Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environments
|
|
- Merilyn Hardy
- 6 years ago
- Views:
Transcription
1 Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environments Andreas Schwarz, Christian Huemmer, Roland Maas, Walter Kellermann Lehrstuhl für Multimediakommunikation und Signalverarbeitung Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany ICASSP 2015
2 Deep Neural Networks for Acoustic Modeling Trend: explicit feature processing implicit learning! MFCCs simple filterbank features [Mohamed et al. 2013]! Filterbanks raw time-domain signals [Jaitly, Hinton 2011]! Denoising noise-aware training [Seltzer et al. 2013] What about spatial information (microphone arrays)?! Stacked feature vectors from multiple channels [Swietojanski et al. 2013]! Phase information is not exploited! Raw multi-channel waveforms [Hoshen et al. 2015]! Hard to generalize for arbitrary acoustic scenarios! Spatial diffuseness features! Represent spatial information independently of source position and microphone array mh acoustics Eigenmike 2
3 Outline Signal Model Coherence-based Dereverberation in the STFT Domain Extraction of Spatial Diffuseness Features 3
4 Signal Model! Desired signal is fully coherent (only delayed between microphones)! Noise and reverberation is diffuse and uncorrelated to the desired signal! Coherence of the mixed sound field can be modeled as: Coherent-to-diffuse ratio (CDR) can be estimated from the complex spatial coherence of the mixture 4
5 Coherence-based STFT-Domain Dereverberation 1. Estimate short-time spatial coherence (quasi-instantaneous) 2. Estimate coherent-to-diffuse ratio (CDR) 3. Perform spectral subtraction to suppress diffuse components [Schwarz/Kellermann, Coherent-to-Diffuse Power Ratio Estimation for Dereverberation, IEEE/ACM Transactions on Audio, Speech and Language Processing, 2015] Only instantaneous signal properties are exploited No knowledge or estimation of source DOA required 5
6 Evaluation Word Error Rate for REVERB challenge evaluation set WER [%] Clean speech-trained DNN SimData RealData 69.3 WER [%] Multi-condition-trained DNN SimData RealData logmelspec enh. logmelspec 0 logmelspec enh. logmelspec Improvement for clean-trained DNN " Disappears with multi-condition training # Multi-condition training neutralizes the effect of dereverberation 6
7 Spatial Feature Extraction Instead of STFT-domain enhancement, extract spatial features! meldiffuseness:! 0 for purely directional sound, 1 for purely diffuse sound! computed from coherent-to-diffuse ratio: D(k,f)=1/(CDR(k,f)+1) 7! Naive approach: magnitude squared coherence (melmsc)! Depends not only on diffuse noise content, but also on microphone spacing, DOA
8 Visualization of Features logmelspec: enhanced logmelspec: meldiffuseness: 8
9 Evaluation Setup REVERB challenge two microphone task [Kinoshita et al. 2013]! noisy and reverberant signals created from WSJCAM0 corpus! varying direction of arrival! 2 microphones, 8cm spacing DNN-based Speech Recognizer! Kaldi toolkit! hybrid DNN-HMM acoustic model! maxout network (4 hidden layers, 2000 inputs, 400 outputs per layer)! 5#frame#splicing! training on#multi!condition noisy and reverberant data (17.5#hours) Feature vectors! noisy logmelspec features:! enhanced logmelspec features:! augmented with melmsc:! augmented with meldiffuseness: overall dimension: 72 logmelspec Δ ΔΔ enh. logmel Δ ΔΔ logmelspec Δ melmsc logmelspec Δ meldiffuseness 9
10 Evaluation Results SimData: measured impulse responses, additive noise RealData: real recordings in noisy environment SimData RealData WER [%] logmelspec enh. logmelspec logmelspec +melmsc logmelspec +meldiffuseness 6% to 11% relative WER reduction by using spatial features 10
11 Summary Motivation! STFT-domain dereverberation has little effect on WER! Idea: exploit spatial information in the DNN Spatial Diffuseness Features! Can be extracted instantaneously! Blind, no knowledge or estimation of the source DOA required! Device-independent features! 6% to 11% relative WER reduction for REVERB challenge 2-channel task! MATLAB code available (see paper) Can we use a similar approach to deal with directional interferers? Thank you for your attention! 11
