A Variance Modeling Framework Based on Variational Autoencoders for Speech Enhancement
|
|
- Rudolph Dixon
- 5 years ago
- Views:
Transcription
1 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, GIPSA-lab IEEE International Workshop on Machine Learning for Signal Processing (MLSP) September 18, 2018 Aalborg, Denmark
2 Introduction
3 Speech enhancement... noisy mixture signal speech enhancement clean speech signal Preprocessing step for various speech information retrieval tasks (e.g. automatic speech recognition, voice activity detection, etc.). 2
4 Speech enhancement as a source separation problem In the short-term Fourier transform (STFT) domain, for all (f, n) B = {0,..., F 1} {0,..., N 1}, we observe: x fn = s fn + b fn, (1) s fn C is the clean speech signal. b fn C is the noise signal. f is the frequency index and n the time-frame index. Objective: Separate the speech and noise signals from the observed mixture signal (under-determined problem). 3
5 Variance modeling with non-negative matrix factorization (NMF) From [1], independently for all (f, n) B: s fn N c ( 0, (W s H s ) f,n ), (2) W s R F Ks + is a dictionary matrix of spectral templates. H s R Ks N + is the activation matrix. K s is the rank of the factorization (usually K s (F + N) FN). [1] C. Févotte, N. Bertin and J. L. Durrieu, Nonnegative matrix factorization with the Itakura-Saito divergence: With application to music analysis, Neural computation,
6 Supervised NMF Supervised setting: W s is learned on a dataset of clean speech signals. H s is estimated from the noisy mixture signal. Pros and cons: Easy to interpret. Linear variance model E[ s fn 2 ] = (W s H s ) f,n = ws,f h s,n. Limited number of trainable parameters. 5
7 In this work we explore the use of neural networks as an alternative to this supervised NMF-based variance model. 6
8 Model
9 Speech variance modeling with neural networks From [2, 3], independently for all (f, n) B: z n N (0, I L ); (3) s fn z n N c (0, σ 2 f (z n)), (4) z n R L is a latent random vector with L F. σ 2 f : R L R + is a non-linear function parametrized by θ s. [2] D. P. Kingma and M. Welling, Auto-encoding variational Bayes, Proc. of ICLR, [3] Y. Bando et al., Statistical speech enhancement based on probabilistic integration of variational autoencoder and non-negative matrix factorization, Proc. of IEEE ICASSP,
10 Noise and mixture models Unsupervised noise model: Independently for all (f, n) B, ( ) b fn N c 0, (W b H b ) f,n, (5) where W b R F K b + and H b R K b N +. 8
11 Noise and mixture models Unsupervised noise model: Independently for all (f, n) B, ( ) b fn N c 0, (W b H b ) f,n, (5) where W b R F K b + and H b R K b N +. Mixture model: For all (f, n) B, where g n R + is a gain parameter. x fn = g n s fn + b fn, (6) 8
12 Noise and mixture models Unsupervised noise model: Independently for all (f, n) B, ( ) b fn N c 0, (W b H b ) f,n, (5) where W b R F K b + and H b R K b N +. Mixture model: For all (f, n) B, where g n R + is a gain parameter. x fn = g n s fn + b fn, (6) Conditional mixture distribution: x fn z n N c ( 0, g n σ 2 f (z n) + (W b H b ) f,n ). (7) 8
13 Inference
14 Parameters estimation For now, we assume that the speech parameters θ s have been learned during a training phase. Unsupervised model parameters: { } θ u = W b R F K b +, H b R K b N +, g = [g 0,..., g N 1 ] R N + Observed data: x = {x fn C} (f,n) B Direct maximum likelihood estimation is intractable 9
15 Parameters estimation For now, we assume that the speech parameters θ s have been learned during a training phase. Unsupervised model parameters: { } θ u = W b R F K b +, H b R K b N +, g = [g 0,..., g N 1 ] R N + Observed data: x = {x fn C} (f,n) B Direct maximum likelihood estimation is intractable Latent data: z = {z n R L } N 1 n=0 Expectation-maximization (EM) algorithm. 9
16 Monte Carlo EM algorithm E-Step. From the current value of the parameters θ u, compute: Q(θ u ; θ u) = E p(z x;θs,θ u ) [ln p(x, z; θ s, θ u )] 10
17 Monte Carlo EM algorithm E-Step. From the current value of the parameters θ u, compute: Q(θ u ; θu) = E p(z x;θs,θ u ) [ln p(x, z; θ s, θ u )] 1 R ) ln p (x, z (r) ; θ s, θ u, (8) R r=1 where the samples { z (r)} are asymptotically drawn from r=1,...,r p(z x; θ s, θu) using a Markov chain Monte Carlo method. 10
