Bo#leneck Features from SNR- Adap9ve Denoising Deep Classifier for Speaker Iden9fica9on
|
|
- Aubrey Gray
- 5 years ago
- Views:
Transcription
1 Bo#leneck Features from SNR- Adap9ve Denoising Deep Classifier for Speaker Iden9fica9on TAN Zhili & MAK Man-Wai APSIPA 2015 Department of Electronic and Informa2on Engineering The Hong Kong Polytechnic University, Hong Kong SAR, China
2 Contents 1. Mo2va2on of Work 2. Deep Belief Network 3. Denoising Autoencoder 4. Denoising Classifier 5. I-Vector and PLDA for Speaker Recogni2on 6. Experiments on YOHO Corpus 7. Conclusions 2
3 Overview of Speaker Iden9fica9on utt. 1 Feature Vector 1 utt. 2 Feature Vector 2 utt. 3 Feature Extraction Feature Vector 3 Classification Speaker ID utt. n Feature Vector n 3
4 Mo9va9on Features in speaker identification, e.g. mel-frequency cepstral coefficient (MFCC), are not designed particularly for extracting speakerdependent information are not noise robust Learning-based features outperform traditional handcrafted features in many areas, e.g. computer vision. 4
5 Proposed Solu9on With noisy speech input, train the deep neural network (DNN) by supervisory signal of both clean speech and speaker ID; Then use the output of the bottleneck layer as feature. Key features of proposed solution: Speaker-dependent Noise robust 5
6 Neural Networks Artificial neural networks (ANNs) are a family of statistical learning models inspired by biological neural networks (the brain). Its aim is to approximate the unknown function from input to target output. x = x 1 x 2 x 3 w 1 w 2 w 3 b 6
7 Deep Belief Network Deep Neural Network with pre-training and finetuning Pre-training: Restricted Boltzmann Machine Fine-tuning: Back-propagation Output Output RBM RBM w 2 Hidden Layer Hidden Layer Input w 1 Hidden Layer Input w 2 +ε 2 w 1 +ε 1 7
8 Autoencoder A particular form of Deep Belief Network The output aims to reconstruct the input The structure is symmetric with respect to the middle layer For speech, the input and output are Gaussian First layer: Gaussian-Bernoulli RBM pre-train Last layer: Linear activation function Fine-tuning: squared error function 8
9 Autoencoder (cont d) RBM RBM Middle Layer 2 w 2 Middle Layer 1 Middle Layer 1 Input w 1 Output Layer Middle Layer 3 Middle Layer 2 Middle Layer 1 Input Layer w 1 T +ε 4 w 2 T +ε 3 w 2 +ε 2 w 1 +ε 1 9
10 Denoising Autoencoder Input: noisy speech Target output: corresponding clean counterpart After fine-tuning, the DAE has the denoising ability 10
11 DBN Classifier Target output: class label Last layer: soft-max function Fine-tuning: cross entropy as error function Class Label RBM Middle Layer 2 RBM w 2 Middle Layer 1 Middle Layer 1 w 1 Input Layer Middle Layer 2 Middle Layer 1 Input Layer w 3 w 2 +ε 2 w 1 +ε 1 11
12 Denoising Classifier Two RMBs are stacked on top of the denoising deep autoencoder The top-rbm layer is connected to class label layer of Speaker ID The first RBM connected to the output of autoencoder is also Gaussian-Bernoulli RBM The whole classifier is fine-tuned by backpropagation again 12
13 Denoising Classifier (cont d) BN Layer Speaker ID Denoised Speech RBM w 4 w 5 Hidden Layer 5 BN Layer BN Features Output Layer (Hidden Layer 4) w 4 +ε 6 w 1 T +ε 4 Hidden Layer 5 Hidden Layer 5 Hidden Layer 3 RBM w 3 w 3 +ε 5 w 2 T +ε 3 Hidden Layer 2 w 2 +ε 2 Hidden Layer 1 w 1 +ε 1 Denoising Deep Autoencoder Visible Layer Hidden Layer 4 w 1 T +ε 4 ' Hidden Layer 3 w 2 T +ε 3 ' Hidden Layer 2 Denoising Deep Classifier Input Layer w 2 +ε 2 ' Noisy Speech Noisy Speech Hidden Layer 1 w 1 +ε 1 ' Input Layer 13
14 I-Vector for Speaker Iden9fica9on Factor analysis model: Speaker-dependent supervector! µ =! µ + Tx s s Speaker-dependent i-vector UBM supervector Low-rank total variability matrix Instead of the high-dimension µ s (e.g ), we use the low-dimension (typically 500) i-vector x s to represent the speaker.! 14
15 Probabilis9c LDA Factor analysis model: i-vector extracted from the utterance of speaker s Defining Speaker subspace Global mean of all i-vectors x s = m + Vz s +ε s Speaker factor Residual noise with covariance Ʃ Then, speakers are compared in the speaker subspace based on z instead of the i-vectors x in the i-vector space, thus channel effect will be suppressed. 15
16 Experimental Setup Evaluation dataset: speech from 138 speakers in the YOHO corpus 96 utterances per speaker as training data Add Babble noise to SNR 15dB, 6dB and 0dB respectively by FaNT tool 40 utterances per SNR condition and per speaker as testing data Baseline: 19 MFCCs together with energy plus their 1st and 2nd derivativesà60-dim 16