12 Results (Details) Recognizer Feature Evaluation Set SimData RealData Room 1 Room 2 Room 3 Room 1 Avg near far near far near far near far Development Set SimData RealData GMM-HMM MFCC-LDA-MLLT-fMLLR logmelspec DNN-HMM enhanced logmelspec logmelspec+ +melmsc logmelspec+ +meldiffuseness Avg Avg Avg 12
arxiv: v1 [cs.lg] 4 Aug 2016
An improved uncertainty decoding scheme with weighted samples for DNN-HMM hybrid systems Christian Huemmer 1, Ramón Fernández Astudillo 2, and Walter Kellermann 1 1 Multimedia Communications and Signal
More informationDeep Learning for Speech Recognition. Hung-yi Lee
Deep Learning for Speech Recognition Hung-yi Lee Outline Conventional Speech Recognition How to use Deep Learning in acoustic modeling? Why Deep Learning? Speaker Adaptation Multi-task Deep Learning New
More informationUncertainty training and decoding methods of deep neural networks based on stochastic representation of enhanced features
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Uncertainty training and decoding methods of deep neural networks based on stochastic representation of enhanced features Tachioka, Y.; Watanabe,
More informationMASK WEIGHTED STFT RATIOS FOR RELATIVE TRANSFER FUNCTION ESTIMATION AND ITS APPLICATION TO ROBUST ASR
MASK WEIGHTED STFT RATIOS FOR RELATIVE TRANSFER FUNCTION ESTIMATION AND ITS APPLICATION TO ROBUST ASR Zhong-Qiu Wang, DeLiang Wang, Department of Computer Science and Engineering, The Ohio State University,
More informationUSING STATISTICAL ROOM ACOUSTICS FOR ANALYSING THE OUTPUT SNR OF THE MWF IN ACOUSTIC SENSOR NETWORKS. Toby Christian Lawin-Ore, Simon Doclo
th European Signal Processing Conference (EUSIPCO 1 Bucharest, Romania, August 7-31, 1 USING STATISTICAL ROOM ACOUSTICS FOR ANALYSING THE OUTPUT SNR OF THE MWF IN ACOUSTIC SENSOR NETWORKS Toby Christian
More informationNOISE ROBUST RELATIVE TRANSFER FUNCTION ESTIMATION. M. Schwab, P. Noll, and T. Sikora. Technical University Berlin, Germany Communication System Group
NOISE ROBUST RELATIVE TRANSFER FUNCTION ESTIMATION M. Schwab, P. Noll, and T. Sikora Technical University Berlin, Germany Communication System Group Einsteinufer 17, 1557 Berlin (Germany) {schwab noll
More informationVery Deep Convolutional Neural Networks for LVCSR
INTERSPEECH 2015 Very Deep Convolutional Neural Networks for LVCSR Mengxiao Bi, Yanmin Qian, Kai Yu Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab,
More informationShinji Watanabe Mitsubishi Electric Research Laboratories (MERL) Xiong Xiao Nanyang Technological University. Marc Delcroix
Shinji Watanabe Mitsubishi Electric Research Laboratories (MERL) Xiong Xiao Nanyang Technological University Marc Delcroix NTT Communication Science Laboratories 2 1. 2. 3. 4. 3 List of abbreviations ASR
More informationMaking Machines Understand Us in Reverberant Rooms [Robustness against reverberation for automatic speech recognition]
Making Machines Understand Us in Reverberant Rooms [Robustness against reverberation for automatic speech recognition] Yoshioka, T., Sehr A., Delcroix M., Kinoshita K., Maas R., Nakatani T., Kellermann
More informationAdapting Wavenet for Speech Enhancement DARIO RETHAGE JULY 12, 2017
Adapting Wavenet for Speech Enhancement DARIO RETHAGE JULY 12, 2017 I am v Master Student v 6 months @ Music Technology Group, Universitat Pompeu Fabra v Deep learning for acoustic source separation v
More informationA unified convolutional beamformer for simultaneous denoising and dereverberation
1 A unified convolutional beamformer for simultaneous denoising and dereverberation Tomohiro Nakatani, Senior Member, IEEE, Keisuke Kinoshita, Senior Member, IEEE arxiv:1812.08400v2 [eess.as] 26 Dec 2018
More informationWhy DNN Works for Acoustic Modeling in Speech Recognition?
