Spectral and Textural Feature-Based System for Automatic Detection of Fricatives and Affricates

Size: px
Start display at page:

Download "Spectral and Textural Feature-Based System for Automatic Detection of Fricatives and Affricates"

Transcription

1 Spectral and Textural Feature-Based System for Automatic Detection of Fricatives and Affricates Dima Ruinskiy Niv Dadush Yizhar Lavner Department of Computer Science, Tel-Hai College, Israel

2 Outline Phoneme Spotting Applications and Approaches Fricatives and Affricates Discriminating Features Our Algorithms Cepstrogram Matching Linear Discriminant Analysis Results and Discussion

3 Phoneme Spotting Definition: Locating all appearances of a phoneme (set of phonemes) in continuous speech. Not to be confused with phoneme classification, where individual phonemes are already marked

4 Phoneme Spotting Applications Speech recognition Spoken term detection Smart audio filtering Multimedia synchronization Audio / Video Lyrics / Music Aesthetic purposes Professional audio recording

5 Traditional Approaches Pattern-matching Classifiers (GMM, SVM ) Hierarchical approach Time-domain and frequency-domain features Choice of features is key Dependent on the phonemes in question

6 Fricatives and Affricates The largest group of phonemes in English /s/ (sound), /sh/ (wash), /f/ (food), /th/ (math) /z/ (zebra), /zh/ (mirage), /v/ (victory), /dh/ (this) Affricates: /ch/ (chess), /ts/ (pizza) Concatenation of a stop and a fricative

7 Fricatives and Affricates Characteristics Noise-like consonants Concentration of energy in high frequencies Weak formant structure Problems Excessive accentuation Hearing-impaired

8 Discriminating Features Short-time Energy N + N E db = 10 log10 x n N n=n 0 Filters out silence and vowel-like phonemes Not useful in filtering out most consonants

9 Discriminating Features Zero-Crossing Rate N +N ZCR = 0.5 sgn x n - sgn x n - 1 N n=n +1 Indicative of high frequencies (noise-like signal) Significantly higher for certain fricatives (/s/, /f/, /sh/) than for other phonemes 0

10 Discriminating Features Band Energy Ratio Measure total spectral energy in two different bands: = 500Hz,3KHz Spectral energy from DFT: The ratio B 1 = 5KHz,10KHz B 2 k B is large when the phoneme contains mostly high frequencies B BER = 10log10 E B /E 1 B2 E = X k 2

11 Discriminating Features Top: Speech signal with instances of /s/ and /sh/ Middle: Band energy ratio in decibels Bottom: Zero-crossing rate

12 Discriminating Features Spectral peak locations The two dominant peaks in the LPC envelope Mel frequency cepstral coefficients Triangular ideal band-pass filters V k (logarithmically spaced and sized) Total spectral energy E(i) in each filter M-1 1 2π 1 MFCC L = log E i cos i + L M M 2 i=0 i

13 Discriminating Features Lacunarity Textural measure of translational invariance For sliding windows of length r compute the mass S(r) across the signal Define the lacunarity Λ(r): Var S r Λ r = + 1 μ 2 S r Apply least-square approximation to get a bestfitting function of the form α/x + β γ

14 Discriminating Features Lacunarity BLUE = fricatives/affricates RED = other phonemes

15 Cepstrogram-Matching Algorithm MFCC vectors for consecutive short windows Arranged in a matrix to form a cepstrogram Sub-frame FRAME S 1 S 3 S 5 S 2 S 4 S 6 S 7 V 1 V 2 V 3 V 4 V 5 V 6 V 7

16 Cepstrogram-Matching Algorithm Training Cepstrograms of several known fricative/affricate phonemes Compute Mean (template) matrix V and Variance matrix. T = 1 N N i=1 M i

17 Cepstrogram-Matching Algorithm Testing Compute cepstrogram of analysis frame: M(X K ) Difference matrix D = M XK - T /V Distance measure: d = j Frame is a candidate if d is below a threshold Candidates are further checked using short-time energy, zero-crossing rate, band energy ratio. i D ij 2

18 Divide into INPUT SIGNAL consecutive X k-2 X k-1 X k X k+1 X k+2 analysis frames TEMPLATE- MATCHING ALGORITHM Compute MFCC matrix Compute Supporting Feature Set Breath Template Matrix Calculate distance measure NO Distance below threshold? YES Preliminary classification as non-fricative Preliminary classification as fricative Detection refinement on all frames in vicinity NO Still classified as fricative? YES Discard Classify as fricative and demarcate boundaries

19 Cepstrogram-Matching Algorithm Achieved good results in breath detection (Ruinskiy-Lavner, 2006) Results for fricatives/affricates are good but not good enough Biggest problem: false positives

20 Linear Discriminant Analysis (LDA) Transforming multi-dimensional feature vectors (of two or more classes) into a onedimensional representation Aimed at maximizing inter-class difference while minimizing intra-class variance

21 Linear Discriminant Analysis (LDA) Classes C 0,C 1 ; Class means m 0,m 1 S B, S w - inter/intra-class variances Maximize T B J w = w T S W w S w w Differentiating J(w) we obtain the extremum: w = S -1 W m1 - m0

22 LDA Classifier Training Several hundred phonemes (from TIMIT) 28% fricatives/affricates, 72% other phonemes Short overlapping frames (8-15ms) Feature vector consisting of: Short-time energy Zero-crossing rate Band energy ratio Lacunarity Spectral peaks