17 DNN Setup Structure: D D D represents the dimension of the input vectors Input for DNN: (1) 1 frame of 256-Dim spectra (Log-spec BN) (2) 7 frames of 20-Dim Mel filter bank output (Log-mel BN) (3) 5 frames of 60-Dim MFCC (MFC BN) Packed with an SNR node Normalized by z-norm 17
18 I-Vector/PLDA Setup Decorrelation for BN features: PCA Whitening GMM-UBM: 256 mixtures Total Variability Matrix: 400 total factors PLDA: SNR independent with 138 latent variables Speaker identification: find the speaker ID having the highest averaged PLDA score given each test utterance 18
19 Denoising Ability of Autoencoder Denoised Speech Output of Hidden Layer 4 Speaker ID w 5 BN Layer BN Features w 4 +ε 6 Clean Speech Hidden Layer 5 Output Layer (Hidden Layer 4) w 1 T +ε 4 Hidden Layer 3 w 3 +ε 5 Hidden Layer 4 w 1 T +ε 4 ' Hidden Layer 3 Denoising Deep Classifier FaNT - 0dB SNR Noisy Speech w 2 T +ε 3 Hidden Layer 2 w 2 +ε 2 Denoising Deep Autoencoder w 2 T +ε 3 ' Hidden Layer 2 w 2 +ε 2 ' Hidden Layer 1 Hidden Layer 1 w 1 +ε 1 w 1 +ε 1 ' Input Layer Input Layer 19
20 Result Log-mel BN outperforms MFCC under noisy condistions 20
21 PLDA Score Combina9on At the PLDA score level, we can fuse the MFCC and the BN features Further improve the performance of speaker identification is the fusion rate and denotes the PLDA scores. 21
22 PLDA Score Combina9on (cont d) Feature Fusion Weight SNR of Test Utterances Clean 15dB 6dB 0dB MFCC % 95.61% 90.05% 65.65% Log-spec BN % 97.88% 94.02% 79.66% Log-mel BN % 98.46% 94.92% 82.50% MFC BN % 96.41% 92.80% 75.45% Score fusion increases the accuracy significantly BN features and MFCC are complementary to each other 22
23 Results on Speaker Verifica9on Results in terms of EER (in %) and mindcf ( 1000): lower is better Signal-to-noise Ra2o (SNR) Clean 15dB 6dB 0dB EER mindcf EER mindcf EER mindcf EER mindcf MFCC Log-mel BN EER: crossing point of FAR and FRR DCF: linear combination of FAR and FRR 23
24 Conclusions On speaker identification task, our Log-mel BN features are comparable with the standard MFCC The BN features and MFCC are complementary to each other, leading to signicant performance gain after fusing the MFCC- and BN-based PLDA scores. On speaker verification task, our Log-mel BN features from denoising deep classier outperform MFCC for all SNR conditions. 24
25 THANKS! Q & A 25
26 APPENDIX 26
27 PLDA Scoring x s = m + Vz s +ε s x t = m + Vz t +ε t 27
28 Results of Score Combina9on 28
Machine Learning for Speaker Recogni2on and Bioinforma2cs
Machine Learning for Speaker Recogni2on and Bioinforma2cs Man-Wai MAK Dept of Electronic and Informa8on Engineering, The Hong Kong Polytechnic University http://wwweiepolyueduhk/~mwmak/ UTS/PolyU Workshop
More informationSPEECH FEATURE DENOISING AND DEREVERBERATION VIA DEEP AUTOENCODERS FOR NOISY REVERBERANT SPEECH RECOGNITION. Xue Feng, Yaodong Zhang, James Glass
2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) SPEECH FEATURE DENOISING AND DEREVERBERATION VIA DEEP AUTOENCODERS FOR NOISY REVERBERANT SPEECH RECOGNITION Xue Feng,
More informationSUT Submission for NIST 2016 Speaker Recognition Evaluation: Description and Analysis
The 2017 Conference on Computational Linguistics and Speech Processing ROCLING 2017, pp. 276-286 The Association for Computational Linguistics and Chinese Language Processing SUT Submission for NIST 2016
More informationVariable-Component Deep Neural Network for Robust Speech Recognition
Variable-Component Deep Neural Network for Robust Speech Recognition Rui Zhao 1, Jinyu Li 2, and Yifan Gong 2 1 Microsoft Search Technology Center Asia, Beijing, China 2 Microsoft Corporation, One Microsoft
More informationNovel Subband Autoencoder Features for Non-intrusive Quality Assessment of Noise Suppressed Speech
INTERSPEECH 16 September 8 12, 16, San Francisco, USA Novel Subband Autoencoder Features for Non-intrusive Quality Assessment of Noise Suppressed Speech Meet H. Soni, Hemant A. Patil Dhirubhai Ambani Institute
More informationImproving Bottleneck Features for Automatic Speech Recognition using Gammatone-based Cochleagram and Sparsity Regularization
Improving Bottleneck Features for Automatic Speech Recognition using Gammatone-based Cochleagram and Sparsity Regularization Chao Ma 1,2,3, Jun Qi 4, Dongmei Li 1,2,3, Runsheng Liu 1,2,3 1. Department