Why DNN Works for Acoustic Modeling in Speech Recognition? Prof. Hui Jiang Department of Computer Science and Engineering York University, Toronto, Ont. M3J 1P3, CANADA Joint work with Y. Bao, J. Pan,
More informationResidual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition
INTERSPEECH 017 August 0 4, 017, Stockholm, Sweden Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition Jaeyoung Kim 1, Mostafa El-Khamy 1, Jungwon Lee 1 1 Samsung Semiconductor,
More informationGlobal SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks
Interspeech 2018 2-6 September 2018, Hyderabad Global SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks Rohith Aralikatti, Dilip Kumar Margam, Tanay Sharma,
More informationMULTI-FRAME FACTORISATION FOR LONG-SPAN ACOUSTIC MODELLING. Liang Lu and Steve Renals
MULTI-FRAME FACTORISATION FOR LONG-SPAN ACOUSTIC MODELLING Liang Lu and Steve Renals Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK {liang.lu, s.renals}@ed.ac.uk ABSTRACT
More informationA new method for a nonlinear acoustic echo cancellation system
A new method for a nonlinear acoustic echo cancellation system Tuan Van Huynh Department of Physics and Computer Science, Faculty of Physics and Engineering Physics, University of Science, Vietnam National
More informationEfficient Target Activity Detection Based on Recurrent Neural Networks
Efficient Target Activity Detection Based on Recurrent Neural Networks D. Gerber, S. Meier, and W. Kellermann Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Motivation Target φ tar oise 1 / 15
More informationRecent advances in distant speech recognition
Interspeech 2016 tutorial: Recent advances in distant speech recognition Marc Delcroix NTT Communication Science Laboratories Shinji Watanabe Mitsubishi Electric Research Laboratories (MERL) Table of contents
More informationFeature-space Speaker Adaptation for Probabilistic Linear Discriminant Analysis Acoustic Models
Feature-space Speaker Adaptation for Probabilistic Linear Discriminant Analysis Acoustic Models Liang Lu, Steve Renals Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK {liang.lu,
More informationDNN-based uncertainty estimation for weighted DNN-HMM ASR
DNN-based uncertainty estimation for weighted DNN-HMM ASR José Novoa, Josué Fredes, Nestor Becerra Yoma Speech Processing and Transmission Lab., Universidad de Chile nbecerra@ing.uchile.cl Abstract In
More informationAcoustic MIMO Signal Processing
Yiteng Huang Jacob Benesty Jingdong Chen Acoustic MIMO Signal Processing With 71 Figures Ö Springer Contents 1 Introduction 1 1.1 Acoustic MIMO Signal Processing 1 1.2 Organization of the Book 4 Part I
More informationSegmental Recurrent Neural Networks for End-to-end Speech Recognition
Segmental Recurrent Neural Networks for End-to-end Speech Recognition Liang Lu, Lingpeng Kong, Chris Dyer, Noah Smith and Steve Renals TTI-Chicago, UoE, CMU and UW 9 September 2016 Background A new wave
More information"Robust Automatic Speech Recognition through on-line Semi Blind Source Extraction"
"Robust Automatic Speech Recognition through on-line Semi Blind Source Extraction" Francesco Nesta, Marco Matassoni {nesta, matassoni}@fbk.eu Fondazione Bruno Kessler-Irst, Trento (ITALY) For contacts:
More informationThe THU-SPMI CHiME-4 system : Lightweight design with advanced multi-channel processing, feature enhancement, and language modeling
The THU-SPMI CHiME-4 system : Lightweight design with advanced multi-channel processing, feature enhancement, and language modeling Hongyu Xiang, Bin ang, Zhijian Ou Speech Processing and Machine Intelligence
More informationAn exploration of dropout with LSTMs
An exploration of out with LSTMs Gaofeng Cheng 1,3, Vijayaditya Peddinti 4,5, Daniel Povey 4,5, Vimal Manohar 4,5, Sanjeev Khudanpur 4,5,Yonghong Yan 1,2,3 1 Key Laboratory of Speech Acoustics and Content
More informationMultichannel Online Dereverberation based on Spectral Magnitude Inverse Filtering
1 Multichannel Online Dereverberation based on Spectral Magnitude Inverse Filtering Xiaofei Li, Laurent Girin, Sharon Gannot and Radu Horaud arxiv:1812.08471v1 [cs.sd] 20 Dec 2018 Abstract This paper addresses
More informationESTIMATION OF RELATIVE TRANSFER FUNCTION IN THE PRESENCE OF STATIONARY NOISE BASED ON SEGMENTAL POWER SPECTRAL DENSITY MATRIX SUBTRACTION
ESTIMATION OF RELATIVE TRANSFER FUNCTION IN THE PRESENCE OF STATIONARY NOISE BASED ON SEGMENTAL POWER SPECTRAL DENSITY MATRIX SUBTRACTION Xiaofei Li 1, Laurent Girin 1,, Radu Horaud 1 1 INRIA Grenoble