23 LDA Classifier Training Classes C 1 (fricatives/affricates), C 0 (others), represented by matrices of data Subtract global mean vector m from columns: c i = ci - m, ci C i, i {0,1} Calculate covariance matrices T i i Ci COV = C and joint covariance matrix C= COV 1+ COV2 N

24 LDA Classification Discrimination function -1 T 1-1 T m0c x - m0c m 0 + log p 0 < T 1-1 T m1c x - m1c m 1 + log p1 f(x) = 2 0 otherwise Silence threshold, Median filtering

25 Divide into INPUT SIGNAL consecutive X k-2 X k-1 X k X k+1 X k+2 analysis frames LINEAR DISCRIMINANT ALGORITHM Compute Feature Vector LDA Classification Classified as fricative? YES NO Post-processing (median/energy filtering) Discard Classify as fricative

26 Results Algorithm Test data Detections False alarms Excluding breath Ceps. 6 speakers (2M+4F) 10 minutes 95.1% 26.2% 14.6% Ceps. (/s/ only) (same as above) 93.2% 2.7% 2.7% LDA TIMIT, 25 speakers 96.4% 15.7% 6.1% Breath detector can eliminate most breath-related false positives Most common false positives after breath: stop consonants (/t/, /k/)

27 Thank you! Q&A

28 Backup

29 Backup

30 Backup

31 Backup

Automatic Speech Recognition (CS753)

Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 12: Acoustic Feature Extraction for ASR Instructor: Preethi Jyothi Feb 13, 2017 Speech Signal Analysis Generate discrete samples A frame Need to focus on short

More information

Signal Modeling Techniques in Speech Recognition. Hassan A. Kingravi

Signal Modeling Techniques in Speech Recognition. Hassan A. Kingravi Signal Modeling Techniques in Speech Recognition Hassan A. Kingravi Outline Introduction Spectral Shaping Spectral Analysis Parameter Transforms Statistical Modeling Discussion Conclusions 1: Introduction

More information

Robust Speaker Identification

Robust Speaker Identification Robust Speaker Identification by Smarajit Bose Interdisciplinary Statistical Research Unit Indian Statistical Institute, Kolkata Joint work with Amita Pal and Ayanendranath Basu Overview } } } } } } }

More information

Nearly Perfect Detection of Continuous F 0 Contour and Frame Classification for TTS Synthesis. Thomas Ewender

Nearly Perfect Detection of Continuous F 0 Contour and Frame Classification for TTS Synthesis. Thomas Ewender Nearly Perfect Detection of Continuous F 0 Contour and Frame Classification for TTS Synthesis Thomas Ewender Outline Motivation Detection algorithm of continuous F 0 contour Frame classification algorithm

More information

Automatic Phoneme Recognition. Segmental Hidden Markov Models

Automatic Phoneme Recognition. Segmental Hidden Markov Models Automatic Phoneme Recognition with Segmental Hidden Markov Models Areg G. Baghdasaryan Thesis submitted to the Faculty of the Virginia Polytechnic Institute and State University in partial fulfillment

More information

PHONEME CLASSIFICATION OVER THE RECONSTRUCTED PHASE SPACE USING PRINCIPAL COMPONENT ANALYSIS

PHONEME CLASSIFICATION OVER THE RECONSTRUCTED PHASE SPACE USING PRINCIPAL COMPONENT ANALYSIS PHONEME CLASSIFICATION OVER THE RECONSTRUCTED PHASE SPACE USING PRINCIPAL COMPONENT ANALYSIS Jinjin Ye jinjin.ye@mu.edu Michael T. Johnson mike.johnson@mu.edu Richard J. Povinelli richard.povinelli@mu.edu

More information

Feature extraction 1

Feature extraction 1 Centre for Vision Speech & Signal Processing University of Surrey, Guildford GU2 7XH. Feature extraction 1 Dr Philip Jackson Cepstral analysis - Real & complex cepstra - Homomorphic decomposition Filter

More information

The effect of speaking rate and vowel context on the perception of consonants. in babble noise

The effect of speaking rate and vowel context on the perception of consonants. in babble noise The effect of speaking rate and vowel context on the perception of consonants in babble noise Anirudh Raju Department of Electrical Engineering, University of California, Los Angeles, California, USA anirudh90@ucla.edu

More information

FEATURE SELECTION USING FISHER S RATIO TECHNIQUE FOR AUTOMATIC SPEECH RECOGNITION

FEATURE SELECTION USING FISHER S RATIO TECHNIQUE FOR AUTOMATIC SPEECH RECOGNITION FEATURE SELECTION USING FISHER S RATIO TECHNIQUE FOR AUTOMATIC SPEECH RECOGNITION Sarika Hegde 1, K. K. Achary 2 and Surendra Shetty 3 1 Department of Computer Applications, NMAM.I.T., Nitte, Karkala Taluk,

More information

Voice Activity Detection Using Pitch Feature

Voice Activity Detection Using Pitch Feature Voice Activity Detection Using Pitch Feature Presented by: Shay Perera 1 CONTENTS Introduction Related work Proposed Improvement References Questions 2 PROBLEM speech Non speech Speech Region Non Speech

More information

Harmonic Structure Transform for Speaker Recognition

Harmonic Structure Transform for Speaker Recognition Harmonic Structure Transform for Speaker Recognition Kornel Laskowski & Qin Jin Carnegie Mellon University, Pittsburgh PA, USA KTH Speech Music & Hearing, Stockholm, Sweden 29 August, 2011 Laskowski &

