Machine Learning for Speaker Recogni2on and Bioinforma2cs
|
|
- Osborne Howard
- 5 years ago
- Views:
Transcription
1 Machine Learning for Speaker Recogni2on and Bioinforma2cs Man-Wai MAK Dept of Electronic and Informa8on Engineering, The Hong Kong Polytechnic University UTS/PolyU Workshop 24 Oct 2017
2 1 High-Level Perspec8ve 2 Speaker Recogni8on Contents Robust speaker recogni8on SNR-invariant PLDA Mixture of PLDA Deep learning for speaker recogni8on 3 Machine Learning for Bioinforma8cs 2
3 A High-Level Perspec2ve of My Work Machine Learning Speech Applica8ons Bioinforma8cs Applica8ons Speaker Recogni8on Emo8on Recogni8on Protein Recogni8on ECG Recogni8on 32
4 What is Speaker Recogni2on Based on the fact that speech produc8on organs are speakerdependent Automa8c speaker recogni8on under controlled environments is easy But under uncontrolled environments, errors are s8ll very high because of different types of variability in speech signals 4
5 Processes of Speaker Verifica2on Utterance from registered speaker low-dim representation of the whole utterance Spectral Analysis 60-dim acoustic vectors Factor Analysis 500-dim i-vector Decision Threshold Spectral Analysis 60-dim acoustic vectors Factor Analysis PLDA Scoring 500-dim i-vector x s x t Decision Making Accept/ Reject Utterance from test speaker PLDA: A supervised factor analysis model that can suppress the channel effects in the i-vectors 5
6 Noise Robust Speaker Recogni2on In conven8onal mul8-condi8on training, we pool i- vectors from various background noise levels to train the PLDA model I-vectors with 2 SNR ranges EM Algorithm PLDA Model 6
7 SNR-Invariant PLDA We proposed to use an SNR subspace to model the SNR variability in uzerances Group1 Group2 Group3 SNR Factor 1 SNR Factor 2 SNR Factor 3 SNR Subspace N Li and MW Mak, "SNR-Invariant PLDA Modeling in Nonparametric Subspace for Robust Speaker Verification", IEEE/ACM Trans on Audio Speech and Language Processing, 2015 N Li, MW Mak, WW Lin and JT Chien, "Discriminative Subspace Modeling of SNR and Duration Variabilities for Robust Speaker Verification", Computer Speech and Language,
8 Compared with Conven2onal PLDA Conventional PLDA xij = m+ Vhi + εij x = m+ Vh + Uw + ε k k ij i k ij SNR-Invariant PLDA 8
9 Noise Robust Speaker Recogni2on Conven8onal i-vector/plda systems use a single PLDA model to handle all SNR condi8ons PLDA Model PLDA Score Enrollment i-vectors 9
10 Mixture of PLDA SNR Es8mator SNR Posterior Estimator We proposed to handle uzerances of diverse SNR by a mixture of PLDA in which the posteriors of the indicator variables depend on the uzerance s SNR PLDA Model 1 PLDA Model 2 PLDA Score PLDA Model 3 MW Mak, XM Pang and JT Chien, "Mixture of PLDA for Noise Robust I-Vector Speaker Verification", IEEE/ACM Trans on Audio Speech and Language Processing,
11 Mixture of PLDA Use a GMM to es8mate the mixture posteriors MW Mak, XM Pang and JT Chien, "Mixture of PLDA for Noise Robust I-Vector Speaker Verification", IEEE/ACM Trans on Audio Speech and Language Processing,
12 DNN-Driven Mixture of PLDA Use a DNN to es8mate the mixture posteriors, given i- vectors as input N Li, MW Mak, and JT Chien, "DNN-driven Mixture of PLDA for Robust Speaker Verification", IEEE/ACM Transactions on Audio, Speech and Language Processing,
13 Deep Learning for Speaker Recogni2on Use DNNs for noise reduc8on and feature extrac8on Z Tan, Y Zhu, MW Mak and B Mak, "Senone I-Vectors for Robust Speaker Verification", ISCSLP'16 13
14 Deep Learning for Speaker Recogni2on Use denoising DNNs for i-vector extrac8on Z Tan, Y Zhu, MW Mak and B Mak, "Senone I-Vectors for Robust Speaker Verification", ISCSLP'16 14
15 Deep Learning for Speaker Recogni2on Use mul8-task DNNs for score calibra8on Z Tan, MW Mak and B Mak, DNN-Based Score Calibration with Multi-Task Learning for Noise Robust Speaker Verification", IEEE/ACM Trans on Audio, Speech and Language Processing, to appear 15
16 Machine Learning for Bioinforma2cs We leverage the knowledge in gene ontology database and Swissprot protein database for protein subcellular localiza8on m=m S AC BLAST GO Terms Retrieval Swiss-Prot Database GO Vectors Construc8on RP 1 RP l SVM SVM w l m=2 m=1 w 1 w L Mul8-label Classifica8 on GOA Database RP L SVM Ensemble RP SB Wan, MW Mak, and SY Kung, "mgoasvm: Multi-label protein subcellular localization based on gene ontology and support vector machines", BMC Bioinformatics,