More informationMULTI-LABEL VS. COMBINED SINGLE-LABEL SOUND EVENT DETECTION WITH DEEP NEURAL NETWORKS. Emre Cakir, Toni Heittola, Heikki Huttunen and Tuomas Virtanen
MULTI-LABEL VS. COMBINED SINGLE-LABEL SOUND EVENT DETECTION WITH DEEP NEURAL NETWORKS Emre Cakir, Toni Heittola, Heikki Huttunen and Tuomas Virtanen Department of Signal Processing, Tampere University
More informationDetection of Overlapping Acoustic Events Based on NMF with Shared Basis Vectors
Detection of Overlapping Acoustic Events Based on NMF with Shared Basis Vectors Kazumasa Yamamoto Department of Computer Science Chubu University Kasugai, Aichi, Japan Email: yamamoto@cs.chubu.ac.jp Chikara
More informationJOINT DEREVERBERATION AND NOISE REDUCTION BASED ON ACOUSTIC MULTICHANNEL EQUALIZATION. Ina Kodrasi, Simon Doclo
JOINT DEREVERBERATION AND NOISE REDUCTION BASED ON ACOUSTIC MULTICHANNEL EQUALIZATION Ina Kodrasi, Simon Doclo University of Oldenburg, Department of Medical Physics and Acoustics, and Cluster of Excellence
More informationModeling Time-Frequency Patterns with LSTM vs. Convolutional Architectures for LVCSR Tasks
Modeling Time-Frequency Patterns with LSTM vs Convolutional Architectures for LVCSR Tasks Tara N Sainath, Bo Li Google, Inc New York, NY, USA {tsainath, boboli}@googlecom Abstract Various neural network
More informationIndependent Component Analysis and Unsupervised Learning. Jen-Tzung Chien
Independent Component Analysis and Unsupervised Learning Jen-Tzung Chien TABLE OF CONTENTS 1. Independent Component Analysis 2. Case Study I: Speech Recognition Independent voices Nonparametric likelihood
More informationSPEECH recognition systems based on hidden Markov
IEEE SIGNAL PROCESSING LETTERS, VOL. X, NO. X, 2014 1 Probabilistic Linear Discriminant Analysis for Acoustic Modelling Liang Lu, Member, IEEE and Steve Renals, Fellow, IEEE Abstract In this letter, we
More informationarxiv: v1 [cs.sd] 30 Oct 2015
ACE Challenge Workshop, a satellite event of IEEE-WASPAA 15 October 18-1, 15, New Paltz, NY ESTIMATION OF THE DIRECT-TO-REVERBERANT ENERGY RATIO USING A SPHERICAL MICROPHONE ARRAY Hanchi Chen, Prasanga
More informationTRINICON: A Versatile Framework for Multichannel Blind Signal Processing
TRINICON: A Versatile Framework for Multichannel Blind Signal Processing Herbert Buchner, Robert Aichner, Walter Kellermann {buchner,aichner,wk}@lnt.de Telecommunications Laboratory University of Erlangen-Nuremberg
More informationBLACK BOX OPTIMIZATION FOR AUTOMATIC SPEECH RECOGNITION. Shinji Watanabe and Jonathan Le Roux
2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) BLACK BOX OPTIMIZATION FOR AUTOMATIC SPEECH RECOGNITION Shinji Watanabe and Jonathan Le Roux Mitsubishi Electric Research
More informationEnvironmental Sound Classification in Realistic Situations
Environmental Sound Classification in Realistic Situations K. Haddad, W. Song Brüel & Kjær Sound and Vibration Measurement A/S, Skodsborgvej 307, 2850 Nærum, Denmark. X. Valero La Salle, Universistat Ramon
More informationBLIND SOURCE EXTRACTION FOR A COMBINED FIXED AND WIRELESS SENSOR NETWORK
2th European Signal Processing Conference (EUSIPCO 212) Bucharest, Romania, August 27-31, 212 BLIND SOURCE EXTRACTION FOR A COMBINED FIXED AND WIRELESS SENSOR NETWORK Brian Bloemendal Jakob van de Laar
More informationDeep clustering-based beamforming for separation with unknown number of sources
INTERSPEECH 2017 August 20 24, 2017, Stockholm, Sweden Deep clustering-based beamorming or separation with unknown number o sources Takuya Higuchi, Keisuke Kinoshita, Marc Delcroix, Kateřina Žmolíková,
More informationCOLLABORATIVE SPEECH DEREVERBERATION: REGULARIZED TENSOR FACTORIZATION FOR CROWDSOURCED MULTI-CHANNEL RECORDINGS. Sanna Wager, Minje Kim
COLLABORATIVE SPEECH DEREVERBERATION: REGULARIZED TENSOR FACTORIZATION FOR CROWDSOURCED MULTI-CHANNEL RECORDINGS Sanna Wager, Minje Kim Indiana University School of Informatics, Computing, and Engineering
More informationBeyond Cross-entropy: Towards Better Frame-level Objective Functions For Deep Neural Network Training In Automatic Speech Recognition
INTERSPEECH 2014 Beyond Cross-entropy: Towards Better Frame-level Objective Functions For Deep Neural Network Training In Automatic Speech Recognition Zhen Huang 1, Jinyu Li 2, Chao Weng 1, Chin-Hui Lee
More informationSpeaker recognition by means of Deep Belief Networks
Speaker recognition by means of Deep Belief Networks Vasileios Vasilakakis, Sandro Cumani, Pietro Laface, Politecnico di Torino, Italy {first.lastname}@polito.it 1. Abstract Most state of the art speaker
More informationRobust Sound Event Detection in Continuous Audio Environments