More informationSTC ANTI-SPOOFING SYSTEMS FOR THE ASVSPOOF 2015 CHALLENGE
STC ANTI-SPOOFING SYSTEMS FOR THE ASVSPOOF 2015 CHALLENGE Sergey Novoselov 1,2, Alexandr Kozlov 2, Galina Lavrentyeva 1,2, Konstantin Simonchik 1,2, Vadim Shchemelinin 1,2 1 ITMO University, St. Petersburg,
More informationStacked Denoising Autoencoders for Face Pose Normalization
Stacked Denoising Autoencoders for Face Pose Normalization Yoonseop Kang 1, Kang-Tae Lee 2,JihyunEun 2, Sung Eun Park 2 and Seungjin Choi 1 1 Department of Computer Science and Engineering Pohang University
More informationIMPROVED SPEAKER RECOGNITION USING DCT COEFFICIENTS AS FEATURES. Mitchell McLaren, Yun Lei
IMPROVED SPEAKER RECOGNITION USING DCT COEFFICIENTS AS FEATURES Mitchell McLaren, Yun Lei Speech Technology and Research Laboratory, SRI International, California, USA {mitch,yunlei}@speech.sri.com ABSTRACT
More informationComparative Evaluation of Feature Normalization Techniques for Speaker Verification
Comparative Evaluation of Feature Normalization Techniques for Speaker Verification Md Jahangir Alam 1,2, Pierre Ouellet 1, Patrick Kenny 1, Douglas O Shaughnessy 2, 1 CRIM, Montreal, Canada {Janagir.Alam,
More informationManifold Constrained Deep Neural Networks for ASR
1 Manifold Constrained Deep Neural Networks for ASR Department of Electrical and Computer Engineering, McGill University Richard Rose and Vikrant Tomar Motivation Speech features can be characterized as
More informationReverberant Speech Recognition Based on Denoising Autoencoder
INTERSPEECH 2013 Reverberant Speech Recognition Based on Denoising Autoencoder Takaaki Ishii 1, Hiroki Komiyama 1, Takahiro Shinozaki 2, Yasuo Horiuchi 1, Shingo Kuroiwa 1 1 Division of Information Sciences,
More informationarxiv: v1 [cs.sd] 8 Jun 2017
SUT SYSTEM DESCRIPTION FOR NIST SRE 2016 Hossein Zeinali 1,2, Hossein Sameti 1 and Nooshin Maghsoodi 1 1 Sharif University of Technology, Tehran, Iran 2 Brno University of Technology, Speech@FIT and IT4I
More informationAkarsh Pokkunuru EECS Department Contractive Auto-Encoders: Explicit Invariance During Feature Extraction
Akarsh Pokkunuru EECS Department 03-16-2017 Contractive Auto-Encoders: Explicit Invariance During Feature Extraction 1 AGENDA Introduction to Auto-encoders Types of Auto-encoders Analysis of different
More informationFOUR WEIGHTINGS AND A FUSION: A CEPSTRAL-SVM SYSTEM FOR SPEAKER RECOGNITION. Sachin S. Kajarekar
FOUR WEIGHTINGS AND A FUSION: A CEPSTRAL-SVM SYSTEM FOR SPEAKER RECOGNITION Sachin S. Kajarekar Speech Technology and Research Laboratory SRI International, Menlo Park, CA, USA sachin@speech.sri.com ABSTRACT
More informationCOMP 551 Applied Machine Learning Lecture 16: Deep Learning
COMP 551 Applied Machine Learning Lecture 16: Deep Learning Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: Class web page: www.cs.mcgill.ca/~hvanho2/comp551 Unless otherwise noted, all
More informationSPEECH FEATURE EXTRACTION USING WEIGHTED HIGHER-ORDER LOCAL AUTO-CORRELATION
Far East Journal of Electronics and Communications Volume 3, Number 2, 2009, Pages 125-140 Published Online: September 14, 2009 This paper is available online at http://www.pphmj.com 2009 Pushpa Publishing
More informationDay 3 Lecture 1. Unsupervised Learning
Day 3 Lecture 1 Unsupervised Learning Semi-supervised and transfer learning Myth: you can t do deep learning unless you have a million labelled examples for your problem. Reality You can learn useful representations
More informationGrundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Unsupervised learning Daniel Hennes 29.01.2018 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Supervised learning Regression (linear
More informationPitch Prediction from Mel-frequency Cepstral Coefficients Using Sparse Spectrum Recovery
Pitch Prediction from Mel-frequency Cepstral Coefficients Using Sparse Spectrum Recovery Achuth Rao MV, Prasanta Kumar Ghosh SPIRE LAB Electrical Engineering, Indian Institute of Science (IISc), Bangalore,
More informationLec 08 Feature Aggregation II: Fisher Vector, Super Vector and AKULA
Image Analysis & Retrieval CS/EE 5590 Special Topics (Class Ids: 44873, 44874) Fall 2016, M/W 4-5:15pm@Bloch 0012 Lec 08 Feature Aggregation II: Fisher Vector, Super Vector and AKULA Zhu Li Dept of CSEE,
More informationDeep Learning. Volker Tresp Summer 2014