17 Machine Learning for Bioinforma2cs Using LASSO and elas8c net, we discovered some essen8al GO terms for each subcellular loca8on SB Wan, MW Mak and SY Kung, "Sparse Regressions for Predicting and Interpreting Subcellular Localization of Multi-label Proteins", BMC Bioinformatics,
18 Machine Learning for Bioinforma2cs For each method (paper), we provide a web server for researchers to use our algorithm SB Wan, MW Mak and SY Kung, "FUEL-mLoc: Feature-Unified Prediction and Explanation of Multi- Localization of Cellular Proteins in Multiple Organisms", Bioinformatics, 2016 SB Wan and MW Mak, Machine Learning for Protein Subcellular Localization Prediction, De Gruyter,
19 Thanks
20 PLDA Likelihood-Ra2o Scores x t : I-vector from a test uzerance x s : I-vector from an enrollment uzerance of speaker s H 0 : Same speaker H 1 : Different speakers x s = m+ Vz + ε s x t = m+ Vz + ε t against x s = m + Vz s +ε s x t = m + Vz t +ε t p(x Score(x s, x t ) = log s, x t Same Speaker) p(x s, x t Different Speaker) = log p(x s, x t z)p(z)dz p(x s z s )p(z s )dz s p(x t z t )p(z t )dz t = 1 2 x T s Qx s + x T t Qx t + 2x T s Px t + const where Full derivation of this scoring function can be found in 20
21 SNR-Invariant PLDA Method of modeling SNR informa8on i-vector w 6dB 6 db w cln SNR Subspace 15 db clean w 15dB I-vector Space N Li, MW Mak, WW Lin and JT Chien, "Discriminative Subspace Modeling of SNR and Duration Variabilities for Robust Speaker Verification", Computer Speech and Language,
Bo#leneck Features from SNR- Adap9ve Denoising Deep Classifier for Speaker Iden9fica9on
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
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 informationAn Ensemble Classifier with Random Projection for Predicting Multi-label Protein Subcellular Localization
An Ensemble Classifier with Random Projection for Predicting Multi-label Protein Subcellular Localization Shibiao Wan, Man-Wai Mak, Bai Zhang, Yue Wang, Sun-Yuan Kung Dept of Electronic and Information
More informationMinimum Redundancy and Maximum Relevance Feature Selec4on. Hang Xiao
Minimum Redundancy and Maximum Relevance Feature Selec4on Hang Xiao Background Feature a feature is an individual measurable heuris4c property of a phenomenon being observed In character recogni4on: horizontal
More informationVideo- to- Video Face Matching: Establishing a Baseline for Unconstrained Face Recogni:on
Video- to- Video Face Matching: Establishing a Baseline for Unconstrained Face Recogni:on Lacey Best- Rowden, Brendan Klare, Joshua Klontz, and Anil K. Jain Biometrics: Theory, Applica:ons, and Systems
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 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 informationSTA 4273H: Sta-s-cal Machine Learning
STA 4273H: Sta-s-cal Machine Learning Russ Salakhutdinov Department of Statistics! rsalakhu@utstat.toronto.edu! h0p://www.cs.toronto.edu/~rsalakhu/ Lecture 3 Parametric Distribu>ons We want model the probability
More informationA Wavenet for Speech Denoising
A Wavenet for Speech Denoising Jordi Pons work done in collaboration with Dario Rethage and Xavier Serra Music Technology Group (Universitat Pompeu Fabra, Barcelona) Summer 2017 Presented at Pandora and
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 informationClustering Lecture 5: Mixture Model
Clustering Lecture 5: Mixture Model Jing Gao SUNY Buffalo 1 Outline Basics Motivation, definition, evaluation Methods Partitional Hierarchical Density-based Mixture model Spectral methods Advanced topics
More informationA Scalable Speech Recognizer with Deep-Neural-Network Acoustic Models
A Scalable Speech Recognizer with Deep-Neural-Network Acoustic Models and Voice-Activated Power Gating Michael Price*, James Glass, Anantha Chandrakasan MIT, Cambridge, MA * now at Analog Devices, Cambridge,
More informationClient Dependent GMM-SVM Models for Speaker Verification
Client Dependent GMM-SVM Models for Speaker Verification Quan Le, Samy Bengio IDIAP, P.O. Box 592, CH-1920 Martigny, Switzerland {quan,bengio}@idiap.ch Abstract. Generative Gaussian Mixture Models (GMMs)