Robust Sound Event Detection in Continuous Audio Environments Haomin Zhang 1, Ian McLoughlin 2,1, Yan Song 1 1 National Engineering Laboratory of Speech and Language Information Processing The University
More informationIndependent Component Analysis and Unsupervised Learning
Independent Component Analysis and Unsupervised Learning Jen-Tzung Chien National Cheng Kung University TABLE OF CONTENTS 1. Independent Component Analysis 2. Case Study I: Speech Recognition Independent
More informationNoise Compensation for Subspace Gaussian Mixture Models
Noise ompensation for ubspace Gaussian Mixture Models Liang Lu University of Edinburgh Joint work with KK hin, A. Ghoshal and. enals Liang Lu, Interspeech, eptember, 2012 Outline Motivation ubspace GMM
More informationAN APPROACH TO PREVENT ADAPTIVE BEAMFORMERS FROM CANCELLING THE DESIRED SIGNAL. Tofigh Naghibi and Beat Pfister
AN APPROACH TO PREVENT ADAPTIVE BEAMFORMERS FROM CANCELLING THE DESIRED SIGNAL Tofigh Naghibi and Beat Pfister Speech Processing Group, Computer Engineering and Networks Lab., ETH Zurich, Switzerland {naghibi,pfister}@tik.ee.ethz.ch
More informationDetection-Based Speech Recognition with Sparse Point Process Models
Detection-Based Speech Recognition with Sparse Point Process Models Aren Jansen Partha Niyogi Human Language Technology Center of Excellence Departments of Computer Science and Statistics ICASSP 2010 Dallas,
More informationarxiv: v2 [cs.sd] 15 Nov 2017
Rank-1 Constrained Multichannel Wiener Filter for Speech Recognition in Noisy Environments Ziteng Wang a,, Emmanuel Vincent b, Romain Serizel c, Yonghong Yan a arxiv:1707.00201v2 [cs.sd] 15 Nov 2017 a
More informationMAXIMUM LIKELIHOOD BASED MULTI-CHANNEL ISOTROPIC REVERBERATION REDUCTION FOR HEARING AIDS
MAXIMUM LIKELIHOOD BASED MULTI-CHANNEL ISOTROPIC REVERBERATION REDUCTION FOR HEARING AIDS Adam Kuklasiński, Simon Doclo, Søren Holdt Jensen, Jesper Jensen, Oticon A/S, 765 Smørum, Denmark University of
More informationSPEECH signals captured using a distant microphone within
572 IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 25, NO. 3, MARCH 2017 Single-Channel Online Enhancement of Speech Corrupted by Reverberation and Noise Clement S. J. Doire, Student
More informationA comparative study of time-delay estimation techniques for convolutive speech mixtures
A comparative study of time-delay estimation techniques for convolutive speech mixtures COSME LLERENA AGUILAR University of Alcala Signal Theory and Communications 28805 Alcalá de Henares SPAIN cosme.llerena@uah.es
More informationBIDIRECTIONAL LSTM-HMM HYBRID SYSTEM FOR POLYPHONIC SOUND EVENT DETECTION
BIDIRECTIONAL LSTM-HMM HYBRID SYSTEM FOR POLYPHONIC SOUND EVENT DETECTION Tomoki Hayashi 1, Shinji Watanabe 2, Tomoki Toda 1, Takaaki Hori 2, Jonathan Le Roux 2, Kazuya Takeda 1 1 Nagoya University, Furo-cho,
More informationMultiple Sound Source Counting and Localization Based on Spatial Principal Eigenvector
INTERSPEECH 27 August 2 24, 27, Stockholm, Sweden Multiple Sound Source Counting and Localization Based on Spatial Principal Eigenvector Bing Yang, Hong Liu, Cheng Pang Key Laboratory of Machine Perception,
More informationAutomatic Speech Recognition (CS753)
Automatic Speech Recognition (CS753) Lecture 12: Acoustic Feature Extraction for ASR Instructor: Preethi Jyothi Feb 13, 2017 Speech Signal Analysis Generate discrete samples A frame Need to focus on short
More informationFeature-Space Structural MAPLR with Regression Tree-based Multiple Transformation Matrices for DNN
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Feature-Space Structural MAPLR with Regression Tree-based Multiple Transformation Matrices for DNN Kanagawa, H.; Tachioka, Y.; Watanabe, S.;
More informationarxiv: v1 [cs.cl] 23 Sep 2013
Feature Learning with Gaussian Restricted Boltzmann Machine for Robust Speech Recognition Xin Zheng 1,2, Zhiyong Wu 1,2,3, Helen Meng 1,3, Weifeng Li 1, Lianhong Cai 1,2 arxiv:1309.6176v1 [cs.cl] 23 Sep
More informationA Variance Modeling Framework Based on Variational Autoencoders for Speech Enhancement
A Variance Modeling Framework Based on Variational Autoencoders for Speech Enhancement Simon Leglaive 1 Laurent Girin 1,2 Radu Horaud 1 1: Inria Grenoble Rhône-Alpes 2: Univ. Grenoble Alpes, Grenoble INP,
More informationREGULARIZING DNN ACOUSTIC MODELS WITH GAUSSIAN STOCHASTIC NEURONS. Hao Zhang, Yajie Miao, Florian Metze
REGULARIZING DNN ACOUSTIC MODELS WITH GAUSSIAN STOCHASTIC NEURONS Hao Zhang, Yajie Miao, Florian Metze Language Technologies Institute, School of Computer Science, Carnegie Mellon University Pittsburgh,