Deep Learning Volker Tresp Summer 2014 1 Neural Network Winter and Revival While Machine Learning was flourishing, there was a Neural Network winter (late 1990 s until late 2000 s) Around 2010 there
More informationSVD-based Universal DNN Modeling for Multiple Scenarios
SVD-based Universal DNN Modeling for Multiple Scenarios Changliang Liu 1, Jinyu Li 2, Yifan Gong 2 1 Microsoft Search echnology Center Asia, Beijing, China 2 Microsoft Corporation, One Microsoft Way, Redmond,
More informationGPU Accelerated Model Combination for Robust Speech Recognition and Keyword Search
GPU Accelerated Model Combination for Robust Speech Recognition and Keyword Search Wonkyum Lee Jungsuk Kim Ian Lane Electrical and Computer Engineering Carnegie Mellon University March 26, 2014 @GTC2014
More informationDeep Learning. Volker Tresp Summer 2015
Deep Learning Volker Tresp Summer 2015 1 Neural Network Winter and Revival While Machine Learning was flourishing, there was a Neural Network winter (late 1990 s until late 2000 s) Around 2010 there
More informationIntroduction to Deep Learning
ENEE698A : Machine Learning Seminar Introduction to Deep Learning Raviteja Vemulapalli Image credit: [LeCun 1998] Resources Unsupervised feature learning and deep learning (UFLDL) tutorial (http://ufldl.stanford.edu/wiki/index.php/ufldl_tutorial)
More informationSpeaker Verification with Adaptive Spectral Subband Centroids
Speaker Verification with Adaptive Spectral Subband Centroids Tomi Kinnunen 1, Bingjun Zhang 2, Jia Zhu 2, and Ye Wang 2 1 Speech and Dialogue Processing Lab Institution for Infocomm Research (I 2 R) 21
More informationImage Restoration Using DNN
Image Restoration Using DNN Hila Levi & Eran Amar Images were taken from: http://people.tuebingen.mpg.de/burger/neural_denoising/ Agenda Domain Expertise vs. End-to-End optimization Image Denoising and
More informationA Deep Learning Framework for Authorship Classification of Paintings
A Deep Learning Framework for Authorship Classification of Paintings Kai-Lung Hua ( 花凱龍 ) Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei,
More informationPair-wise Distance Metric Learning of Neural Network Model for Spoken Language Identification
INTERSPEECH 2016 September 8 12, 2016, San Francisco, USA Pair-wise Distance Metric Learning of Neural Network Model for Spoken Language Identification 2 1 Xugang Lu 1, Peng Shen 1, Yu Tsao 2, Hisashi
More informationDeep Generative Models Variational Autoencoders
Deep Generative Models Variational Autoencoders Sudeshna Sarkar 5 April 2017 Generative Nets Generative models that represent probability distributions over multiple variables in some way. Directed Generative
More informationVulnerability of Voice Verification System with STC anti-spoofing detector to different methods of spoofing attacks
Vulnerability of Voice Verification System with STC anti-spoofing detector to different methods of spoofing attacks Vadim Shchemelinin 1,2, Alexandr Kozlov 2, Galina Lavrentyeva 2, Sergey Novoselov 1,2
More informationFUSION MODEL BASED ON CONVOLUTIONAL NEURAL NETWORKS WITH TWO FEATURES FOR ACOUSTIC SCENE CLASSIFICATION
Please contact the conference organizers at dcasechallenge@gmail.com if you require an accessible file, as the files provided by ConfTool Pro to reviewers are filtered to remove author information, and
More informationMultifactor Fusion for Audio-Visual Speaker Recognition
Proceedings of the 7th WSEAS International Conference on Signal, Speech and Image Processing, Beijing, China, September 15-17, 2007 70 Multifactor Fusion for Audio-Visual Speaker Recognition GIRIJA CHETTY
More informationEnergy Based Models, Restricted Boltzmann Machines and Deep Networks. Jesse Eickholt
Energy Based Models, Restricted Boltzmann Machines and Deep Networks Jesse Eickholt ???? Who s heard of Energy Based Models (EBMs) Restricted Boltzmann Machines (RBMs) Deep Belief Networks Auto-encoders
More informationOutlier detection using autoencoders
Outlier detection using autoencoders August 19, 2016 Author: Olga Lyudchik Supervisors: Dr. Jean-Roch Vlimant Dr. Maurizio Pierini CERN Non Member State Summer Student Report 2016 Abstract Outlier detection
More informationLecture 13. Deep Belief Networks. Michael Picheny, Bhuvana Ramabhadran, Stanley F. Chen
Lecture 13 Deep Belief Networks Michael Picheny, Bhuvana Ramabhadran, Stanley F. Chen IBM T.J. Watson Research Center Yorktown Heights, New York, USA {picheny,bhuvana,stanchen}@us.ibm.com 12 December 2012