18 Monte Carlo EM algorithm E-Step. From the current value of the parameters θ u, compute: Q(θ u ; θu) = E p(z x;θs,θ u ) [ln p(x, z; θ s, θ u )] 1 R ) ln p (x, z (r) ; θ s, θ u, (8) R r=1 where the samples { z (r)} are asymptotically drawn from r=1,...,r p(z x; θ s, θu) using a Markov chain Monte Carlo method. M-Step. θ u arg max θ u Q(θ u ; θ u), (9) with θ u = {H b R K b N +, W b R F K b +, g R N +}. 10
19 Speech estimation Let s fn = g n s fn be the scaled speech STFT coefficients. Posterior mean estimation For all (f, n) B, ˆ s fn = E p( sfn x fn ;θ s,θ u)[ s fn ] [ g n σf 2 = E (z ] n) p(zn xn;θ s,θ u) g n σf 2(z x fn. (10) n) + (W b H b ) f,n Intractable expectation Markov chain Monte Carlo. 11
20 Training the generative model with variational autoencoders
21 Problem setting Training dataset of STFT speech time frames: s = {s n C F Ntr 1 } n=0. Generative model (reminder): Independently for all (f, n) B: z n N (0, I L ); s fn z n N c (0, σ 2 f (z n)), where z n R L Ntr 1 and in the following z = {z n } n=0. Problem: Learn the parameters θ s of this generative model (weights and biases of the neural network). Maximum likelihood is intractable variational autoencoders [2]. [2] D. P. Kingma and M. Welling, Auto-encoding variational Bayes, Proc. of ICLR,
22 Variational inference Find q(z s; φ) which approximates p(z s; θ s ). 13
23 Variational inference Find q(z s; φ) which approximates p(z s; θ s ). Kullback-Leibler divergence as a measure of fit: ) D KL (q(z s; φ) p(z s; θ s ) = ln p(s; θ s ) L(φ, θ s ), (11) where L(φ, θ s ) = E q(z s;φ) [ln p (s z; θ s )] }{{} Reconstruction accuracy D KL (q(z s; φ) p(z)). (12) }{{} Regularization We would like to maximize L(φ, θ s ) with respect to both φ and θ s. We need to define q(z s; φ). 13
24 Variational distribution Independently for all n {0,..., N tr 1} and l {0,..., L 1}: ( ( (z n ) l s n N µ l sn 2), σ l 2 denotes element-wise exponentiation; ( sn 2) ), (13) µ l : R F + R and σ l 2 parametrized by φ. : R F + R + are non-linear functions 14
25 Variational free energy L (θ s, φ) = c F f =0 L l=1 N tr 1 n=0 N tr 1 n=0 E q(zn s n;φ) [ ln σ 2 l ( )] [d IS s fn 2 ; σf 2 (z n) ( s n 2) µ l ( s n 2) 2 σ 2 l ( s n 2)], (14) where d IS (x; y) = x/y ln(x/y) 1 is the Itakura-Saito (IS) divergence. Intractable expectation approximated by a sample average ( reparametrization trick ). Differentiable with respect to both θ s and φ (backpropagation). Optimized using gradient-ascent-based algorithm. 15
26 Experiments
27 Dataset Clean speech signals: TIMIT database. Noise signals: DEMAND database (domestic environment, nature, office, indoor public spaces, street and transportation). Training: training set of TIMIT database; 4 hours of speech; 462 speakers. Testing: 168 noisy mixtures at 0 db signal-to-noise ratio; 1 sentence/speaker in the test set of TIMIT. 16
28 Semi-supervised NMF baseline Independently for all (f, n) B: s fn N c (0, (W s H s ) f,n ) and b fn N c (0, (W b H b ) f,n ). Training: From the observed clean speech signals min W s R F Ks Ks N +, H s R+ (f,n) B d IS ( s fn 2 ; (W s H s ) f,n ). Inference: From the observed mixture signal x fn = s fn + b fn, min Ks N H s R+, W b R F K b +, H b R K b N + (f,n) B d IS ( x fn 2 ; (W s H s + W b H b ) f,n ). (W s H s ) f,n Speech reconstruction: ŝ fn = x fn (W s H s + W b H b ) f,n 17
29 Fully-supervised deep-learning reference method Fully-supervised deep-learning approach proposed in [4]. A deep neural network is trained to map noisy speech log-power spectrograms to clean speech log-power spectrograms. Trained with more that 100 different noise types effective in handling unseen noise types. [4] Y. Xu et al., A regression approach to speech enhancement based on deep neural networks, IEEE Transactions on Audio, Speech and Language Processing,
30 Experiments The enhanced speech quality is evaluated in terms of: Signal-to-distortion ratio (SDR) in decibels (db). Perceptual evaluation of speech quality (PESQ) measure in between 0.5 and 4.5. The higher, the better. Different values for the latent dimension L and speech NMF rank K s : 8, 16, 32, 64 or
31 Experimental results (SDR) Median value indicated above each boxplot. 20
32 Experimental results (PESQ) Median value indicated above each boxplot. 21
33 Musical audio example. All models have been trained on speech (not singing voice). mixture original voice frequency (khz) 8 frequency (khz) time (s) fully-supervised DNN time (s) frequency (khz) 7 6 frequency (khz) 7 frequency (khz) time (s) proposed semi-supervised NMF time (s) time (s)
34 Conclusion