More informationON ADVERSARIAL TRAINING AND LOSS FUNCTIONS FOR SPEECH ENHANCEMENT. Ashutosh Pandey 1 and Deliang Wang 1,2. {pandey.99, wang.5664,
ON ADVERSARIAL TRAINING AND LOSS FUNCTIONS FOR SPEECH ENHANCEMENT Ashutosh Pandey and Deliang Wang,2 Department of Computer Science and Engineering, The Ohio State University, USA 2 Center for Cognitive
More informationResearch Article Deep Neural Networks with Multistate Activation Functions
Computational Intelligence and Neuroscience Volume 5, Article ID 767, pages http://dx.doi.org/.55/5/767 Research Article Deep Neural Networks with Multistate Activation Functions Chenghao Cai, Yanyan u,
More informationMusical noise reduction in time-frequency-binary-masking-based blind source separation systems
Musical noise reduction in time-frequency-binary-masing-based blind source separation systems, 3, a J. Čermá, 1 S. Arai, 1. Sawada and 1 S. Maino 1 Communication Science Laboratories, Corporation, Kyoto,
More informationDeep NMF for Speech Separation
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Deep NMF for Speech Separation Le Roux, J.; Hershey, J.R.; Weninger, F.J. TR2015-029 April 2015 Abstract Non-negative matrix factorization
More informationSession Variability Compensation in Automatic Speaker Recognition
Session Variability Compensation in Automatic Speaker Recognition Javier González Domínguez VII Jornadas MAVIR Universidad Autónoma de Madrid November 2012 Outline 1. The Inter-session Variability Problem
More informationALTERNATIVE OBJECTIVE FUNCTIONS FOR DEEP CLUSTERING
ALTERNATIVE OBJECTIVE FUNCTIONS FOR DEEP CLUSTERING Zhong-Qiu Wang,2, Jonathan Le Roux, John R. Hershey Mitsubishi Electric Research Laboratories (MERL), USA 2 Department of Computer Science and Engineering,
More informationBLSTM-HMM HYBRID SYSTEM COMBINED WITH SOUND ACTIVITY DETECTION NETWORK FOR POLYPHONIC SOUND EVENT DETECTION
BLSTM-HMM HYBRID SYSTEM COMBINED WITH SOUND ACTIVITY DETECTION NETWORK FOR POLYPHONIC SOUND EVENT DETECTION Tomoki Hayashi 1, Shinji Watanabe 2, Tomoki Toda 1, Takaaki Hori 2, Jonathan Le Roux 2, Kazuya
More informationSINGLE-CHANNEL BLIND ESTIMATION OF REVERBERATION PARAMETERS
SINGLE-CHANNEL BLIND ESTIMATION OF REVERBERATION PARAMETERS Clement S. J. Doire, Mike Brookes, Patrick A. Naylor, Dave Betts, Christopher M. Hicks, Mohammad A. Dmour, Søren Holdt Jensen Electrical and
More informationALGONQUIN - Learning dynamic noise models from noisy speech for robust speech recognition
ALGONQUIN - Learning dynamic noise models from noisy speech for robust speech recognition Brendan J. Freyl, Trausti T. Kristjanssonl, Li Deng 2, Alex Acero 2 1 Probabilistic and Statistical Inference Group,
More informationDeep Neural Networks
Deep Neural Networks DT2118 Speech and Speaker Recognition Giampiero Salvi KTH/CSC/TMH giampi@kth.se VT 2015 1 / 45 Outline State-to-Output Probability Model Artificial Neural Networks Perceptron Multi
More informationSINGLE-CHANNEL SPEECH PRESENCE PROBABILITY ESTIMATION USING INTER-FRAME AND INTER-BAND CORRELATIONS
204 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) SINGLE-CHANNEL SPEECH PRESENCE PROBABILITY ESTIMATION USING INTER-FRAME AND INTER-BAND CORRELATIONS Hajar Momeni,2,,
More informationRobotic Sound Source Separation using Independent Vector Analysis Martin Rothbucher, Christian Denk, Martin Reverchon, Hao Shen and Klaus Diepold
Robotic Sound Source Separation using Independent Vector Analysis Martin Rothbucher, Christian Denk, Martin Reverchon, Hao Shen and Klaus Diepold Technical Report Robotic Sound Source Separation using
More informationTemporal Modeling and Basic Speech Recognition
UNIVERSITY ILLINOIS @ URBANA-CHAMPAIGN OF CS 498PS Audio Computing Lab Temporal Modeling and Basic Speech Recognition Paris Smaragdis paris@illinois.edu paris.cs.illinois.edu Today s lecture Recognizing
More informationSMALL-FOOTPRINT HIGH-PERFORMANCE DEEP NEURAL NETWORK-BASED SPEECH RECOGNITION USING SPLIT-VQ. Yongqiang Wang, Jinyu Li and Yifan Gong
SMALL-FOOTPRINT HIGH-PERFORMANCE DEEP NEURAL NETWORK-BASED SPEECH RECOGNITION USING SPLIT-VQ Yongqiang Wang, Jinyu Li and Yifan Gong Microsoft Corporation, One Microsoft Way, Redmond, WA 98052 {erw, jinyli,
More informationPHONEME CLASSIFICATION OVER THE RECONSTRUCTED PHASE SPACE USING PRINCIPAL COMPONENT ANALYSIS
PHONEME CLASSIFICATION OVER THE RECONSTRUCTED PHASE SPACE USING PRINCIPAL COMPONENT ANALYSIS Jinjin Ye jinjin.ye@mu.edu Michael T. Johnson mike.johnson@mu.edu Richard J. Povinelli richard.povinelli@mu.edu