More informationThe Approach of Mean Shift based Cosine Dissimilarity for Multi-Recording Speaker Clustering
The Approach of Mean Shift based Cosine Dissimilarity for Multi-Recording Speaker Clustering 1 D. Jareena Begum, 2 K Rajendra Prasad, 3 M Suleman Basha 1 M.Tech in SE, RGMCET, Nandyal 2 Assoc Prof, Dept
More informationEmotion Detection using Deep Belief Networks
Emotion Detection using Deep Belief Networks Kevin Terusaki and Vince Stigliani May 9, 2014 Abstract In this paper, we explore the exciting new field of deep learning. Recent discoveries have made it possible
More informationTutorial Deep Learning : Unsupervised Feature Learning
Tutorial Deep Learning : Unsupervised Feature Learning Joana Frontera-Pons 4th September 2017 - Workshop Dictionary Learning on Manifolds OUTLINE Introduction Representation Learning TensorFlow Examples
More informationPDF hosted at the Radboud Repository of the Radboud University Nijmegen
PDF hosted at the Radboud Repository of the Radboud University Nijmegen The following full text is a publisher's version. For additional information about this publication click this link. http://hdl.handle.net/2066/94752
More informationCS 6501: Deep Learning for Computer Graphics. Training Neural Networks II. Connelly Barnes
CS 6501: Deep Learning for Computer Graphics Training Neural Networks II Connelly Barnes Overview Preprocessing Initialization Vanishing/exploding gradients problem Batch normalization Dropout Additional
More informationTo be Bernoulli or to be Gaussian, for a Restricted Boltzmann Machine
2014 22nd International Conference on Pattern Recognition To be Bernoulli or to be Gaussian, for a Restricted Boltzmann Machine Takayoshi Yamashita, Masayuki Tanaka, Eiji Yoshida, Yuji Yamauchi and Hironobu
More informationAudio-visual Biometrics Using Reliability-based Late Fusion and Deep Neural Networks Mohammad Rafiqul Alam
Audio-visual Biometrics Using Reliability-based Late Fusion and Deep Neural Networks Mohammad Rafiqul Alam This thesis is presented for the degree of Doctor of Philosophy of The University of Western Australia
More informationNON-LINEAR DIMENSION REDUCTION OF GABOR FEATURES FOR NOISE-ROBUST ASR. Hitesh Anand Gupta, Anirudh Raju, Abeer Alwan
NON-LINEAR DIMENSION REDUCTION OF GABOR FEATURES FOR NOISE-ROBUST ASR Hitesh Anand Gupta, Anirudh Raju, Abeer Alwan Department of Electrical Engineering, University of California Los Angeles, USA {hiteshag,
More informationComparison of Clustering Methods: a Case Study of Text-Independent Speaker Modeling
Comparison of Clustering Methods: a Case Study of Text-Independent Speaker Modeling Tomi Kinnunen, Ilja Sidoroff, Marko Tuononen, Pasi Fränti Speech and Image Processing Unit, School of Computing, University
More informationAutoencoders, denoising autoencoders, and learning deep networks
4 th CiFAR Summer School on Learning and Vision in Biology and Engineering Toronto, August 5-9 2008 Autoencoders, denoising autoencoders, and learning deep networks Part II joint work with Hugo Larochelle,
More informationOptimization of Observation Membership Function By Particle Swarm Method for Enhancing Performances of Speaker Identification
Proceedings of the 6th WSEAS International Conference on SIGNAL PROCESSING, Dallas, Texas, USA, March 22-24, 2007 52 Optimization of Observation Membership Function By Particle Swarm Method for Enhancing
More informationAudio-visual speech recognition using deep bottleneck features and high-performance lipreading
Proceedings of APSIPA Annual Summit and Conference 215 16-19 December 215 Audio-visual speech recognition using deep bottleneck features and high-performance lipreading Satoshi TAMURA, Hiroshi NINOMIYA,
More informationQuery-by-example spoken term detection based on phonetic posteriorgram Query-by-example spoken term detection based on phonetic posteriorgram
International Conference on Education, Management and Computing Technology (ICEMCT 2015) Query-by-example spoken term detection based on phonetic posteriorgram Query-by-example spoken term detection based
More informationAn Optimization of Deep Neural Networks in ASR using Singular Value Decomposition
An Optimization of Deep Neural Networks in ASR using Singular Value Decomposition Bachelor Thesis of Igor Tseyzer At the Department of Informatics Institute for Anthropomatics (IFA) Reviewer: Second reviewer:
More informationWhy DNN Works for Speech and How to Make it More Efficient?