More information

Semi-Supervised Learning of Speech Sounds

Semi-Supervised Learning of Speech Sounds Aren Jansen Partha Niyogi Department of Computer Science Interspeech 2007 Objectives 1 Present a manifold learning algorithm based on locality preserving projections for semi-supervised phone classification

More information

TinySR. Peter Schmidt-Nielsen. August 27, 2014

TinySR. Peter Schmidt-Nielsen. August 27, 2014 TinySR Peter Schmidt-Nielsen August 27, 2014 Abstract TinySR is a light weight real-time small vocabulary speech recognizer written entirely in portable C. The library fits in a single file (plus header),

More information

Signal representations: Cepstrum

Signal representations: Cepstrum Signal representations: Cepstrum Source-filter separation for sound production For speech, source corresponds to excitation by a pulse train for voiced phonemes and to turbulence (noise) for unvoiced phonemes,

More information

Feature extraction 2

Feature extraction 2 Centre for Vision Speech & Signal Processing University of Surrey, Guildford GU2 7XH. Feature extraction 2 Dr Philip Jackson Linear prediction Perceptual linear prediction Comparison of feature methods

More information

ENTROPY RATE-BASED STATIONARY / NON-STATIONARY SEGMENTATION OF SPEECH

ENTROPY RATE-BASED STATIONARY / NON-STATIONARY SEGMENTATION OF SPEECH ENTROPY RATE-BASED STATIONARY / NON-STATIONARY SEGMENTATION OF SPEECH Wolfgang Wokurek Institute of Natural Language Processing, University of Stuttgart, Germany wokurek@ims.uni-stuttgart.de, http://www.ims-stuttgart.de/~wokurek

More information

Support Vector Machines using GMM Supervectors for Speaker Verification

Support Vector Machines using GMM Supervectors for Speaker Verification 1 Support Vector Machines using GMM Supervectors for Speaker Verification W. M. Campbell, D. E. Sturim, D. A. Reynolds MIT Lincoln Laboratory 244 Wood Street Lexington, MA 02420 Corresponding author e-mail:

More information

Dominant Feature Vectors Based Audio Similarity Measure

Dominant Feature Vectors Based Audio Similarity Measure Dominant Feature Vectors Based Audio Similarity Measure Jing Gu 1, Lie Lu 2, Rui Cai 3, Hong-Jiang Zhang 2, and Jian Yang 1 1 Dept. of Electronic Engineering, Tsinghua Univ., Beijing, 100084, China 2 Microsoft

More information

The Noisy Channel Model. Statistical NLP Spring Mel Freq. Cepstral Coefficients. Frame Extraction ... Lecture 9: Acoustic Models

The Noisy Channel Model. Statistical NLP Spring Mel Freq. Cepstral Coefficients. Frame Extraction ... Lecture 9: Acoustic Models Statistical NLP Spring 2010 The Noisy Channel Model Lecture 9: Acoustic Models Dan Klein UC Berkeley Acoustic model: HMMs over word positions with mixtures of Gaussians as emissions Language model: Distributions

More information

An Evolutionary Programming Based Algorithm for HMM training

An Evolutionary Programming Based Algorithm for HMM training An Evolutionary Programming Based Algorithm for HMM training Ewa Figielska,Wlodzimierz Kasprzak Institute of Control and Computation Engineering, Warsaw University of Technology ul. Nowowiejska 15/19,

More information

The Noisy Channel Model. Statistical NLP Spring Mel Freq. Cepstral Coefficients. Frame Extraction ... Lecture 10: Acoustic Models

The Noisy Channel Model. Statistical NLP Spring Mel Freq. Cepstral Coefficients. Frame Extraction ... Lecture 10: Acoustic Models Statistical NLP Spring 2009 The Noisy Channel Model Lecture 10: Acoustic Models Dan Klein UC Berkeley Search through space of all possible sentences. Pick the one that is most probable given the waveform.

More information

Statistical NLP Spring The Noisy Channel Model

Statistical NLP Spring The Noisy Channel Model Statistical NLP Spring 2009 Lecture 10: Acoustic Models Dan Klein UC Berkeley The Noisy Channel Model Search through space of all possible sentences. Pick the one that is most probable given the waveform.

More information

Singer Identification using MFCC and LPC and its comparison for ANN and Naïve Bayes Classifiers

Singer Identification using MFCC and LPC and its comparison for ANN and Naïve Bayes Classifiers Singer Identification using MFCC and LPC and its comparison for ANN and Naïve Bayes Classifiers Kumari Rambha Ranjan, Kartik Mahto, Dipti Kumari,S.S.Solanki Dept. of Electronics and Communication Birla

More information

Lecture 5: GMM Acoustic Modeling and Feature Extraction

Lecture 5: GMM Acoustic Modeling and Feature Extraction CS 224S / LINGUIST 285 Spoken Language Processing Andrew Maas Stanford University Spring 2017 Lecture 5: GMM Acoustic Modeling and Feature Extraction Original slides by Dan Jurafsky Outline for Today Acoustic

More information

Speech Signal Representations

Speech Signal Representations Speech Signal Representations Berlin Chen 2003 References: 1. X. Huang et. al., Spoken Language Processing, Chapters 5, 6 2. J. R. Deller et. al., Discrete-Time Processing of Speech Signals, Chapters 4-6

More information

Topic 6. Timbre Representations

Topic 6. Timbre Representations Topic 6 Timbre Representations We often say that singer s voice is magnetic the violin sounds bright this French horn sounds solid that drum sounds dull What aspect(s) of sound are these words describing?

