7-Speech Recognition Speech Recognition Concepts

Slides:



Advertisements
Similar presentations
Robust Speech recognition V. Barreaud LORIA. Mismatch Between Training and Testing n mismatch influences scores n causes of mismatch u Speech Variation.
Advertisements

Hidden Markov Models (HMM) Rabiner’s Paper
Angelo Dalli Department of Intelligent Computing Systems
Automatic Speech Recognition II  Hidden Markov Models  Neural Network.
Hidden Markov Model 主講人:虞台文 大同大學資工所 智慧型多媒體研究室. Contents Introduction – Markov Chain – Hidden Markov Model (HMM) Formal Definition of HMM & Problems Estimate.
Hidden Markov Models. A Hidden Markov Model consists of 1.A sequence of states {X t |t  T } = {X 1, X 2,..., X T }, and 2.A sequence of observations.
Hidden Markov Models Bonnie Dorr Christof Monz CMSC 723: Introduction to Computational Linguistics Lecture 5 October 6, 2004.
2004/11/161 A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition LAWRENCE R. RABINER, FELLOW, IEEE Presented by: Chi-Chun.
Page 1 Hidden Markov Models for Automatic Speech Recognition Dr. Mike Johnson Marquette University, EECE Dept.
Hidden Markov Models Adapted from Dr Catherine Sweeney-Reed’s slides.
Hidden Markov Models Theory By Johan Walters (SR 2003)
Hidden Markov Models Fundamentals and applications to bioinformatics.
Hidden Markov Models in NLP
Lecture 15 Hidden Markov Models Dr. Jianjun Hu mleg.cse.sc.edu/edu/csce833 CSCE833 Machine Learning University of South Carolina Department of Computer.
HMM-BASED PATTERN DETECTION. Outline  Markov Process  Hidden Markov Models Elements Basic Problems Evaluation Optimization Training Implementation 2-D.
Hidden Markov Models. Hidden Markov Model In some Markov processes, we may not be able to observe the states directly.
1 Hidden Markov Model Instructor : Saeed Shiry  CHAPTER 13 ETHEM ALPAYDIN © The MIT Press, 2004.
Dynamic Time Warping Applications and Derivation
Visual Recognition Tutorial1 Markov models Hidden Markov models Forward/Backward algorithm Viterbi algorithm Baum-Welch estimation algorithm Hidden.
Natural Language Understanding
EE513 Audio Signals and Systems Statistical Pattern Classification Kevin D. Donohue Electrical and Computer Engineering University of Kentucky.
Introduction to Automatic Speech Recognition
ETHEM ALPAYDIN © The MIT Press, Lecture Slides for.
Isolated-Word Speech Recognition Using Hidden Markov Models
1 7-Speech Recognition (Cont’d) HMM Calculating Approaches Neural Components Three Basic HMM Problems Viterbi Algorithm State Duration Modeling Training.
Gaussian Mixture Model and the EM algorithm in Speech Recognition
THE HIDDEN MARKOV MODEL (HMM)
HMM - Basics.
Fundamentals of Hidden Markov Model Mehmet Yunus Dönmez.
1 HMM - Part 2 Review of the last lecture The EM algorithm Continuous density HMM.
International Conference on Intelligent and Advanced Systems 2007 Chee-Ming Ting Sh-Hussain Salleh Tian-Swee Tan A. K. Ariff. Jain-De,Lee.
Jun-Won Suh Intelligent Electronic Systems Human and Systems Engineering Department of Electrical and Computer Engineering Speaker Verification System.
ECE 8443 – Pattern Recognition ECE 8423 – Adaptive Signal Processing Objectives: ML and Simple Regression Bias of the ML Estimate Variance of the ML Estimate.
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition Objectives: Reestimation Equations Continuous Distributions.
ECE 8443 – Pattern Recognition ECE 8527 – Introduction to Machine Learning and Pattern Recognition Objectives: Reestimation Equations Continuous Distributions.