35 Conclusion Variational autoencoders are an interesting alternative to supervised NMF models. Some perspectives: Monte Carlo EM is slow variational inference; Temporal model on the latent variables; Multi-microphone extension; Uncertainty propagation for speech information retrieval. 23
36 Thank you Audio examples and code available online: 23
Variational inference
Simon Leglaive Télécom ParisTech, CNRS LTCI, Université Paris Saclay November 18, 2016, Télécom ParisTech, Paris, France. Outline Introduction Probabilistic model Problem Log-likelihood decomposition EM
More informationVariational Autoencoder
Variational Autoencoder Göker Erdo gan August 8, 2017 The variational autoencoder (VA) [1] is a nonlinear latent variable model with an efficient gradient-based training procedure based on variational
More informationStochastic Backpropagation, Variational Inference, and Semi-Supervised Learning
Stochastic Backpropagation, Variational Inference, and Semi-Supervised Learning Diederik (Durk) Kingma Danilo J. Rezende (*) Max Welling Shakir Mohamed (**) Stochastic Gradient Variational Inference Bayesian
More informationAuto-Encoding Variational Bayes
Auto-Encoding Variational Bayes Diederik P Kingma, Max Welling June 18, 2018 Diederik P Kingma, Max Welling Auto-Encoding Variational Bayes June 18, 2018 1 / 39 Outline 1 Introduction 2 Variational Lower
More informationGaussian Processes for Audio Feature Extraction
Gaussian Processes for Audio Feature Extraction Dr. Richard E. Turner (ret26@cam.ac.uk) Computational and Biological Learning Lab Department of Engineering University of Cambridge Machine hearing pipeline
More informationVariational Autoencoders (VAEs)
September 26 & October 3, 2017 Section 1 Preliminaries Kullback-Leibler divergence KL divergence (continuous case) p(x) andq(x) are two density distributions. Then the KL-divergence is defined as Z KL(p
More informationVariational Autoencoders
Variational Autoencoders Recap: Story so far A classification MLP actually comprises two components A feature extraction network that converts the inputs into linearly separable features Or nearly linearly
More informationLatent Variable Models
Latent Variable Models Stefano Ermon, Aditya Grover Stanford University Lecture 5 Stefano Ermon, Aditya Grover (AI Lab) Deep Generative Models Lecture 5 1 / 31 Recap of last lecture 1 Autoregressive models:
More informationExpectation-maximization algorithms for Itakura-Saito nonnegative matrix factorization
Expectation-maximization algorithms for Itakura-Saito nonnegative matrix factorization Paul Magron, Tuomas Virtanen To cite this version: Paul Magron, Tuomas Virtanen. Expectation-maximization algorithms
More informationDiscovering Convolutive Speech Phones using Sparseness and Non-Negativity Constraints
Discovering Convolutive Speech Phones using Sparseness and Non-Negativity Constraints Paul D. O Grady and Barak A. Pearlmutter Hamilton Institute, National University of Ireland Maynooth, Co. Kildare,
More informationMatrix Factorization for Speech Enhancement
Matrix Factorization for Speech Enhancement Peter Li Peter.Li@nyu.edu Yijun Xiao ryjxiao@nyu.edu 1 Introduction In this report, we explore techniques for speech enhancement using matrix factorization.
More informationESTIMATING TRAFFIC NOISE LEVELS USING ACOUSTIC MONITORING: A PRELIMINARY STUDY
ESTIMATING TRAFFIC NOISE LEVELS USING ACOUSTIC MONITORING: A PRELIMINARY STUDY Jean-Rémy Gloaguen, Arnaud Can Ifsttar - LAE Route de Bouaye - CS4 44344, Bouguenais, FR jean-remy.gloaguen@ifsttar.fr Mathieu
More informationNon-Negative Matrix Factorization And Its Application to Audio. Tuomas Virtanen Tampere University of Technology
Non-Negative Matrix Factorization And Its Application to Audio Tuomas Virtanen Tampere University of Technology tuomas.virtanen@tut.fi 2 Contents Introduction to audio signals Spectrogram representation
More informationNonnegative Matrix Factorization with Markov-Chained Bases for Modeling Time-Varying Patterns in Music Spectrograms
Nonnegative Matrix Factorization with Markov-Chained Bases for Modeling Time-Varying Patterns in Music Spectrograms Masahiro Nakano 1, Jonathan Le Roux 2, Hirokazu Kameoka 2,YuKitano 1, Nobutaka Ono 1,
More informationSINGLE CHANNEL SPEECH MUSIC SEPARATION USING NONNEGATIVE MATRIX FACTORIZATION AND SPECTRAL MASKS. Emad M. Grais and Hakan Erdogan
SINGLE CHANNEL SPEECH MUSIC SEPARATION USING NONNEGATIVE MATRIX FACTORIZATION AND SPECTRAL MASKS Emad M. Grais and Hakan Erdogan Faculty of Engineering and Natural Sciences, Sabanci University, Orhanli
