DEEP LEARNING TECHNIQUES FOR SINGLE-CHANNEL SPEECH ENHANCEMENT AND RECOGNITION
A HYBRID APPROACH TO COMBINING CONVENTIONAL AND DEEP LEARNING TECHNIQUES FOR SINGLE-CHANNEL SPEECH ENHANCEMENT AND RECOGNITION Yan-Hui Tu 1, Ivan Tashev 2, Chin-Hui Lee 3, Shuayb Zarar 2 1 University of
Dimension Reduction of the Modulation Spectrogram for Speaker Verification
Dimension Reduction of the Modulation Spectrogram for Speaker Verification Tomi Kinnunen Speech and Image Processing Unit Department of Computer Science University of Joensuu, Finland tkinnu@cs.joensuu.fi
Enhancing the Complex-valued Acoustic Spectrograms in Modulation Domain for Creating Noise-Robust Features in Speech Recognition
Proceedings of APSIPA Annual Summit and Conference 15 16-19 December 15 Enhancing the Complex-valued Acoustic Spectrograms in Modulation Domain for Creating Noise-Robust Features in Speech Recognition
신경망기반자동번역기술. Konkuk University Computational Intelligence Lab. 김강일
신경망기반자동번역기술 Konkuk University Computational Intelligence Lab. http://ci.konkuk.ac.kr kikim01@kunkuk.ac.kr 김강일 Index Issues in AI and Deep Learning Overview of Machine Translation Advanced Techniques in
SINGING-VOICE SEPARATION FROM MONAURAL RECORDINGS USING DEEP RECURRENT NEURAL NETWORKS
SINGING-VOICE SEPARATION FROM MONAURAL RECORDINGS USING DEEP RECURRENT NEURAL NETWORKS Po-Sen Huang, Minje Kim, Mark Hasegawa-Johnson, Paris Smaragdis Department of Electrical and Computer Engineering,
Enhancement of Speech Signal by Adaptation of Scales and Thresholds of Bionic Wavelet Transform Coefficients
ISSN (Print) : 232 3765 An ISO 3297: 27 Certified Organization Vol. 3, Special Issue 3, April 214 Paiyanoor-63 14, Tamil Nadu, India Enhancement of Speech Signal by Adaptation of Scales and Thresholds
An Improved Voice Activity Detection Based on Deep Belief Networks
e-issn 2455 1392 Volume 2 Issue 4, April 2016 pp. 676-683 Scientific Journal Impact Factor : 3.468 http://www.ijcter.com An Improved Voice Activity Detection Based on Deep Belief Networks Shabeeba T. K.
CV Florian Eyben.
CV Florian Eyben eyben@tum.de Technische Universität München Institute for Human-Machine Communication (MMK) Theresienstr. 90 80333 München Germany Phone: +49 89 28928549 E-mail: eyben@tum.de Web: www.eyben.eu
SYNTHETIC SPEECH DETECTION USING TEMPORAL MODULATION FEATURE
SYNTHETIC SPEECH DETECTION USING TEMPORAL MODULATION FEATURE Zhizheng Wu 1,2, Xiong Xiao 2, Eng Siong Chng 1,2, Haizhou Li 1,2,3 1 School of Computer Engineering, Nanyang Technological University (NTU),
Adaptive Filters Application of Linear Prediction
Adaptive Filters Application of Linear Prediction Gerhard Schmidt Christian-Albrechts-Universität zu Kiel Faculty of Engineering Electrical Engineering and Information Technology Digital Signal Processing
High-speed Noise Cancellation with Microphone Array
Noise Cancellation a Posteriori Probability, Maximum Criteria Independent Component Analysis High-speed Noise Cancellation with Microphone Array We propose the use of a microphone array based on independent
Acoustic Beamforming for Speaker Diarization of Meetings
JOURNAL OF L A TEX CLASS FILES, VOL. 6, NO. 1, JANUARY 2007 1 Acoustic Beamforming for Speaker Diarization of Meetings Xavier Anguera, Member, IEEE, Chuck Wooters, Member, IEEE, Javier Hernando, Member,
Introduction to HTK Toolkit
Introduction to HTK Toolkit Berlin Chen 2004 Reference: - Steve Young et al. The HTK Book. Version 3.2, 2002. Outline An Overview of HTK HTK Processing Stages Data Preparation Tools Training Tools Testing
CONVOLUTIONAL NEURAL NETWORK FOR ROBUST PITCH DETERMINATION. Hong Su, Hui Zhang, Xueliang Zhang, Guanglai Gao
CONVOLUTIONAL NEURAL NETWORK FOR ROBUST PITCH DETERMINATION Hong Su, Hui Zhang, Xueliang Zhang, Guanglai Gao Department of Computer Science, Inner Mongolia University, Hohhot, China, 0002 suhong90 imu@qq.com,
Announcements. Today. Speech and Language. State Path Trellis. HMMs: MLE Queries. Introduction to Artificial Intelligence. V22.