Why DNN Works for Speech and How to Make it More Efficient? Hui Jiang Department of Electrical Engineering and Computer Science Lassonde School of Engineering, York University, CANADA Joint work with Y.
More informationJoint Optimisation of Tandem Systems using Gaussian Mixture Density Neural Network Discriminative Sequence Training
Joint Optimisation of Tandem Systems using Gaussian Mixture Density Neural Network Discriminative Sequence Training Chao Zhang and Phil Woodland March 8, 07 Cambridge University Engineering Department
More informationUnsupervised Representation Learning Using Convolutional Restricted Boltzmann Machine for Spoof Speech Detection
INTERSPEECH 2017 August 20 24, 2017, Stockholm, Sweden Unsupervised Representation Learning Using Convolutional Restricted Boltzmann Machine for Spoof Speech Detection Hardik B. Sailor, Madhu R. Kamble,
More informationCOMPUTATIONAL INTELLIGENCE
COMPUTATIONAL INTELLIGENCE Radial Basis Function Networks Adrian Horzyk Preface Radial Basis Function Networks (RBFN) are a kind of artificial neural networks that use radial basis functions (RBF) as activation
More informationNajiya P Fathima, C. V. Vipin Kishnan; International Journal of Advance Research, Ideas and Innovations in Technology
ISSN: 2454-32X Impact factor: 4.295 (Volume 4, Issue 2) Available online at: www.ijariit.com Analysis of Different Classifier for the Detection of Double Compressed AMR Audio Fathima Najiya P najinasi2@gmail.com
More informationSRE08 system. Nir Krause Ran Gazit Gennady Karvitsky. Leave Impersonators, fraudsters and identity thieves speechless
Leave Impersonators, fraudsters and identity thieves speechless SRE08 system Nir Krause Ran Gazit Gennady Karvitsky Copyright 2008 PerSay Inc. All Rights Reserved Focus: Multilingual telephone speech and
More informationRestricted Boltzmann Machines. Shallow vs. deep networks. Stacked RBMs. Boltzmann Machine learning: Unsupervised version
Shallow vs. deep networks Restricted Boltzmann Machines Shallow: one hidden layer Features can be learned more-or-less independently Arbitrary function approximator (with enough hidden units) Deep: two
More informationComplex Identification Decision Based on Several Independent Speaker Recognition Methods. Ilya Oparin Speech Technology Center
Complex Identification Decision Based on Several Independent Speaker Recognition Methods Ilya Oparin Speech Technology Center Corporate Overview Global provider of voice biometric solutions Company name:
More informationCompressing Deep Neural Networks using a Rank-Constrained Topology
Compressing Deep Neural Networks using a Rank-Constrained Topology Preetum Nakkiran Department of EECS University of California, Berkeley, USA preetum@berkeley.edu Raziel Alvarez, Rohit Prabhavalkar, Carolina
More informationarxiv: v1 [cs.cl] 18 Jan 2015
Workshop on Knowledge-Powered Deep Learning for Text Mining (KPDLTM-2014) arxiv:1501.04325v1 [cs.cl] 18 Jan 2015 Lars Maaloe DTU Compute, Technical University of Denmark (DTU) B322, DK-2800 Lyngby Morten
More informationarxiv: v2 [cs.lg] 6 Jun 2015
HOPE (Zhang and Jiang) 1 Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks Shiliang Zhang and Hui Jiang arxiv:1502.00702v2 [cs.lg 6 Jun 2015 National
More informationMulti-pose lipreading and audio-visual speech recognition
RESEARCH Open Access Multi-pose lipreading and audio-visual speech recognition Virginia Estellers * and Jean-Philippe Thiran Abstract In this article, we study the adaptation of visual and audio-visual
More informationGYROPHONE RECOGNIZING SPEECH FROM GYROSCOPE SIGNALS. Yan Michalevsky (1), Gabi Nakibly (2) and Dan Boneh (1)
GYROPHONE RECOGNIZING SPEECH FROM GYROSCOPE SIGNALS Yan Michalevsky (1), Gabi Nakibly (2) and Dan Boneh (1) (1) Stanford University (2) National Research and Simulation Center, Rafael Ltd. 0 MICROPHONE
More informationIntroducing I-Vectors for Joint Anti-spoofing and Speaker Verification
Introducing I-Vectors for Joint Anti-spoofing and Speaker Verification Elie Khoury, Tomi Kinnunen, Aleksandr Sizov, Zhizheng Wu, Sébastien Marcel Idiap Research Institute, Switzerland School of Computing,
More informationNeural Networks and Deep Learning
Neural Networks and Deep Learning Example Learning Problem Example Learning Problem Celebrity Faces in the Wild Machine Learning Pipeline Raw data Feature extract. Feature computation Inference: prediction,
More informationParallel Implementation of Deep Learning Using MPI
Parallel Implementation of Deep Learning Using MPI CSE633 Parallel Algorithms (Spring 2014) Instructor: Prof. Russ Miller Team #13: Tianle Ma Email: tianlema@buffalo.edu May 7, 2014 Content Introduction