More information

Computer Science March, Homework Assignment #3 Due: Thursday, 1 April, 2010 at 12 PM

Computer Science March, Homework Assignment #3 Due: Thursday, 1 April, 2010 at 12 PM Computer Science 401 8 March, 2010 St. George Campus University of Toronto Homework Assignment #3 Due: Thursday, 1 April, 2010 at 12 PM Speech TA: Frank Rudzicz 1 Introduction This assignment introduces

More information

Lecture 7: Feature Extraction

Lecture 7: Feature Extraction Lecture 7: Feature Extraction Kai Yu SpeechLab Department of Computer Science & Engineering Shanghai Jiao Tong University Autumn 2014 Kai Yu Lecture 7: Feature Extraction SJTU Speech Lab 1 / 28 Table of

More information

SPEECH ANALYSIS AND SYNTHESIS

SPEECH ANALYSIS AND SYNTHESIS 16 Chapter 2 SPEECH ANALYSIS AND SYNTHESIS 2.1 INTRODUCTION: Speech signal analysis is used to characterize the spectral information of an input speech signal. Speech signal analysis [52-53] techniques

More information

SPEECH RECOGNITION USING TIME DOMAIN FEATURES FROM PHASE SPACE RECONSTRUCTIONS

SPEECH RECOGNITION USING TIME DOMAIN FEATURES FROM PHASE SPACE RECONSTRUCTIONS SPEECH RECOGNITION USING TIME DOMAIN FEATURES FROM PHASE SPACE RECONSTRUCTIONS by Jinjin Ye, B.S. A THESIS SUBMITTED TO THE FACULTY OF THE GRADUATE SCHOOL IN PARTIAL FULFILLMENT OF THE REQUIREMENTS for

More information

Model-based unsupervised segmentation of birdcalls from field recordings

Model-based unsupervised segmentation of birdcalls from field recordings Model-based unsupervised segmentation of birdcalls from field recordings Anshul Thakur School of Computing and Electrical Engineering Indian Institute of Technology Mandi Himachal Pradesh, India Email:

More information

Session Variability Compensation in Automatic Speaker Recognition

Session Variability Compensation in Automatic Speaker Recognition Session Variability Compensation in Automatic Speaker Recognition Javier González Domínguez VII Jornadas MAVIR Universidad Autónoma de Madrid November 2012 Outline 1. The Inter-session Variability Problem

More information

Estimation of Relative Operating Characteristics of Text Independent Speaker Verification

Estimation of Relative Operating Characteristics of Text Independent Speaker Verification International Journal of Engineering Science Invention Volume 1 Issue 1 December. 2012 PP.18-23 Estimation of Relative Operating Characteristics of Text Independent Speaker Verification Palivela Hema 1,

More information

The Noisy Channel Model. CS 294-5: Statistical Natural Language Processing. Speech Recognition Architecture. Digitizing Speech

The Noisy Channel Model. CS 294-5: Statistical Natural Language Processing. Speech Recognition Architecture. Digitizing Speech CS 294-5: Statistical Natural Language Processing The Noisy Channel Model Speech Recognition II Lecture 21: 11/29/05 Search through space of all possible sentences. Pick the one that is most probable given

More information

Frog Sound Identification System for Frog Species Recognition

Frog Sound Identification System for Frog Species Recognition Frog Sound Identification System for Frog Species Recognition Clifford Loh Ting Yuan and Dzati Athiar Ramli Intelligent Biometric Research Group (IBG), School of Electrical and Electronic Engineering,

More information

ON THE USE OF MLP-DISTANCE TO ESTIMATE POSTERIOR PROBABILITIES BY KNN FOR SPEECH RECOGNITION

ON THE USE OF MLP-DISTANCE TO ESTIMATE POSTERIOR PROBABILITIES BY KNN FOR SPEECH RECOGNITION Zaragoza Del 8 al 1 de Noviembre de 26 ON THE USE OF MLP-DISTANCE TO ESTIMATE POSTERIOR PROBABILITIES BY KNN FOR SPEECH RECOGNITION Ana I. García Moral, Carmen Peláez Moreno EPS-Universidad Carlos III

More information

Sound Recognition in Mixtures

Sound 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 information

ECE 661: Homework 10 Fall 2014

ECE 661: Homework 10 Fall 2014 ECE 661: Homework 10 Fall 2014 This homework consists of the following two parts: (1) Face recognition with PCA and LDA for dimensionality reduction and the nearest-neighborhood rule for classification;

More information

Noise Robust Isolated Words Recognition Problem Solving Based on Simultaneous Perturbation Stochastic Approximation Algorithm

Noise Robust Isolated Words Recognition Problem Solving Based on Simultaneous Perturbation Stochastic Approximation Algorithm EngOpt 2008 - International Conference on Engineering Optimization Rio de Janeiro, Brazil, 0-05 June 2008. Noise Robust Isolated Words Recognition Problem Solving Based on Simultaneous Perturbation Stochastic

More information

Estimation of Cepstral Coefficients for Robust Speech Recognition

Estimation of Cepstral Coefficients for Robust Speech Recognition Estimation of Cepstral Coefficients for Robust Speech Recognition by Kevin M. Indrebo, B.S., M.S. A Dissertation submitted to the Faculty of the Graduate School, Marquette University, in Partial Fulfillment