More informationPa#ern Recogni-on for Neuroimaging Toolbox
Pa#ern Recogni-on for Neuroimaging Toolbox Pa#ern Recogni-on Methods: Basics João M. Monteiro Based on slides from Jessica Schrouff and Janaina Mourão-Miranda PRoNTo course UCL, London, UK 2017 Outline
More informationTWO-STEP SEMI-SUPERVISED APPROACH FOR MUSIC STRUCTURAL CLASSIFICATION. Prateek Verma, Yang-Kai Lin, Li-Fan Yu. Stanford University
TWO-STEP SEMI-SUPERVISED APPROACH FOR MUSIC STRUCTURAL CLASSIFICATION Prateek Verma, Yang-Kai Lin, Li-Fan Yu Stanford University ABSTRACT Structural segmentation involves finding hoogeneous sections appearing
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 informationHidden Markov Models. Gabriela Tavares and Juri Minxha Mentor: Taehwan Kim CS159 04/25/2017
Hidden Markov Models Gabriela Tavares and Juri Minxha Mentor: Taehwan Kim CS159 04/25/2017 1 Outline 1. 2. 3. 4. Brief review of HMMs Hidden Markov Support Vector Machines Large Margin Hidden Markov Models
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 informationAudioSet: Real-world Audio Event Classification
AudioSet: Real-world Audio Event Classification g.co/audioset Rif A. Saurous, Shawn Hershey, Dan Ellis, Aren Jansen and the Google Sound Understanding Team 2017-10-20 Outline The Early Years: Weakly-Supervised
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 informationPreface to the Second Edition. Preface to the First Edition. 1 Introduction 1
Preface to the Second Edition Preface to the First Edition vii xi 1 Introduction 1 2 Overview of Supervised Learning 9 2.1 Introduction... 9 2.2 Variable Types and Terminology... 9 2.3 Two Simple Approaches
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 informationTrial-Based Calibration for Speaker Recognition in Unseen Conditions
Trial-Based Calibration for Speaker Recognition in Unseen Conditions Mitchell McLaren, Aaron Lawson, Luciana Ferrer, Nicolas Scheffer, Yun Lei Speech Technology and Research Laboratory SRI International,
More informationThe Hitachi/JHU CHiME-5 system: Advances in speech recognition for everyday home environments using multiple microphone arrays
CHiME2018 workshop The Hitachi/JHU CHiME-5 system: Advances in speech recognition for everyday home environments using multiple microphone arrays Naoyuki Kanda 1, Rintaro Ikeshita 1, Shota Horiguchi 1,
More informationImproving Speaker Verification Performance in Presence of Spoofing Attacks Using Out-of-Domain Spoofed Data
INTERSPEECH 17 August 24, 17, Stockholm, Sweden Improving Speaker Verification Performance in Presence of Spoofing Attacks Using Out-of-Domain Spoofed Data Achintya Kr. Sarkar 1, Md. Sahidullah 2, Zheng-Hua
More informationFrom processing to learning on graphs
From processing to learning on graphs Patrick Pérez Maths and Images in Paris IHP, 2 March 2017 Signals on graphs Natural graph: mesh, network, etc., related to a real structure, various signals can live
More informationCS395T Visual Recogni5on and Search. Gautam S. Muralidhar
CS395T Visual Recogni5on and Search Gautam S. Muralidhar Today s Theme Unsupervised discovery of images Main mo5va5on behind unsupervised discovery is that supervision is expensive Common tasks include
More informationKernels for Structured Data
T-122.102 Special Course in Information Science VI: Co-occurence methods in analysis of discrete data Kernels for Structured Data Based on article: A Survey of Kernels for Structured Data by Thomas Gärtner
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 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 informationIMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING
IMAGE RESTORATION VIA EFFICIENT GAUSSIAN MIXTURE MODEL LEARNING Jianzhou Feng Li Song Xiaog Huo Xiaokang Yang Wenjun Zhang Shanghai Digital Media Processing Transmission Key Lab, Shanghai Jiaotong University
More informationEpitomic Analysis of Human Motion
Epitomic Analysis of Human Motion Wooyoung Kim James M. Rehg Department of Computer Science Georgia Institute of Technology Atlanta, GA 30332 {wooyoung, rehg}@cc.gatech.edu Abstract Epitomic analysis is
More informationDynamic Time Warping
Centre for Vision Speech & Signal Processing University of Surrey, Guildford GU2 7XH. Dynamic Time Warping Dr Philip Jackson Acoustic features Distance measures Pattern matching Distortion penalties DTW