More informationAn Efficient Posterior Regularized Latent Variable Model for Interactive Sound Source Separation
An Efficient Posterior Regularized Latent Variable Model for Interactive Sound Source Separation Nicholas J. Bryan Center for Computer Research in Music and Acoustics, Stanford University Gautham J. Mysore
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 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 informationProbabilistic Reasoning in Deep Learning
Probabilistic Reasoning in Deep Learning Dr Konstantina Palla, PhD palla@stats.ox.ac.uk September 2017 Deep Learning Indaba, Johannesburgh Konstantina Palla 1 / 39 OVERVIEW OF THE TALK Basics of Bayesian
More informationSingle Channel Music Sound Separation Based on Spectrogram Decomposition and Note Classification
Single Channel Music Sound Separation Based on Spectrogram Decomposition and Note Classification Hafiz Mustafa and Wenwu Wang Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey,
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 informationBayesian Deep Learning
Bayesian Deep Learning Mohammad Emtiyaz Khan AIP (RIKEN), Tokyo http://emtiyaz.github.io emtiyaz.khan@riken.jp June 06, 2018 Mohammad Emtiyaz Khan 2018 1 What will you learn? Why is Bayesian inference
More informationAN EM ALGORITHM FOR AUDIO SOURCE SEPARATION BASED ON THE CONVOLUTIVE TRANSFER FUNCTION
AN EM ALGORITHM FOR AUDIO SOURCE SEPARATION BASED ON THE CONVOLUTIVE TRANSFER FUNCTION Xiaofei Li, 1 Laurent Girin, 2,1 Radu Horaud, 1 1 INRIA Grenoble Rhône-Alpes, France 2 Univ. Grenoble Alpes, GIPSA-Lab,
More informationRecent Advances in Bayesian Inference Techniques
Recent Advances in Bayesian Inference Techniques Christopher M. Bishop Microsoft Research, Cambridge, U.K. research.microsoft.com/~cmbishop SIAM Conference on Data Mining, April 2004 Abstract Bayesian
More informationDeep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, Spis treści
Deep learning / Ian Goodfellow, Yoshua Bengio and Aaron Courville. - Cambridge, MA ; London, 2017 Spis treści Website Acknowledgments Notation xiii xv xix 1 Introduction 1 1.1 Who Should Read This Book?
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 informationVariational Inference via Stochastic Backpropagation
Variational Inference via Stochastic Backpropagation Kai Fan February 27, 2016 Preliminaries Stochastic Backpropagation Variational Auto-Encoding Related Work Summary Outline Preliminaries Stochastic Backpropagation
More informationPILCO: A Model-Based and Data-Efficient Approach to Policy Search
PILCO: A Model-Based and Data-Efficient Approach to Policy Search (M.P. Deisenroth and C.E. Rasmussen) CSC2541 November 4, 2016 PILCO Graphical Model PILCO Probabilistic Inference for Learning COntrol
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 informationDensity Estimation. Seungjin Choi
Density Estimation Seungjin Choi Department of Computer Science and Engineering Pohang University of Science and Technology 77 Cheongam-ro, Nam-gu, Pohang 37673, Korea seungjin@postech.ac.kr http://mlg.postech.ac.kr/
More informationLearning with Noisy Labels. Kate Niehaus Reading group 11-Feb-2014
Learning with Noisy Labels Kate Niehaus Reading group 11-Feb-2014 Outline Motivations Generative model approach: Lawrence, N. & Scho lkopf, B. Estimating a Kernel Fisher Discriminant in the Presence of
More informationEUSIPCO
EUSIPCO 213 1569744273 GAMMA HIDDEN MARKOV MODEL AS A PROBABILISTIC NONNEGATIVE MATRIX FACTORIZATION Nasser Mohammadiha, W. Bastiaan Kleijn, Arne Leijon KTH Royal Institute of Technology, Department of
More informationGenerative models for missing value completion
Generative models for missing value completion Kousuke Ariga Department of Computer Science and Engineering University of Washington Seattle, WA 98105 koar8470@cs.washington.edu Abstract Deep generative
More informationNONNEGATIVE MATRIX FACTORIZATION WITH TRANSFORM LEARNING. Dylan Fagot, Herwig Wendt and Cédric Févotte
NONNEGATIVE MATRIX FACTORIZATION WITH TRANSFORM LEARNING Dylan Fagot, Herwig Wendt and Cédric Févotte IRIT, Université de Toulouse, CNRS, Toulouse, France firstname.lastname@irit.fr ABSTRACT Traditional
More informationDeep Variational Inference. FLARE Reading Group Presentation Wesley Tansey 9/28/2016
Deep Variational Inference FLARE Reading Group Presentation Wesley Tansey 9/28/2016 What is Variational Inference? What is Variational Inference? Want to estimate some distribution, p*(x) p*(x) What is