More information

Mixtures of Gaussians with Sparse Structure

Mixtures of Gaussians with Sparse Structure Mixtures of Gaussians with Sparse Structure Costas Boulis 1 Abstract When fitting a mixture of Gaussians to training data there are usually two choices for the type of Gaussians used. Either diagonal or

More information

Sparse Models for Speech Recognition

Sparse Models for Speech Recognition Sparse Models for Speech Recognition Weibin Zhang and Pascale Fung Human Language Technology Center Hong Kong University of Science and Technology Outline Introduction to speech recognition Motivations

More information

Environmental Sound Classification in Realistic Situations

Environmental 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 information

Automatic Speech Recognition (CS753)

Automatic Speech Recognition (CS753) Automatic Speech Recognition (CS753) Lecture 21: Speaker Adaptation Instructor: Preethi Jyothi Oct 23, 2017 Speaker variations Major cause of variability in speech is the differences between speakers Speaking

More information

Why DNN Works for Acoustic Modeling in Speech Recognition?

Why DNN Works for Acoustic Modeling in Speech Recognition? Why DNN Works for Acoustic Modeling in Speech Recognition? Prof. Hui Jiang Department of Computer Science and Engineering York University, Toronto, Ont. M3J 1P3, CANADA Joint work with Y. Bao, J. Pan,

More information

University of Colorado at Boulder ECEN 4/5532. Lab 2 Lab report due on February 16, 2015

University of Colorado at Boulder ECEN 4/5532. Lab 2 Lab report due on February 16, 2015 University of Colorado at Boulder ECEN 4/5532 Lab 2 Lab report due on February 16, 2015 This is a MATLAB only lab, and therefore each student needs to turn in her/his own lab report and own programs. 1

More information

On the Influence of the Delta Coefficients in a HMM-based Speech Recognition System

On the Influence of the Delta Coefficients in a HMM-based Speech Recognition System On the Influence of the Delta Coefficients in a HMM-based Speech Recognition System Fabrice Lefèvre, Claude Montacié and Marie-José Caraty Laboratoire d'informatique de Paris VI 4, place Jussieu 755 PARIS

More information

Shankar Shivappa University of California, San Diego April 26, CSE 254 Seminar in learning algorithms

Shankar Shivappa University of California, San Diego April 26, CSE 254 Seminar in learning algorithms Recognition of Visual Speech Elements Using Adaptively Boosted Hidden Markov Models. Say Wei Foo, Yong Lian, Liang Dong. IEEE Transactions on Circuits and Systems for Video Technology, May 2004. Shankar

More information

Heeyoul (Henry) Choi. Dept. of Computer Science Texas A&M University

Heeyoul (Henry) Choi. Dept. of Computer Science Texas A&M University Heeyoul (Henry) Choi Dept. of Computer Science Texas A&M University hchoi@cs.tamu.edu Introduction Speaker Adaptation Eigenvoice Comparison with others MAP, MLLR, EMAP, RMP, CAT, RSW Experiments Future

More information

Chapter 9. Linear Predictive Analysis of Speech Signals 语音信号的线性预测分析

Chapter 9. Linear Predictive Analysis of Speech Signals 语音信号的线性预测分析 Chapter 9 Linear Predictive Analysis of Speech Signals 语音信号的线性预测分析 1 LPC Methods LPC methods are the most widely used in speech coding, speech synthesis, speech recognition, speaker recognition and verification

More information

where =0,, 1, () is the sample at time index and is the imaginary number 1. Then, () is a vector of values at frequency index corresponding to the mag

where =0,, 1, () is the sample at time index and is the imaginary number 1. Then, () is a vector of values at frequency index corresponding to the mag Efficient Discrete Tchebichef on Spectrum Analysis of Speech Recognition Ferda Ernawan and Nur Azman Abu Abstract Speech recognition is still a growing field of importance. The growth in computing power

More information

Mixtures of Gaussians with Sparse Regression Matrices. Constantinos Boulis, Jeffrey Bilmes

Mixtures of Gaussians with Sparse Regression Matrices. Constantinos Boulis, Jeffrey Bilmes Mixtures of Gaussians with Sparse Regression Matrices Constantinos Boulis, Jeffrey Bilmes {boulis,bilmes}@ee.washington.edu Dept of EE, University of Washington Seattle WA, 98195-2500 UW Electrical Engineering

More information

Session 1: Pattern Recognition

Session 1: Pattern Recognition Proc. Digital del Continguts Musicals Session 1: Pattern Recognition 1 2 3 4 5 Music Content Analysis Pattern Classification The Statistical Approach Distribution Models Singing Detection Dan Ellis

More information

Stress detection through emotional speech analysis

Stress detection through emotional speech analysis Stress detection through emotional speech analysis INMA MOHINO inmaculada.mohino@uah.edu.es ROBERTO GIL-PITA roberto.gil@uah.es LORENA ÁLVAREZ PÉREZ loreduna88@hotmail Abstract: Stress is a reaction or

More information

Introduction to Signal Detection and Classification. Phani Chavali

Introduction to Signal Detection and Classification. Phani Chavali Introduction to Signal Detection and Classification Phani Chavali Outline Detection Problem Performance Measures Receiver Operating Characteristics (ROC) F-Test - Test Linear Discriminant Analysis (LDA)

More information

AUDIO-VISUAL RELIABILITY ESTIMATES USING STREAM

AUDIO-VISUAL RELIABILITY ESTIMATES USING STREAM SCHOOL OF ENGINEERING - STI ELECTRICAL ENGINEERING INSTITUTE SIGNAL PROCESSING LABORATORY Mihai Gurban ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE EPFL - FSTI - IEL - LTS Station Switzerland-5 LAUSANNE Phone:

More information

Hidden Markov Model and Speech Recognition

Hidden Markov Model and Speech Recognition 1 Dec,2006 Outline Introduction 1 Introduction 2 3 4 5 Introduction What is Speech Recognition? Understanding what is being said Mapping speech data to textual information Speech Recognition is indeed

More information

Statistical NLP Spring Digitizing Speech

Statistical NLP Spring Digitizing Speech Statistical NLP Spring 2008 Lecture 10: Acoustic Models Dan Klein UC Berkeley Digitizing Speech 1 Frame Extraction A frame (25 ms wide) extracted every 10 ms 25 ms 10ms... a 1 a 2 a 3 Figure from Simon

More information

Digitizing Speech. Statistical NLP Spring Frame Extraction. Gaussian Emissions. Vector Quantization. HMMs for Continuous Observations? ...

Digitizing Speech. Statistical NLP Spring Frame Extraction. Gaussian Emissions. Vector Quantization. HMMs for Continuous Observations? ... Statistical NLP Spring 2008 Digitizing Speech Lecture 10: Acoustic Models Dan Klein UC Berkeley Frame Extraction A frame (25 ms wide extracted every 10 ms 25 ms 10ms... a 1 a 2 a 3 Figure from Simon Arnfield

More information

Reformulating the HMM as a trajectory model by imposing explicit relationship between static and dynamic features

Reformulating the HMM as a trajectory model by imposing explicit relationship between static and dynamic features Reformulating the HMM as a trajectory model by imposing explicit relationship between static and dynamic features Heiga ZEN (Byung Ha CHUN) Nagoya Inst. of Tech., Japan Overview. Research backgrounds 2.

More information

University of Cambridge Engineering Part IIB Module 3F3: Signal and Pattern Processing Handout 2:. The Multivariate Gaussian & Decision Boundaries

University of Cambridge Engineering Part IIB Module 3F3: Signal and Pattern Processing Handout 2:. The Multivariate Gaussian & Decision Boundaries University of Cambridge Engineering Part IIB Module 3F3: Signal and Pattern Processing Handout :. The Multivariate Gaussian & Decision Boundaries..15.1.5 1 8 6 6 8 1 Mark Gales mjfg@eng.cam.ac.uk Lent

More information

Improving Liquid State Machines Through Iterative Refinement of the Reservoir

Improving Liquid State Machines Through Iterative Refinement of the Reservoir Improving Liquid State Machines Through Iterative Refinement of the Reservoir David Norton, Dan Ventura Computer Science Department, Brigham Young University, Provo, Utah, United States Abstract Liquid

More information

Text-Independent Speaker Identification using Statistical Learning

Text-Independent Speaker Identification using Statistical Learning University of Arkansas, Fayetteville ScholarWorks@UARK Theses and Dissertations 7-2015 Text-Independent Speaker Identification using Statistical Learning Alli Ayoola Ojutiku University of Arkansas, Fayetteville

More information

Selecting Good Speech Features for Recognition

Selecting Good Speech Features for Recognition ETRI Journal, volume 18, number 1, April 1996 29 Selecting Good Speech Features for Recognition Youngjik Lee and Kyu-Woong Hwang CONTENTS I. INTRODUCTION II. COMPARISON OF MEASURES III. ANALYSIS OF SPEECH

More information

Fuzzy Support Vector Machines for Automatic Infant Cry Recognition

Fuzzy Support Vector Machines for Automatic Infant Cry Recognition Fuzzy Support Vector Machines for Automatic Infant Cry Recognition Sandra E. Barajas-Montiel and Carlos A. Reyes-García Instituto Nacional de Astrofisica Optica y Electronica, Luis Enrique Erro #1, Tonantzintla,

More information

Brief Introduction of Machine Learning Techniques for Content Analysis

Brief Introduction of Machine Learning Techniques for Content Analysis 1 Brief Introduction of Machine Learning Techniques for Content Analysis Wei-Ta Chu 2008/11/20 Outline 2 Overview Gaussian Mixture Model (GMM) Hidden Markov Model (HMM) Support Vector Machine (SVM) Overview

More information

JOINT TIME-FREQUENCY SCATTERING FOR AUDIO CLASSIFICATION

JOINT TIME-FREQUENCY SCATTERING FOR AUDIO CLASSIFICATION 2015 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, SEPT. 17 20, 2015, BOSTON, USA JOINT TIME-FREQUENCY SCATTERING FOR AUDIO CLASSIFICATION Joakim Andén PACM Princeton University,

More information

DISCRIMINATIVE DECORELATION FOR CLUSTERING AND CLASSIFICATION

DISCRIMINATIVE DECORELATION FOR CLUSTERING AND CLASSIFICATION DISCRIMINATIVE DECORELATION FOR CLUSTERING AND CLASSIFICATION ECCV 12 Bharath Hariharan, Jitandra Malik, and Deva Ramanan MOTIVATION State-of-the-art Object Detection HOG Linear SVM Dalal&Triggs Histograms

More information

Modeling Prosody for Speaker Recognition: Why Estimating Pitch May Be a Red Herring

Modeling Prosody for Speaker Recognition: Why Estimating Pitch May Be a Red Herring Modeling Prosody for Speaker Recognition: Why Estimating Pitch May Be a Red Herring Kornel Laskowski & Qin Jin Carnegie Mellon University Pittsburgh PA, USA 28 June, 2010 Laskowski & Jin ODYSSEY 2010,