More information2-2-2, Hikaridai, Seika-cho, Soraku-gun, Kyoto , Japan 2 Graduate School of Information Science, Nara Institute of Science and Technology
ISCA Archive STREAM WEIGHT OPTIMIZATION OF SPEECH AND LIP IMAGE SEQUENCE FOR AUDIO-VISUAL SPEECH RECOGNITION Satoshi Nakamura 1 Hidetoshi Ito 2 Kiyohiro Shikano 2 1 ATR Spoken Language Translation Research
More information10703 Deep Reinforcement Learning and Control
10703 Deep Reinforcement Learning and Control Russ Salakhutdinov Machine Learning Department rsalakhu@cs.cmu.edu Policy Gradient II Used Materials Disclaimer: Much of the material and slides for this lecture
More informationMulti-label classification using rule-based classifier systems
Multi-label classification using rule-based classifier systems Shabnam Nazmi (PhD candidate) Department of electrical and computer engineering North Carolina A&T state university Advisor: Dr. A. Homaifar
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 Convolutional Neural Network using Triplet of Faces, Deep Ensemble, and Scorelevel Fusion for Face Recognition
IEEE 2017 Conference on Computer Vision and Pattern Recognition Deep Convolutional Neural Network using Triplet of Faces, Deep Ensemble, and Scorelevel Fusion for Face Recognition Bong-Nam Kang*, Yonghyun
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 informationConfidence Measures: how much we can trust our speech recognizers
Confidence Measures: how much we can trust our speech recognizers Prof. Hui Jiang Department of Computer Science York University, Toronto, Ontario, Canada Email: hj@cs.yorku.ca Outline Speech recognition
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 informationSAS: A speaker verification spoofing database containing diverse attacks
SAS: A speaker verification spoofing database containing diverse attacks Zhizheng Wu 1, Ali Khodabakhsh 2, Cenk Demiroglu 2, Junichi Yamagishi 1,3, Daisuke Saito 4, Tomoki Toda 5, Simon King 1 1 University
More informationABSTRACT 1. INTRODUCTION
LOW-RANK PLUS DIAGONAL ADAPTATION FOR DEEP NEURAL NETWORKS Yong Zhao, Jinyu Li, and Yifan Gong Microsoft Corporation, One Microsoft Way, Redmond, WA 98052, USA {yonzhao; jinyli; ygong}@microsoft.com ABSTRACT
More informationMaximum Likelihood Beamforming for Robust Automatic Speech Recognition
Maximum Likelihood Beamforming for Robust Automatic Speech Recognition Barbara Rauch barbara@lsv.uni-saarland.de IGK Colloquium, Saarbrücken, 16 February 2006 Agenda Background: Standard ASR Robust ASR
More informationFingerprint Mosaicking by Rolling with Sliding
Fingerprint Mosaicking by Rolling with Sliding Kyoungtaek Choi, Hunjae Park, Hee-seung Choi and Jaihie Kim Department of Electrical and Electronic Engineering,Yonsei University Biometrics Engineering Research
More informationExperimental Evaluation of Latent Variable Models. for Dimensionality Reduction
Experimental Evaluation of Latent Variable Models for Dimensionality Reduction Miguel Á. Carreira-Perpiñán and Steve Renals a Dept. of Computer Science, University of Sheffield {M.Carreira,S.Renals}@dcs.shef.ac.uk
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 informationDeep Learning on Graphs
Deep Learning on Graphs with Graph Convolutional Networks Hidden layer Hidden layer Input Output ReLU ReLU, 22 March 2017 joint work with Max Welling (University of Amsterdam) BDL Workshop @ NIPS 2016
More informationSUPERVISED LEARNING METHODS. Stanley Liang, PhD Candidate, Lassonde School of Engineering, York University Helix Science Engagement Programs 2018
SUPERVISED LEARNING METHODS Stanley Liang, PhD Candidate, Lassonde School of Engineering, York University Helix Science Engagement Programs 2018 2 CHOICE OF ML You cannot know which algorithm will work
More informationMachine Learning Crash Course: Part I
Machine Learning Crash Course: Part I Ariel Kleiner August 21, 2012 Machine learning exists at the intersec
More informationDeep Temporal Models (Benchmarks and Applica6ons Analysis)
Deep Temporal Models (Benchmarks and Applica6ons Analysis) Sek Chai SRI Interna6onal Presented at: NICE 2016, March 7, 2016 2016 SRI International Project Summary Goals Analyze Deep Temporal Models (DTMs).