More informationPosterior Regularization
Posterior Regularization 1 Introduction One of the key challenges in probabilistic structured learning, is the intractability of the posterior distribution, for fast inference. There are numerous methods
More informationNon-negative Matrix Factorization: Algorithms, Extensions and Applications
Non-negative Matrix Factorization: Algorithms, Extensions and Applications Emmanouil Benetos www.soi.city.ac.uk/ sbbj660/ March 2013 Emmanouil Benetos Non-negative Matrix Factorization March 2013 1 / 25
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 information502 IEEE SIGNAL PROCESSING LETTERS, VOL. 23, NO. 4, APRIL 2016
502 IEEE SIGNAL PROCESSING LETTERS, VOL. 23, NO. 4, APRIL 2016 Discriminative Training of NMF Model Based on Class Probabilities for Speech Enhancement Hanwook Chung, Student Member, IEEE, Eric Plourde,
More informationIntroduction to Machine Learning
Introduction to Machine Learning Brown University CSCI 1950-F, Spring 2012 Prof. Erik Sudderth Lecture 25: Markov Chain Monte Carlo (MCMC) Course Review and Advanced Topics Many figures courtesy Kevin
More informationScalable audio separation with light Kernel Additive Modelling
Scalable audio separation with light Kernel Additive Modelling Antoine Liutkus 1, Derry Fitzgerald 2, Zafar Rafii 3 1 Inria, Université de Lorraine, LORIA, UMR 7503, France 2 NIMBUS Centre, Cork Institute
More informationNon-Stationary Noise Power Spectral Density Estimation Based on Regional Statistics
Non-Stationary Noise Power Spectral Density Estimation Based on Regional Statistics Xiaofei Li, Laurent Girin, Sharon Gannot, Radu Horaud To cite this version: Xiaofei Li, Laurent Girin, Sharon Gannot,
More informationEXPLOITING LONG-TERM TEMPORAL DEPENDENCIES IN NMF USING RECURRENT NEURAL NETWORKS WITH APPLICATION TO SOURCE SEPARATION
EXPLOITING LONG-TERM TEMPORAL DEPENDENCIES IN NMF USING RECURRENT NEURAL NETWORKS WITH APPLICATION TO SOURCE SEPARATION Nicolas Boulanger-Lewandowski Gautham J. Mysore Matthew Hoffman Université de Montréal
More informationUnsupervised Learning
CS 3750 Advanced Machine Learning hkc6@pitt.edu Unsupervised Learning Data: Just data, no labels Goal: Learn some underlying hidden structure of the data P(, ) P( ) Principle Component Analysis (Dimensionality
More informationORTHOGONALITY-REGULARIZED MASKED NMF FOR LEARNING ON WEAKLY LABELED AUDIO DATA. Iwona Sobieraj, Lucas Rencker, Mark D. Plumbley
ORTHOGONALITY-REGULARIZED MASKED NMF FOR LEARNING ON WEAKLY LABELED AUDIO DATA Iwona Sobieraj, Lucas Rencker, Mark D. Plumbley University of Surrey Centre for Vision Speech and Signal Processing Guildford,
More informationSupervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization Nasser Mohammadiha*, Student Member, IEEE, Paris Smaragdis,
More informationPattern Recognition and Machine Learning. Bishop Chapter 9: Mixture Models and EM
Pattern Recognition and Machine Learning Chapter 9: Mixture Models and EM Thomas Mensink Jakob Verbeek October 11, 27 Le Menu 9.1 K-means clustering Getting the idea with a simple example 9.2 Mixtures
More informationLecture 16 Deep Neural Generative Models
Lecture 16 Deep Neural Generative Models CMSC 35246: Deep Learning Shubhendu Trivedi & Risi Kondor University of Chicago May 22, 2017 Approach so far: We have considered simple models and then constructed
More informationA State-Space Approach to Dynamic Nonnegative Matrix Factorization
1 A State-Space Approach to Dynamic Nonnegative Matrix Factorization Nasser Mohammadiha, Paris Smaragdis, Ghazaleh Panahandeh, Simon Doclo arxiv:179.5v1 [cs.lg] 31 Aug 17 Abstract Nonnegative matrix factorization
More informationMachine Learning Techniques for Computer Vision
Machine Learning Techniques for Computer Vision Part 2: Unsupervised Learning Microsoft Research Cambridge x 3 1 0.5 0.2 0 0.5 0.3 0 0.5 1 ECCV 2004, Prague x 2 x 1 Overview of Part 2 Mixture models EM
More informationNonparametric Bayesian Methods (Gaussian Processes)
[70240413 Statistical Machine Learning, Spring, 2015] Nonparametric Bayesian Methods (Gaussian Processes) Jun Zhu dcszj@mail.tsinghua.edu.cn http://bigml.cs.tsinghua.edu.cn/~jun State Key Lab of Intelligent
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 informationBlack-box α-divergence Minimization
Black-box α-divergence Minimization José Miguel Hernández-Lobato, Yingzhen Li, Daniel Hernández-Lobato, Thang Bui, Richard Turner, Harvard University, University of Cambridge, Universidad Autónoma de Madrid.