More informationLINEARLY AUGMENTED DEEP NEURAL NETWORK
LINEARLY AUGMENTED DEEP NEURAL NETWORK Pegah Ghahremani Johns Hopkins University, Baltimore pghahre1@jhu.edu Jasha Droppo, Michael L. Seltzer Microsoft Research, Redmond {jdroppo,mseltzer}@microsoft.com
More informationFUNDAMENTAL LIMITATION OF FREQUENCY DOMAIN BLIND SOURCE SEPARATION FOR CONVOLVED MIXTURE OF SPEECH
FUNDAMENTAL LIMITATION OF FREQUENCY DOMAIN BLIND SOURCE SEPARATION FOR CONVOLVED MIXTURE OF SPEECH Shoko Araki Shoji Makino Ryo Mukai Tsuyoki Nishikawa Hiroshi Saruwatari NTT Communication Science Laboratories
More informationCoupled initialization of multi-channel non-negative matrix factorization based on spatial and spectral information
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Coupled initialization of multi-channel non-negative matrix factorization based on spatial and spectral information Tachioka, Y.; Narita, T.;
More informationLecture 3: ASR: HMMs, Forward, Viterbi
Original slides by Dan Jurafsky CS 224S / LINGUIST 285 Spoken Language Processing Andrew Maas Stanford University Spring 2017 Lecture 3: ASR: HMMs, Forward, Viterbi Fun informative read on phonetics The
More informationSPEECH ENHANCEMENT USING PCA AND VARIANCE OF THE RECONSTRUCTION ERROR IN DISTRIBUTED SPEECH RECOGNITION
SPEECH ENHANCEMENT USING PCA AND VARIANCE OF THE RECONSTRUCTION ERROR IN DISTRIBUTED SPEECH RECOGNITION Amin Haji Abolhassani 1, Sid-Ahmed Selouani 2, Douglas O Shaughnessy 1 1 INRS-Energie-Matériaux-Télécommunications,
More informationInvestigate more robust features for Speech Recognition using Deep Learning
DEGREE PROJECT IN ELECTRICAL ENGINEERING, SECOND CYCLE, 30 CREDITS STOCKHOLM, SWEDEN 2016 Investigate more robust features for Speech Recognition using Deep Learning TIPHANIE DENIAUX KTH ROYAL INSTITUTE
More informationSingle and Multi Channel Feature Enhancement for Distant Speech Recognition
Single and Multi Channel Feature Enhancement for Distant Speech Recognition John McDonough (1), Matthias Wölfel (2), Friedrich Faubel (3) (1) (2) (3) Saarland University Spoken Language Systems Overview
More informationRARE SOUND EVENT DETECTION USING 1D CONVOLUTIONAL RECURRENT NEURAL NETWORKS
RARE SOUND EVENT DETECTION USING 1D CONVOLUTIONAL RECURRENT NEURAL NETWORKS Hyungui Lim 1, Jeongsoo Park 1,2, Kyogu Lee 2, Yoonchang Han 1 1 Cochlear.ai, Seoul, Korea 2 Music and Audio Research Group,
More informationRecurrent Poisson Process Unit for Speech Recognition
Recurrent Poisson Process Unit for Speech Recognition Hengguan Huang 1, Hao Wang 2, Brian Mak 1 1 The Hong Kong University of Science and Technology 2 Massachusetts Institute of Technology {hhuangaj,mak}@cse.ust.hk,
More informationPresented By: Omer Shmueli and Sivan Niv
Deep Speaker: an End-to-End Neural Speaker Embedding System Chao Li, Xiaokong Ma, Bing Jiang, Xiangang Li, Xuewei Zhang, Xiao Liu, Ying Cao, Ajay Kannan, Zhenyao Zhu Presented By: Omer Shmueli and Sivan
More informationDeep Learning for Automatic Speech Recognition Part II
Deep Learning for Automatic Speech Recognition Part II Xiaodong Cui IBM T. J. Watson Research Center Yorktown Heights, NY 10598 Fall, 2018 Outline A brief revisit of sampling, pitch/formant and MFCC DNN-HMM
More informationROBUSTNESS OF PARAMETRIC SOURCE DEMIXING IN ECHOIC ENVIRONMENTS. Radu Balan, Justinian Rosca, Scott Rickard
ROBUSTNESS OF PARAMETRIC SOURCE DEMIXING IN ECHOIC ENVIRONMENTS Radu Balan, Justinian Rosca, Scott Rickard Siemens Corporate Research Multimedia and Video Technology Princeton, NJ 5 fradu.balan,justinian.rosca,scott.rickardg@scr.siemens.com
More informationUnfolded Recurrent Neural Networks for Speech Recognition
INTERSPEECH 2014 Unfolded Recurrent Neural Networks for Speech Recognition George Saon, Hagen Soltau, Ahmad Emami and Michael Picheny IBM T. J. Watson Research Center, Yorktown Heights, NY, 10598 gsaon@us.ibm.com
More informationTime-Varying Autoregressions for Speaker Verification in Reverberant Conditions
INTERSPEECH 017 August 0 4, 017, Stockholm, Sweden Time-Varying Autoregressions for Speaker Verification in Reverberant Conditions Ville Vestman 1, Dhananjaya Gowda, Md Sahidullah 1, Paavo Alku 3, Tomi
More informationShort-Time Fourier Transform and Chroma Features
Friedrich-Alexander-Universität Erlangen-Nürnberg Lab Course Short-Time Fourier Transform and Chroma Features International Audio Laboratories Erlangen Prof. Dr. Meinard Müller Friedrich-Alexander Universität
More informationDept. Electronics and Electrical Engineering, Keio University, Japan. NTT Communication Science Laboratories, NTT Corporation, Japan.