More informationEnd- To- End Speech Recogni0on with Recurrent Neural Networks
RTTH Summer School on Speech Technology: A Deep Learning Perspec0ve End- To- End Speech Recogni0on with Recurrent Neural Networks José A. R. Fonollosa Universitat Politècnica de Catalunya. Barcelona Barcelona,
More informationClassification. 1 o Semestre 2007/2008
Classification Departamento de Engenharia Informática Instituto Superior Técnico 1 o Semestre 2007/2008 Slides baseados nos slides oficiais do livro Mining the Web c Soumen Chakrabarti. Outline 1 2 3 Single-Class
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 informationMACHINE LEARNING: CLUSTERING, AND CLASSIFICATION. Steve Tjoa June 25, 2014
MACHINE LEARNING: CLUSTERING, AND CLASSIFICATION Steve Tjoa kiemyang@gmail.com June 25, 2014 Review from Day 2 Supervised vs. Unsupervised Unsupervised - clustering Supervised binary classifiers (2 classes)
More informationSparse and large-scale learning with heterogeneous data
Sparse and large-scale learning with heterogeneous data February 15, 2007 Gert Lanckriet (gert@ece.ucsd.edu) IEEE-SDCIS In this talk Statistical machine learning Techniques: roots in classical statistics
More informationSparse Solutions to Linear Inverse Problems. Yuzhe Jin
Sparse Solutions to Linear Inverse Problems Yuzhe Jin Outline Intro/Background Two types of algorithms Forward Sequential Selection Methods Diversity Minimization Methods Experimental results Potential
More informationCOMP 551 Applied Machine Learning Lecture 13: Unsupervised learning
COMP 551 Applied Machine Learning Lecture 13: Unsupervised learning Associate Instructor: Herke van Hoof (herke.vanhoof@mail.mcgill.ca) Slides mostly by: (jpineau@cs.mcgill.ca) Class web page: www.cs.mcgill.ca/~jpineau/comp551
More informationTerraSwarm. A Machine Learning and Op0miza0on Toolkit for the Swarm. Ilge Akkaya, Shuhei Emoto, Edward A. Lee. University of California, Berkeley
TerraSwarm A Machine Learning and Op0miza0on Toolkit for the Swarm Ilge Akkaya, Shuhei Emoto, Edward A. Lee University of California, Berkeley TerraSwarm Tools Telecon 17 November 2014 Sponsored by the
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 informationSpeech Technology Using in Wechat
Speech Technology Using in Wechat FENG RAO Powered by WeChat Outline Introduce Algorithm of Speech Recognition Acoustic Model Language Model Decoder Speech Technology Open Platform Framework of Speech
More informationAutoencoder. Representation learning (related to dictionary learning) Both the input and the output are x
Deep Learning 4 Autoencoder, Attention (spatial transformer), Multi-modal learning, Neural Turing Machine, Memory Networks, Generative Adversarial Net Jian Li IIIS, Tsinghua Autoencoder Autoencoder Unsupervised
More informationIntroduc)on to Probabilis)c Latent Seman)c Analysis. NYP Predic)ve Analy)cs Meetup June 10, 2010
Introduc)on to Probabilis)c Latent Seman)c Analysis NYP Predic)ve Analy)cs Meetup June 10, 2010 PLSA A type of latent variable model with observed count data and nominal latent variable(s). Despite the
More informationBilevel Sparse Coding
Adobe Research 345 Park Ave, San Jose, CA Mar 15, 2013 Outline 1 2 The learning model The learning algorithm 3 4 Sparse Modeling Many types of sensory data, e.g., images and audio, are in high-dimensional
More informationFeature Selec+on. Machine Learning Fall 2018 Kasthuri Kannan
Feature Selec+on Machine Learning Fall 2018 Kasthuri Kannan Interpretability vs. Predic+on Types of feature selec+on Subset selec+on/forward/backward Shrinkage (Lasso/Ridge) Best model (CV) Feature selec+on
More informationPartial Least Squares Regression on Grassmannian Manifold for Emotion Recognition
Emotion Recognition In The Wild Challenge and Workshop (EmotiW 2013) Partial Least Squares Regression on Grassmannian Manifold for Emotion Recognition Mengyi Liu, Ruiping Wang, Zhiwu Huang, Shiguang Shan,