Introduction to Artificial Intelligence Announcements V22.0472-001 Fall 2009 Lecture 19: Speech Recognition & Viterbi Decoding Rob Fergus Dept of Computer Science, Courant Institute, NYU Slides from John
Robust Speech Recognition Group Carnegie Mellon University. Telephone: Fax:
Robust Automatic Speech Recognition In the 21 st Century Richard Stern (with Alex Acero, Yu-Hsiang Chiu, Evandro Gouvêa, Chanwoo Kim, Kshitiz Kumar, Amir Moghimi, Pedro Moreno, Hyung-Min Park, Bhiksha
Noise Estimation and Noise Removal Techniques for Speech Recognition in Adverse Environment
Noise Estimation and Noise Removal Techniques for Speech Recognition in Adverse Environment Urmila Shrawankar 1,3 and Vilas Thakare 2 1 IEEE Student Member & Research Scholar, (CSE), SGB Amravati University,
Binaural segregation in multisource reverberant environments
Binaural segregation in multisource reverberant environments Nicoleta Roman a Department of Computer Science and Engineering, The Ohio State University, Columbus, Ohio 43210 Soundararajan Srinivasan b
BEAMNET: END-TO-END TRAINING OF A BEAMFORMER-SUPPORTED MULTI-CHANNEL ASR SYSTEM
BEAMNET: END-TO-END TRAINING OF A BEAMFORMER-SUPPORTED MULTI-CHANNEL ASR SYSTEM Jahn Heymann, Lukas Drude, Christoph Boeddeker, Patrick Hanebrink, Reinhold Haeb-Umbach Paderborn University Department of
A ROBUST FRONTEND FOR ASR: COMBINING DENOISING, NOISE MASKING AND FEATURE NORMALIZATION. Maarten Van Segbroeck and Shrikanth S.
A ROBUST FRONTEND FOR ASR: COMBINING DENOISING, NOISE MASKING AND FEATURE NORMALIZATION Maarten Van Segbroeck and Shrikanth S. Narayanan Signal Analysis and Interpretation Lab, University of Southern California,
Different Approaches of Spectral Subtraction Method for Speech Enhancement
ISSN 2249 5460 Available online at www.internationalejournals.com International ejournals International Journal of Mathematical Sciences, Technology and Humanities 95 (2013 1056 1062 Different Approaches
Pattern Recognition. Part 6: Bandwidth Extension. Gerhard Schmidt
Pattern Recognition Part 6: Gerhard Schmidt Christian-Albrechts-Universität zu Kiel Faculty of Engineering Institute of Electrical and Information Engineering Digital Signal Processing and System Theory
Auditory motivated front-end for noisy speech using spectro-temporal modulation filtering
Auditory motivated front-end for noisy speech using spectro-temporal modulation filtering Sriram Ganapathy a) and Mohamed Omar IBM T.J. Watson Research Center, Yorktown Heights, New York 10562 ganapath@us.ibm.com,
Attention-based Multi-Encoder-Decoder Recurrent Neural Networks
Attention-based Multi-Encoder-Decoder Recurrent Neural Networks Stephan Baier 1, Sigurd Spieckermann 2 and Volker Tresp 1,2 1- Ludwig Maximilian University Oettingenstr. 67, Munich, Germany 2- Siemens
HOW DO DEEP CONVOLUTIONAL NEURAL NETWORKS
Under review as a conference paper at ICLR 28 HOW DO DEEP CONVOLUTIONAL NEURAL NETWORKS LEARN FROM RAW AUDIO WAVEFORMS? Anonymous authors Paper under double-blind review ABSTRACT Prior work on speech and