More informationSound Recognition in Mixtures
Sound Recognition in Mixtures Juhan Nam, Gautham J. Mysore 2, and Paris Smaragdis 2,3 Center for Computer Research in Music and Acoustics, Stanford University, 2 Advanced Technology Labs, Adobe Systems
More informationDeep Generative Models
Deep Generative Models Durk Kingma Max Welling Deep Probabilistic Models Worksop Wednesday, 1st of Oct, 2014 D.P. Kingma Deep generative models Transformations between Bayes nets and Neural nets Transformation
More informationBayesian Semi-supervised Learning with Deep Generative Models
Bayesian Semi-supervised Learning with Deep Generative Models Jonathan Gordon Department of Engineering Cambridge University jg801@cam.ac.uk José Miguel Hernández-Lobato Department of Engineering Cambridge
More informationThe connection of dropout and Bayesian statistics
The connection of dropout and Bayesian statistics Interpretation of dropout as approximate Bayesian modelling of NN http://mlg.eng.cam.ac.uk/yarin/thesis/thesis.pdf Dropout Geoffrey Hinton Google, University
More informationNatural Gradients via the Variational Predictive Distribution
Natural Gradients via the Variational Predictive Distribution Da Tang Columbia University datang@cs.columbia.edu Rajesh Ranganath New York University rajeshr@cims.nyu.edu Abstract Variational inference
More informationProbabilistic & Bayesian deep learning. Andreas Damianou
Probabilistic & Bayesian deep learning Andreas Damianou Amazon Research Cambridge, UK Talk at University of Sheffield, 19 March 2019 In this talk Not in this talk: CRFs, Boltzmann machines,... In this
More informationSTA 4273H: Statistical Machine Learning
STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 7 Approximate
More informationFACTORS IN FACTORIZATION: DOES BETTER AUDIO SOURCE SEPARATION IMPLY BETTER POLYPHONIC MUSIC TRANSCRIPTION?
FACTORS IN FACTORIZATION: DOES BETTER AUDIO SOURCE SEPARATION IMPLY BETTER POLYPHONIC MUSIC TRANSCRIPTION? Tiago Fernandes Tavares, George Tzanetakis, Peter Driessen University of Victoria Department of
More informationLow-Rank Time-Frequency Synthesis
Low-Rank - Synthesis Cédric Févotte Laboratoire Lagrange CNRS, OCA & Université de Nice Nice, France cfevotte@unice.fr Matthieu Kowalski Laboratoire des Signaux et Systèmes CNRS, Supélec & Université Paris-Sud
More informationPATTERN RECOGNITION AND MACHINE LEARNING
PATTERN RECOGNITION AND MACHINE LEARNING Chapter 1. Introduction Shuai Huang April 21, 2014 Outline 1 What is Machine Learning? 2 Curve Fitting 3 Probability Theory 4 Model Selection 5 The curse of dimensionality
More informationProbabilistic Graphical Models
10-708 Probabilistic Graphical Models Homework 3 (v1.1.0) Due Apr 14, 7:00 PM Rules: 1. Homework is due on the due date at 7:00 PM. The homework should be submitted via Gradescope. Solution to each problem
More informationIntroduction to Machine Learning
Introduction to Machine Learning Brown University CSCI 1950-F, Spring 2012 Prof. Erik Sudderth Lecture 20: Expectation Maximization Algorithm EM for Mixture Models Many figures courtesy Kevin Murphy s
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 informationNMF WITH SPECTRAL AND TEMPORAL CONTINUITY CRITERIA FOR MONAURAL SOUND SOURCE SEPARATION. Julian M. Becker, Christian Sohn and Christian Rohlfing
NMF WITH SPECTRAL AND TEMPORAL CONTINUITY CRITERIA FOR MONAURAL SOUND SOURCE SEPARATION Julian M. ecker, Christian Sohn Christian Rohlfing Institut für Nachrichtentechnik RWTH Aachen University D-52056
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 informationJOINT ACOUSTIC AND SPECTRAL MODELING FOR SPEECH DEREVERBERATION USING NON-NEGATIVE REPRESENTATIONS
JOINT ACOUSTIC AND SPECTRAL MODELING FOR SPEECH DEREVERBERATION USING NON-NEGATIVE REPRESENTATIONS Nasser Mohammadiha Paris Smaragdis Simon Doclo Dept. of Medical Physics and Acoustics and Cluster of Excellence
More informationMULTIPITCH ESTIMATION AND INSTRUMENT RECOGNITION BY EXEMPLAR-BASED SPARSE REPRESENTATION. Ikuo Degawa, Kei Sato, Masaaki Ikehara
MULTIPITCH ESTIMATION AND INSTRUMENT RECOGNITION BY EXEMPLAR-BASED SPARSE REPRESENTATION Ikuo Degawa, Kei Sato, Masaaki Ikehara EEE Dept. Keio University Yokohama, Kanagawa 223-8522 Japan E-mail:{degawa,
More informationVariational Inference in TensorFlow. Danijar Hafner Stanford CS University College London, Google Brain