More informationA Survey on Postive and Unlabelled Learning
A Survey on Postive and Unlabelled Learning Gang Li Computer & Information Sciences University of Delaware ligang@udel.edu Abstract In this paper we survey the main algorithms used in positive and unlabeled
More informationCS 229 Midterm Review
CS 229 Midterm Review Course Staff Fall 2018 11/2/2018 Outline Today: SVMs Kernels Tree Ensembles EM Algorithm / Mixture Models [ Focus on building intuition, less so on solving specific problems. Ask
More informationMulti-Modal Audio, Video, and Physiological Sensor Learning for Continuous Emotion Prediction
Multi-Modal Audio, Video, and Physiological Sensor Learning for Continuous Emotion Prediction Youngjune Gwon 1, Kevin Brady 1, Pooya Khorrami 2, Elizabeth Godoy 1, William Campbell 1, Charlie Dagli 1,
More informationDr Andrew Abel University of Stirling, Scotland
Dr Andrew Abel University of Stirling, Scotland University of Stirling - Scotland Cognitive Signal Image and Control Processing Research (COSIPRA) Cognitive Computation neurobiology, cognitive psychology
More informationMachine learning for image- based localiza4on. Juho Kannala May 15, 2017
Machine learning for image- based localiza4on Juho Kannala May 15, 2017 Contents Problem sebng (What?) Mo4va4on & applica4ons (Why?) Previous work & background (How?) Our own studies and results Open ques4ons
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 informationLarge-Scale Lasso and Elastic-Net Regularized Generalized Linear Models
Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models DB Tsai Steven Hillion Outline Introduction Linear / Nonlinear Classification Feature Engineering - Polynomial Expansion Big-data
More informationCNN for Low Level Image Processing. Huanjing Yue
CNN for Low Level Image Processing Huanjing Yue 2017.11 1 Deep Learning for Image Restoration General formulation: min Θ L( x, x) s. t. x = F(y; Θ) Loss function Parameters to be learned Key issues The
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 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 informationBiometrics Technology: Multi-modal (Part 2)
Biometrics Technology: Multi-modal (Part 2) References: At the Level: [M7] U. Dieckmann, P. Plankensteiner and T. Wagner, "SESAM: A biometric person identification system using sensor fusion ", Pattern
More informationThe Pre-Image Problem and Kernel PCA for Speech Enhancement
The Pre-Image Problem and Kernel PCA for Speech Enhancement Christina Leitner and Franz Pernkopf Signal Processing and Speech Communication Laboratory, Graz University of Technology, Inffeldgasse 6c, 8
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 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 informationDecision Support Systems
Decision Support Systems 2011/2012 Week 3. Lecture 5 Previous Class: Data Pre- Processing Data quality: accuracy, completeness, consistency, 4meliness, believability, interpretability Data cleaning: handling
More informationMachine Learning. CS 232: Ar)ficial Intelligence Naïve Bayes Oct 26, 2015
1 CS 232: Ar)ficial Intelligence Naïve Bayes Oct 26, 2015 Machine Learning Part 1 of course: how use a model to make op)mal decisions (state space, MDPs) Machine learning: how to acquire a model from data
More informationDeep Generative Models and a Probabilistic Programming Library
Deep Generative Models and a Probabilistic Programming Library Discriminative (Deep) Learning Learn a (differentiable) function mapping from input to output x f(x; θ) y Gradient back-propagation Generative
More informationImage Denoising via Group Sparse Eigenvectors of Graph Laplacian
Image Denoising via Group Sparse Eigenvectors of Graph Laplacian Yibin Tang, Ying Chen, Ning Xu, Aimin Jiang, Lin Zhou College of IOT Engineering, Hohai University, Changzhou, China School of Information