More informationNeural Networks: promises of current research
April 2008 www.apstat.com Current research on deep architectures A few labs are currently researching deep neural network training: Geoffrey Hinton s lab at U.Toronto Yann LeCun s lab at NYU Our LISA lab
More informationExtending reservoir computing with random static projections: a hybrid between extreme learning and RC
Extending reservoir computing with random static projections: a hybrid between extreme learning and RC John Butcher 1, David Verstraeten 2, Benjamin Schrauwen 2,CharlesDay 1 and Peter Haycock 1 1- Institute
More informationSYNTHESIZED STEREO MAPPING VIA DEEP NEURAL NETWORKS FOR NOISY SPEECH RECOGNITION
2014 IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP) SYNTHESIZED STEREO MAPPING VIA DEEP NEURAL NETWORKS FOR NOISY SPEECH RECOGNITION Jun Du 1, Li-Rong Dai 1, Qiang Huo
More informationAudio-visual interaction in sparse representation features for noise robust audio-visual speech recognition
ISCA Archive http://www.isca-speech.org/archive Auditory-Visual Speech Processing (AVSP) 2013 Annecy, France August 29 - September 1, 2013 Audio-visual interaction in sparse representation features for
More information1 Introduction. 3 Data Preprocessing. 2 Literature Review
Rock or not? This sure does. [Category] Audio & Music CS 229 Project Report Anand Venkatesan(anand95), Arjun Parthipan(arjun777), Lakshmi Manoharan(mlakshmi) 1 Introduction Music Genre Classification continues
More informationAn Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation
An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation Hugo Larochelle, Dumitru Erhan, Aaron Courville, James Bergstra, and Yoshua Bengio Université de Montréal 13/06/2007
More informationANALYSING REPLAY SPOOFING COUNTERMEASURE PERFORMANCE UNDER VARIED CONDITIONS
2018 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, SEPT. 17 20, 2018, AALBORG, DENMARK ANALYSING REPLAY SPOOFING COUNTERMEASURE PERFORMANCE UNDER VARIED CONDITIONS Bhusan Chettri
More informationMulti-Modal Human Verification Using Face and Speech
22 Multi-Modal Human Verification Using Face and Speech Changhan Park 1 and Joonki Paik 2 1 Advanced Technology R&D Center, Samsung Thales Co., Ltd., 2 Graduate School of Advanced Imaging Science, Multimedia,
More informationDeep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks
Deep Tracking: Biologically Inspired Tracking with Deep Convolutional Networks Si Chen The George Washington University sichen@gwmail.gwu.edu Meera Hahn Emory University mhahn7@emory.edu Mentor: Afshin
More informationFurther Studies of a FFT-Based Auditory Spectrum with Application in Audio Classification
ICSP Proceedings Further Studies of a FFT-Based Auditory with Application in Audio Classification Wei Chu and Benoît Champagne Department of Electrical and Computer Engineering McGill University, Montréal,
More informationNeural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing
Neural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing feature 3 PC 3 Beate Sick Many slides are taken form Hinton s great lecture on NN: https://www.coursera.org/course/neuralnets
More informationUsing Capsule Networks. for Image and Speech Recognition Problems. Yan Xiong
Using Capsule Networks for Image and Speech Recognition Problems by Yan Xiong A Thesis Presented in Partial Fulfillment of the Requirements for the Degree Master of Science Approved November 2018 by the
More informationABC submission for NIST SRE 2016
ABC submission for NIST SRE 2016 Agnitio+BUT+CRIM Oldrich Plchot, Pavel Matejka, Ondrej Novotny, Anna Silnova, Johan Rohdin, Mireia Diez, Ondrej Glembek, Xiaowei Jiang, Lukas Burget, Martin Karafiat, Lucas
More informationNeural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani
Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer
More informationA Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation
A Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation * A. H. M. Al-Helali, * W. A. Mahmmoud, and * H. A. Ali * Al- Isra Private University Email: adnan_hadi@yahoo.com Abstract:
More informationNeural Networks for Machine Learning. Lecture 15a From Principal Components Analysis to Autoencoders
Neural Networks for Machine Learning Lecture 15a From Principal Components Analysis to Autoencoders Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Principal Components
More informationOnline PLCA for Real-time Semi-supervised Source Separation
Online PLCA for Real-time Semi-supervised Source Separation Zhiyao Duan 1, Gautham J. Mysore 2 and Paris Smaragdis 2,3 1 EECS Department, Northwestern University, 2 Advanced Technology Labs, Adobe Systems