More information

Hidden Markov Models. Dr. Naomi Harte

Hidden Markov Models. Dr. Naomi Harte Hidden Markov Models Dr. Naomi Harte The Talk Hidden Markov Models What are they? Why are they useful? The maths part Probability calculations Training optimising parameters Viterbi unseen sequences Real

More information

Front-End Factor Analysis For Speaker Verification

Front-End Factor Analysis For Speaker Verification IEEE TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING Front-End Factor Analysis For Speaker Verification Najim Dehak, Patrick Kenny, Réda Dehak, Pierre Dumouchel, and Pierre Ouellet, Abstract This

More information

Multimedia Systems Giorgio Leonardi A.A Lecture 4 -> 6 : Quantization

Multimedia Systems Giorgio Leonardi A.A Lecture 4 -> 6 : Quantization Multimedia Systems Giorgio Leonardi A.A.2014-2015 Lecture 4 -> 6 : Quantization Overview Course page (D.I.R.): https://disit.dir.unipmn.it/course/view.php?id=639 Consulting: Office hours by appointment:

More information

T Automatic Speech Recognition: From Theory to Practice

T Automatic Speech Recognition: From Theory to Practice Automatic Speech Recognition: From Theory to Practice http://www.cis.hut.fi/opinnot// September 20, 2004 Prof. Bryan Pellom Department of Computer Science Center for Spoken Language Research University

More information

Speech Spectra and Spectrograms

Speech Spectra and Spectrograms ACOUSTICS TOPICS ACOUSTICS SOFTWARE SPH301 SLP801 RESOURCE INDEX HELP PAGES Back to Main "Speech Spectra and Spectrograms" Page Speech Spectra and Spectrograms Robert Mannell 6. Some consonant spectra

More information

Speech Enhancement with Applications in Speech Recognition

Speech Enhancement with Applications in Speech Recognition Speech Enhancement with Applications in Speech Recognition A First Year Report Submitted to the School of Computer Engineering of the Nanyang Technological University by Xiao Xiong for the Confirmation

More information

Lecture 3: Pattern Classification

Lecture 3: Pattern Classification EE E6820: Speech & Audio Processing & Recognition Lecture 3: Pattern Classification 1 2 3 4 5 The problem of classification Linear and nonlinear classifiers Probabilistic classification Gaussians, mixtures

More information

arxiv: v1 [cs.sd] 25 Oct 2014

arxiv: v1 [cs.sd] 25 Oct 2014 Choice of Mel Filter Bank in Computing MFCC of a Resampled Speech arxiv:1410.6903v1 [cs.sd] 25 Oct 2014 Laxmi Narayana M, Sunil Kumar Kopparapu TCS Innovation Lab - Mumbai, Tata Consultancy Services, Yantra

More information

Lecture 3: Pattern Classification. Pattern classification

Lecture 3: Pattern Classification. Pattern classification EE E68: Speech & Audio Processing & Recognition Lecture 3: Pattern Classification 3 4 5 The problem of classification Linear and nonlinear classifiers Probabilistic classification Gaussians, mitures and

More information

Exemplar-based voice conversion using non-negative spectrogram deconvolution

Exemplar-based voice conversion using non-negative spectrogram deconvolution Exemplar-based voice conversion using non-negative spectrogram deconvolution Zhizheng Wu 1, Tuomas Virtanen 2, Tomi Kinnunen 3, Eng Siong Chng 1, Haizhou Li 1,4 1 Nanyang Technological University, Singapore

More information

Correspondence. Pulse Doppler Radar Target Recognition using a Two-Stage SVM Procedure

Correspondence. Pulse Doppler Radar Target Recognition using a Two-Stage SVM Procedure Correspondence Pulse Doppler Radar Target Recognition using a Two-Stage SVM Procedure It is possible to detect and classify moving and stationary targets using ground surveillance pulse-doppler radars

More information

CEPSTRAL analysis has been widely used in signal processing

CEPSTRAL analysis has been widely used in signal processing 162 IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, VOL. 7, NO. 2, MARCH 1999 On Second-Order Statistics and Linear Estimation of Cepstral Coefficients Yariv Ephraim, Fellow, IEEE, and Mazin Rahim, Senior

More information

Lecture Notes 5: Multiresolution Analysis

Lecture Notes 5: Multiresolution Analysis Optimization-based data analysis Fall 2017 Lecture Notes 5: Multiresolution Analysis 1 Frames A frame is a generalization of an orthonormal basis. The inner products between the vectors in a frame and

More information

SINGLE 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 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 information

Modifying Voice Activity Detection in Low SNR by correction factors

Modifying Voice Activity Detection in Low SNR by correction factors Modifying Voice Activity Detection in Low SNR by correction factors H. Farsi, M. A. Mozaffarian, H.Rahmani Department of Electrical Engineering University of Birjand P.O. Box: +98-9775-376 IRAN hfarsi@birjand.ac.ir

More information

Lab 9a. Linear Predictive Coding for Speech Processing

Lab 9a. Linear Predictive Coding for Speech Processing EE275Lab October 27, 2007 Lab 9a. Linear Predictive Coding for Speech Processing Pitch Period Impulse Train Generator Voiced/Unvoiced Speech Switch Vocal Tract Parameters Time-Varying Digital Filter H(z)