More informationHybrid Speech Synthesis
Hybrid Speech Synthesis Simon King Centre for Speech Technology Research University of Edinburgh 2 What are you going to learn? Another recap of unit selection let s properly understand the Acoustic Space
More informationCS 6140: Machine Learning Spring Final Exams. What we learned Final Exams 2/26/16
Logis@cs CS 6140: Machine Learning Spring 2016 Instructor: Lu Wang College of Computer and Informa@on Science Northeastern University Webpage: www.ccs.neu.edu/home/luwang Email: luwang@ccs.neu.edu Assignment
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 informationCS 6140: Machine Learning Spring 2016
CS 6140: Machine Learning Spring 2016 Instructor: Lu Wang College of Computer and Informa?on Science Northeastern University Webpage: www.ccs.neu.edu/home/luwang Email: luwang@ccs.neu.edu Logis?cs Assignment
More informationHow to choose a Voice Biometrics Engine
Emilio Mar*nez emar%nez@agni%o- corp.com How to choose a Voice Biometrics Engine Voice Biometrics Engines Authen*ca*on solu*on vs. Voice Biometrics Engine 2 Selec2ng a VB Engine Voice Biometrics End Users
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 informationSemi- Supervised Learning
Semi- Supervised Learning Aarti Singh Machine Learning 10-601 Dec 1, 2011 Slides Courtesy: Jerry Zhu 1 Supervised Learning Feature Space Label Space Goal: Optimal predictor (Bayes Rule) depends on unknown
More informationSemi-Supervised Hierarchical Models for 3D Human Pose Reconstruction
Semi-Supervised Hierarchical Models for 3D Human Pose Reconstruction Atul Kanaujia, CBIM, Rutgers Cristian Sminchisescu, TTI-C Dimitris Metaxas,CBIM, Rutgers 3D Human Pose Inference Difficulties Towards
More informationLecture 7: Spectral Clustering; Linear Dimensionality Reduc:on via Principal Component Analysis
Lecture 7: Spectral Clustering; Linear Dimensionality Reduc:on via Principal Component Analysis Lester Mackey April, Stats 6B: Unsupervised Learning Blackboard discussion See lecture notes Spectral clustering
More informationDetector. Flash. Detector
CLIPS at TRECvid: Shot Boundary Detection and Feature Detection Georges M. Quénot, Daniel Moraru, and Laurent Besacier CLIPS-IMAG, BP53, 38041 Grenoble Cedex 9, France Georges.Quenot@imag.fr Abstract This
More informationDiscovery Net : A UK e-science Pilot Project for Grid-based Knowledge Discovery Services. Patrick Wendel Imperial College, London
Discovery Net : A UK e-science Pilot Project for Grid-based Knowledge Discovery Services Patrick Wendel Imperial College, London Data Mining and Exploration Middleware for Distributed and Grid Computing,
More informationFeature Selection by Independent Component Analysis for Robust Speaker Verification
IJCSNS International Journal of Computer Science and Network Security, VOL.6 No.3B, March 2006 229 Feature Selection by Independent Component Analysis for Robust Speaker Verification Ahmet Şentürk and
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 informationGeneralized Principal Component Analysis via Lossy Coding and Compression Yi Ma
Generalized Principal Component Analysis via Lossy Coding and Compression Yi Ma Image Formation & Processing Group, Beckman Decision & Control Group, Coordinated Science Lab. Electrical & Computer Engineering
More informationNeural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017
3/0/207 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/0/207 Perceptron as a neural
More informationLarge Scale Data Analysis Using Deep Learning
Large Scale Data Analysis Using Deep Learning Machine Learning Basics - 1 U Kang Seoul National University U Kang 1 In This Lecture Overview of Machine Learning Capacity, overfitting, and underfitting
More information