Variational Inference in TensorFlow Danijar Hafner Stanford CS 20 2018-02-16 University College London, Google Brain Outline Variational Inference Tensorflow Distributions VAE in TensorFlow Variational
More informationProbabilistic Inference of Speech Signals from Phaseless Spectrograms
Probabilistic Inference of Speech Signals from Phaseless Spectrograms Kannan Achan, Sam T. Roweis, Brendan J. Frey Machine Learning Group University of Toronto Abstract Many techniques for complex speech
More informationREVIEW OF SINGLE CHANNEL SOURCE SEPARATION TECHNIQUES
REVIEW OF SINGLE CHANNEL SOURCE SEPARATION TECHNIQUES Kedar Patki University of Rochester Dept. of Electrical and Computer Engineering kedar.patki@rochester.edu ABSTRACT The paper reviews the problem of
More informationAuto-Encoding Variational Bayes. Stochastic Backpropagation and Approximate Inference in Deep Generative Models
Auto-Encoding Variational Bayes Diederik Kingma and Max Welling Stochastic Backpropagation and Approximate Inference in Deep Generative Models Danilo J. Rezende, Shakir Mohamed, Daan Wierstra Neural Variational
More informationProbabilistic Graphical Models
Probabilistic Graphical Models Brown University CSCI 2950-P, Spring 2013 Prof. Erik Sudderth Lecture 13: Learning in Gaussian Graphical Models, Non-Gaussian Inference, Monte Carlo Methods Some figures
More informationSTA 414/2104: Machine Learning
STA 414/2104: Machine Learning Russ Salakhutdinov Department of Computer Science! Department of Statistics! rsalakhu@cs.toronto.edu! http://www.cs.toronto.edu/~rsalakhu/ Lecture 9 Sequential Data So far
More informationVariational Principal Components
Variational Principal Components Christopher M. Bishop Microsoft Research 7 J. J. Thomson Avenue, Cambridge, CB3 0FB, U.K. cmbishop@microsoft.com http://research.microsoft.com/ cmbishop In Proceedings
More informationSUPERVISED NON-EUCLIDEAN SPARSE NMF VIA BILEVEL OPTIMIZATION WITH APPLICATIONS TO SPEECH ENHANCEMENT
SUPERVISED NON-EUCLIDEAN SPARSE NMF VIA BILEVEL OPTIMIZATION WITH APPLICATIONS TO SPEECH ENHANCEMENT Pablo Sprechmann, 1 Alex M. Bronstein, 2 and Guillermo Sapiro 1 1 Duke University, USA; 2 Tel Aviv University,
More informationMachine Learning and Bayesian Inference. Unsupervised learning. Can we find regularity in data without the aid of labels?
Machine Learning and Bayesian Inference Dr Sean Holden Computer Laboratory, Room FC6 Telephone extension 6372 Email: sbh11@cl.cam.ac.uk www.cl.cam.ac.uk/ sbh11/ Unsupervised learning Can we find regularity
More informationGWAS V: Gaussian processes
GWAS V: Gaussian processes Dr. Oliver Stegle Christoh Lippert Prof. Dr. Karsten Borgwardt Max-Planck-Institutes Tübingen, Germany Tübingen Summer 2011 Oliver Stegle GWAS V: Gaussian processes Summer 2011
More informationHow to do backpropagation in a brain
How to do backpropagation in a brain Geoffrey Hinton Canadian Institute for Advanced Research & University of Toronto & Google Inc. Prelude I will start with three slides explaining a popular type of deep
More informationAcoustic Vector Sensor based Speech Source Separation with Mixed Gaussian-Laplacian Distributions
Acoustic Vector Sensor based Speech Source Separation with Mixed Gaussian-Laplacian Distributions Xiaoyi Chen, Atiyeh Alinaghi, Xionghu Zhong and Wenwu Wang Department of Acoustic Engineering, School of
More informationDeep unsupervised learning
Deep unsupervised learning Advanced data-mining Yongdai Kim Department of Statistics, Seoul National University, South Korea Unsupervised learning In machine learning, there are 3 kinds of learning paradigm.
More informationADVANCED MACHINE LEARNING ADVANCED MACHINE LEARNING. Non-linear regression techniques Part - II
1 Non-linear regression techniques Part - II Regression Algorithms in this Course Support Vector Machine Relevance Vector Machine Support vector regression Boosting random projections Relevance vector
More informationTHE task of identifying the environment in which a sound
1 Feature Learning with Matrix Factorization Applied to Acoustic Scene Classification Victor Bisot, Romain Serizel, Slim Essid, and Gaël Richard Abstract In this paper, we study the usefulness of various
More informationAudio Source Separation Based on Convolutive Transfer Function and Frequency-Domain Lasso Optimization
Audio Source Separation Based on Convolutive Transfer Function and Frequency-Domain Lasso Optimization Xiaofei Li, Laurent Girin, Radu Horaud To cite this version: Xiaofei Li, Laurent Girin, Radu Horaud.
More informationIEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 18, NO. 3, MARCH
IEEE TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 18, NO. 3, MARCH 2010 589 Gamma Markov Random Fields for Audio Source Modeling Onur Dikmen, Member, IEEE, and A. Taylan Cemgil, Member,
More informationLONG-TERM REVERBERATION MODELING FOR UNDER-DETERMINED AUDIO SOURCE SEPARATION WITH APPLICATION TO VOCAL MELODY EXTRACTION.
LONG-TERM REVERBERATION MODELING FOR UNDER-DETERMINED AUDIO SOURCE SEPARATION WITH APPLICATION TO VOCAL MELODY EXTRACTION. Romain Hennequin Deezer R&D 10 rue d Athènes, 75009 Paris, France rhennequin@deezer.com
More informationProbabilistic Machine Learning
Probabilistic Machine Learning Bayesian Nets, MCMC, and more Marek Petrik 4/18/2017 Based on: P. Murphy, K. (2012). Machine Learning: A Probabilistic Perspective. Chapter 10. Conditional Independence Independent
More informationSource Separation Tutorial Mini-Series III: Extensions and Interpretations to Non-Negative Matrix Factorization
Source Separation Tutorial Mini-Series III: Extensions and Interpretations to Non-Negative Matrix Factorization Nicholas Bryan Dennis Sun Center for Computer Research in Music and Acoustics, Stanford University
More informationExpectation Propagation for Approximate Bayesian Inference
Expectation Propagation for Approximate Bayesian Inference José Miguel Hernández Lobato Universidad Autónoma de Madrid, Computer Science Department February 5, 2007 1/ 24 Bayesian Inference Inference Given
More informationSTA 4273H: Statistical Machine Learning
STA 4273H: Statistical Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! http://www.utstat.utoronto.ca/~rsalakhu/ Sidney Smith Hall, Room 6002 Lecture 11 Project
More informationMULTI-RESOLUTION SIGNAL DECOMPOSITION WITH TIME-DOMAIN SPECTROGRAM FACTORIZATION. Hirokazu Kameoka
MULTI-RESOLUTION SIGNAL DECOMPOSITION WITH TIME-DOMAIN SPECTROGRAM FACTORIZATION Hiroazu Kameoa The University of Toyo / Nippon Telegraph and Telephone Corporation ABSTRACT This paper proposes a novel
More informationProbabilistic Graphical Models for Image Analysis - Lecture 1
Probabilistic Graphical Models for Image Analysis - Lecture 1 Alexey Gronskiy, Stefan Bauer 21 September 2018 Max Planck ETH Center for Learning Systems Overview 1. Motivation - Why Graphical Models 2.
More informationLecture : Probabilistic Machine Learning
Lecture : Probabilistic Machine Learning Riashat Islam Reasoning and Learning Lab McGill University September 11, 2018 ML : Many Methods with Many Links Modelling Views of Machine Learning Machine Learning
More informationTUTORIAL PART 1 Unsupervised Learning
TUTORIAL PART 1 Unsupervised Learning Marc'Aurelio Ranzato Department of Computer Science Univ. of Toronto ranzato@cs.toronto.edu Co-organizers: Honglak Lee, Yoshua Bengio, Geoff Hinton, Yann LeCun, Andrew
More informationOPTIMAL WEIGHT LEARNING FOR COUPLED TENSOR FACTORIZATION WITH MIXED DIVERGENCES
OPTIMAL WEIGHT LEARNING FOR COUPLED TENSOR FACTORIZATION WITH MIXED DIVERGENCES Umut Şimşekli, Beyza Ermiş, A. Taylan Cemgil Boğaziçi University Dept. of Computer Engineering 34342, Bebek, İstanbul, Turkey
More informationarxiv: v5 [cs.lg] 2 Nov 2015
A Recurrent Latent Variable Model for Sequential Data arxiv:1506.02216v5 [cs.lg] 2 Nov 2015 Junyoung Chung, Kyle Kastner, Laurent Dinh, Kratarth Goel, Aaron Courville, Yoshua Bengio Department of Computer
More informationBACKPROPAGATION THROUGH THE VOID
BACKPROPAGATION THROUGH THE VOID Optimizing Control Variates for Black-Box Gradient Estimation 27 Nov 2017, University of Cambridge Speaker: Geoffrey Roeder, University of Toronto OPTIMIZING EXPECTATIONS
More informationExpectation Maximization
Expectation Maximization Bishop PRML Ch. 9 Alireza Ghane c Ghane/Mori 4 6 8 4 6 8 4 6 8 4 6 8 5 5 5 5 5 5 4 6 8 4 4 6 8 4 5 5 5 5 5 5 µ, Σ) α f Learningscale is slightly Parameters is slightly larger larger
More information