More information

MVA Processing of Speech Features. Chia-Ping Chen, Jeff Bilmes

MVA Processing of Speech Features. Chia-Ping Chen, Jeff Bilmes MVA Processing of Speech Features Chia-Ping Chen, Jeff Bilmes {chiaping,bilmes}@ee.washington.edu SSLI Lab Dept of EE, University of Washington Seattle, WA - UW Electrical Engineering UWEE Technical Report

More information

Lecture 9: Classification, LDA

Lecture 9: Classification, LDA Lecture 9: Classification, LDA Reading: Chapter 4 STATS 202: Data mining and analysis Jonathan Taylor, 10/12 Slide credits: Sergio Bacallado 1 / 1 Review: Main strategy in Chapter 4 Find an estimate ˆP

More information

Randomized Algorithms

Randomized Algorithms Randomized Algorithms Saniv Kumar, Google Research, NY EECS-6898, Columbia University - Fall, 010 Saniv Kumar 9/13/010 EECS6898 Large Scale Machine Learning 1 Curse of Dimensionality Gaussian Mixture Models

More information

Robust Sound Event Detection in Continuous Audio Environments

Robust Sound Event Detection in Continuous Audio Environments Robust Sound Event Detection in Continuous Audio Environments Haomin Zhang 1, Ian McLoughlin 2,1, Yan Song 1 1 National Engineering Laboratory of Speech and Language Information Processing The University

More information

Quarterly Progress and Status Report. On the synthesis and perception of voiceless fricatives

Quarterly Progress and Status Report. On the synthesis and perception of voiceless fricatives Dept. for Speech, Music and Hearing Quarterly Progress and Status Report On the synthesis and perception of voiceless fricatives Mártony, J. journal: STLQPSR volume: 3 number: 1 year: 1962 pages: 017022

More information

Machine Learning 2nd Edition

Machine Learning 2nd Edition INTRODUCTION TO Lecture Slides for Machine Learning 2nd Edition ETHEM ALPAYDIN, modified by Leonardo Bobadilla and some parts from http://www.cs.tau.ac.il/~apartzin/machinelearning/ The MIT Press, 2010

More information

Support Vector Machines. CAP 5610: Machine Learning Instructor: Guo-Jun QI

Support Vector Machines. CAP 5610: Machine Learning Instructor: Guo-Jun QI Support Vector Machines CAP 5610: Machine Learning Instructor: Guo-Jun QI 1 Linear Classifier Naive Bayes Assume each attribute is drawn from Gaussian distribution with the same variance Generative model:

More information

Gaussian Mixture Model Uncertainty Learning (GMMUL) Version 1.0 User Guide

Gaussian Mixture Model Uncertainty Learning (GMMUL) Version 1.0 User Guide Gaussian Mixture Model Uncertainty Learning (GMMUL) Version 1. User Guide Alexey Ozerov 1, Mathieu Lagrange and Emmanuel Vincent 1 1 INRIA, Centre de Rennes - Bretagne Atlantique Campus de Beaulieu, 3

More information

Segmental Recurrent Neural Networks for End-to-end Speech Recognition

Segmental Recurrent Neural Networks for End-to-end Speech Recognition Segmental Recurrent Neural Networks for End-to-end Speech Recognition Liang Lu, Lingpeng Kong, Chris Dyer, Noah Smith and Steve Renals TTI-Chicago, UoE, CMU and UW 9 September 2016 Background A new wave

More information

Mel-Generalized Cepstral Representation of Speech A Unified Approach to Speech Spectral Estimation. Keiichi Tokuda

Mel-Generalized Cepstral Representation of Speech A Unified Approach to Speech Spectral Estimation. Keiichi Tokuda Mel-Generalized Cepstral Representation of Speech A Unified Approach to Speech Spectral Estimation Keiichi Tokuda Nagoya Institute of Technology Carnegie Mellon University Tamkang University March 13,

More information

Boosting: Algorithms and Applications

Boosting: Algorithms and Applications Boosting: Algorithms and Applications Lecture 11, ENGN 4522/6520, Statistical Pattern Recognition and Its Applications in Computer Vision ANU 2 nd Semester, 2008 Chunhua Shen, NICTA/RSISE Boosting Definition

More information

Analysis of audio intercepts: Can we identify and locate the speaker?

Analysis of audio intercepts: Can we identify and locate the speaker? Motivation Analysis of audio intercepts: Can we identify and locate the speaker? K V Vijay Girish, PhD Student Research Advisor: Prof A G Ramakrishnan Research Collaborator: Dr T V Ananthapadmanabha Medical

More information

AN INVERTIBLE DISCRETE AUDITORY TRANSFORM

AN INVERTIBLE DISCRETE AUDITORY TRANSFORM COMM. MATH. SCI. Vol. 3, No. 1, pp. 47 56 c 25 International Press AN INVERTIBLE DISCRETE AUDITORY TRANSFORM JACK XIN AND YINGYONG QI Abstract. A discrete auditory transform (DAT) from sound signal to

More information

Improved noise power spectral density tracking by a MAP-based postprocessor

Improved noise power spectral density tracking by a MAP-based postprocessor Improved noise power spectral density tracking by a MAP-based postprocessor Aleksej Chinaev, Alexander Krueger, Dang Hai Tran Vu, Reinhold Haeb-Umbach University of Paderborn, Germany March 8th, 01 Computer

More information

SIGNALS measured in microphones are often contaminated

SIGNALS measured in microphones are often contaminated IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, VOL. 24, NO. 12, DECEMBER 2016 2313 Kernel Method for Voice Activity Detection in the Presence of Transients David Dov, Ronen Talmon, Member,

More information