More informationFace Image Quality Assessment for Face Selection in Surveillance Video using Convolutional Neural Networks
Face Image Quality Assessment for Face Selection in Surveillance Video using Convolutional Neural Networks Vignesh Sankar, K. V. S. N. L. Manasa Priya, Sumohana Channappayya Indian Institute of Technology
More informationTemporal Multimodal Learning in Audiovisual Speech Recognition
Temporal Multimodal Learning in Audiovisual Speech Recognition Di Hu, Xuelong Li, Xiaoqiang Lu School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical
More informationDEEP LEARNING TO DIVERSIFY BELIEF NETWORKS FOR REMOTE SENSING IMAGE CLASSIFICATION
DEEP LEARNING TO DIVERSIFY BELIEF NETWORKS FOR REMOTE SENSING IMAGE CLASSIFICATION S.Dhanalakshmi #1 #PG Scholar, Department of Computer Science, Dr.Sivanthi Aditanar college of Engineering, Tiruchendur
More informationHello Edge: Keyword Spotting on Microcontrollers
Hello Edge: Keyword Spotting on Microcontrollers Yundong Zhang, Naveen Suda, Liangzhen Lai and Vikas Chandra ARM Research, Stanford University arxiv.org, 2017 Presented by Mohammad Mofrad University of
More informationarxiv: v1 [cs.sd] 24 May 2017
Anti-spoofing Methods for Automatic Speaker Verification System Galina Lavrentyeva 1,2, Sergey Novoselov 1,2, and Konstantin Simonchik 1,2 arxiv:1705.08865v1 [cs.sd] 24 May 2017 1 Speech Technology Center
More informationCOSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor
COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality
More informationA long, deep and wide artificial neural net for robust speech recognition in unknown noise
A long, deep and wide artificial neural net for robust speech recognition in unknown noise Feipeng Li, Phani S. Nidadavolu, and Hynek Hermansky Center for Language and Speech Processing Johns Hopkins University,
More informationMaking Deep Belief Networks Effective for Large Vocabulary Continuous Speech Recognition
Making Deep Belief Networks Effective for Large Vocabulary Continuous Speech Recognition Tara N. Sainath 1, Brian Kingsbury 1, Bhuvana Ramabhadran 1, Petr Fousek 2, Petr Novak 2, Abdel-rahman Mohamed 3
More informationSeparating Speech From Noise Challenge
Separating Speech From Noise Challenge We have used the data from the PASCAL CHiME challenge with the goal of training a Support Vector Machine (SVM) to estimate a noise mask that labels time-frames/frequency-bins
More informationReplay Attack Detection using DNN for Channel Discrimination
INTERSPEECH 2017 August 20 24, 2017, Stockholm, Sweden Replay Attack Detection using DNN for Channel Discrimination Parav Nagarsheth, Elie Khoury, Kailash Patil, Matt Garland Pindrop, Atlanta, USA {pnagarsheth,ekhoury,kpatil,matt.garland}@pindrop.com
More informationDeep Learning with R. Francesca Lazzeri Data Scientist II - Microsoft, AI Research
with R Francesca Lazzeri - @frlazzeri Data Scientist II - Microsoft, AI Research Agenda with R What is Demo Better understanding of R DL tools Fundamental concepts in Forward Propagation Algorithm Activation
More informationLearning robust features from underwater ship-radiated noise with mutual information group sparse DBN
Learning robust features from underwater ship-radiated noise with mutual information group sparse DBN Sheng SHEN ; Honghui YANG ; Zhen HAN ; Junun SHI ; Jinyu XIONG ; Xiaoyong ZHANG School of Marine Science
More informationAn Arabic Optical Character Recognition System Using Restricted Boltzmann Machines
An Arabic Optical Character Recognition System Using Restricted Boltzmann Machines Abdullah M. Rashwan, Mohamed S. Kamel, and Fakhri Karray University of Waterloo Abstract. Most of the state-of-the-art
More informationImproving Robustness to Compressed Speech in Speaker Recognition
INTERSPEECH 2013 Improving Robustness to Compressed Speech in Speaker Recognition Mitchell McLaren 1, Victor Abrash 1, Martin Graciarena 1, Yun Lei 1, Jan Pe sán 2 1 Speech Technology and Research Laboratory,
More informationSupervector Compression Strategies to Speed up I-Vector System Development
Supervector Compression Strategies to Speed up I-Vector System Development Ville Vestman Tomi Kinnunen University of Eastern Finland Finland vvestman@cs.uef.fi tkinnu@cs.uef.fi system can be achieved [5
More informationListening With Your Eyes: Towards a Practical. Visual Speech Recognition System
Listening With Your Eyes: Towards a Practical Visual Speech Recognition System By Chao Sui submitted in fulfilment of the requirements for the degree of Doctor of Philosophy School of Computer Science
More information