JOINT SEPARATION AND DEREVERBERATION OF REVERBERANT MIXTURES WITH DETERMINED MULTICHANNEL NON-NEGATIVE MATRIX FACTORIZATION Hideaki Kagami, Hirokazu Kameoka, Masahiro Yukawa Dept. Electronics and Electrical
More informationTensor-Train Long Short-Term Memory for Monaural Speech Enhancement
1 Tensor-Train Long Short-Term Memory for Monaural Speech Enhancement Suman Samui, Indrajit Chakrabarti, and Soumya K. Ghosh, arxiv:1812.10095v1 [cs.sd] 25 Dec 2018 Abstract In recent years, Long Short-Term
More informationLoudspeaker Choice and Placement. D. G. Meyer School of Electrical & Computer Engineering
Loudspeaker Choice and Placement D. G. Meyer School of Electrical & Computer Engineering Outline Sound System Design Goals Review Acoustic Environment Outdoors Acoustic Environment Indoors Loudspeaker
More informationSource localization and separation for binaural hearing aids
Source localization and separation for binaural hearing aids Mehdi Zohourian, Gerald Enzner, Rainer Martin Listen Workshop, July 218 Institute of Communication Acoustics Outline 1 Introduction 2 Binaural
More informationEstimation of Cepstral Coefficients for Robust Speech Recognition
Estimation of Cepstral Coefficients for Robust Speech Recognition by Kevin M. Indrebo, B.S., M.S. A Dissertation submitted to the Faculty of the Graduate School, Marquette University, in Partial Fulfillment
More informationIntegrating neural network based beamforming and weighted prediction error dereverberation
Interspeech 2018 2-6 September 2018, Hyderabad Integrating neural network based beamorming and weighted prediction error dereverberation Lukas Drude 1, Christoph Boeddeker 1, Jahn Heymann 1, Reinhold Haeb-Umbach
More informationNoise Robust Isolated Words Recognition Problem Solving Based on Simultaneous Perturbation Stochastic Approximation Algorithm
EngOpt 2008 - International Conference on Engineering Optimization Rio de Janeiro, Brazil, 0-05 June 2008. Noise Robust Isolated Words Recognition Problem Solving Based on Simultaneous Perturbation Stochastic
More informationBlind Machine Separation Te-Won Lee
Blind Machine Separation Te-Won Lee University of California, San Diego Institute for Neural Computation Blind Machine Separation Problem we want to solve: Single microphone blind source separation & deconvolution
More informationCovariance Matrix Enhancement Approach to Train Robust Gaussian Mixture Models of Speech Data
Covariance Matrix Enhancement Approach to Train Robust Gaussian Mixture Models of Speech Data Jan Vaněk, Lukáš Machlica, Josef V. Psutka, Josef Psutka University of West Bohemia in Pilsen, Univerzitní
More informationSparse Models for Speech Recognition
Sparse Models for Speech Recognition Weibin Zhang and Pascale Fung Human Language Technology Center Hong Kong University of Science and Technology Outline Introduction to speech recognition Motivations
More informationSTFT Bin Selection for Localization Algorithms based on the Sparsity of Speech Signal Spectra
STFT Bin Selection for Localization Algorithms based on the Sparsity of Speech Signal Spectra Andreas Brendel, Chengyu Huang, and Walter Kellermann Multimedia Communications and Signal Processing, Friedrich-Alexander-Universität
More informationExploring the Relationship between Conic Affinity of NMF Dictionaries and Speech Enhancement Metrics
Interspeech 2018 2-6 September 2018, Hyderabad Exploring the Relationship between Conic Affinity of NMF Dictionaries and Speech Enhancement Metrics Pavlos Papadopoulos, Colin Vaz, Shrikanth Narayanan Signal
More information