HMM - Part 2 The EM algorithm Continuous density HMM.
1 CSE 552/652 Hidden Markov Models for Speech Recognition Spring, 2005 Oregon Health & Science University OGI School of Science & Engineering John-Paul.
1 CONTEXT DEPENDENT CLASSIFICATION  Remember: Bayes rule  Here: The class to which a feature vector belongs depends on:  Its own value  The values.
CHAPTER 8 DISCRIMINATIVE CLASSIFIERS HIDDEN MARKOV MODELS.
1 CS 552/652 Speech Recognition with Hidden Markov Models Winter 2011 Oregon Health & Science University Center for Spoken Language Understanding John-Paul.
ECE 8443 – Pattern Recognition ECE 8423 – Adaptive Signal Processing Objectives: Supervised Learning Resources: AG: Conditional Maximum Likelihood DP:
1 CSE 552/652 Hidden Markov Models for Speech Recognition Spring, 2006 Oregon Health & Science University OGI School of Science & Engineering John-Paul.
1 Hidden Markov Model Observation : O1,O2,... States in time : q1, q2,... All states : s1, s2,... Si Sj.
1 Hidden Markov Models Hsin-min Wang References: 1.L. R. Rabiner and B. H. Juang, (1993) Fundamentals of Speech Recognition, Chapter.
Statistical Models for Automatic Speech Recognition Lukáš Burget.
1 Hidden Markov Model Observation : O1,O2,... States in time : q1, q2,... All states : s1, s2,..., sN Si Sj.
Automated Speach Recognotion Automated Speach Recognition By: Amichai Painsky.
Hidden Markov Models. A Hidden Markov Model consists of 1.A sequence of states {X t |t  T } = {X 1, X 2,..., X T }, and 2.A sequence of observations.
A Hybrid Model of HMM and RBFN Model of Speech Recognition 길이만, 김수연, 김성호, 원윤정, 윤아림 한국과학기술원 응용수학전공.
Definition of the Hidden Markov Model A Seminar Speech Recognition presentation A Seminar Speech Recognition presentation October 24 th 2002 Pieter Bas.
Other Models for Time Series. The Hidden Markov Model (HMM)
1 7-Speech Recognition Speech Recognition Concepts Speech Recognition Approaches Recognition Theories Bayse Rule Simple Language Model P(A|W) Network Types.
Visual Recognition Tutorial1 Markov models Hidden Markov models Forward/Backward algorithm Viterbi algorithm Baum-Welch estimation algorithm Hidden.
Hidden Markov Models BMI/CS 576
Hidden Markov Models.
EEL 6586: AUTOMATIC SPEECH PROCESSING Hidden Markov Model Lecture
Statistical Models for Automatic Speech Recognition
Computational NeuroEngineering Lab
Hidden Markov Models Part 2: Algorithms
Statistical Models for Automatic Speech Recognition
8-Speech Recognition Speech Recognition Concepts
Hidden Markov Model LR Rabiner
4.0 More about Hidden Markov Models
N-Gram Model Formulas Word sequences Chain rule of probability
CONTEXT DEPENDENT CLASSIFICATION
EE513 Audio Signals and Systems
Handwritten Characters Recognition Based on an HMM Model
LECTURE 15: REESTIMATION, EM AND MIXTURES
Introduction to HMM (cont)
Hidden Markov Models By Manish Shrivastava.
Presentation transcript:

7-Speech Recognition Speech Recognition Concepts Speech Recognition Approaches Recognition Theories Bayse Rule Simple Language Model P(A|W) Network Types

7-Speech Recognition (Cont’d) HMM Calculating Approaches Neural Components Three Basic HMM Problems Viterbi Algorithm State Duration Modeling Training In HMM

Speech Recognition Concepts Speech recognition is inverse of Speech Synthesis Text Speech Speech Synthesis NLP Speech Processing Speech Speech Processing NLP Understanding Phone Sequence Text Speech Recognition

Speech Recognition Approaches Bottom-Up Approach Top-Down Approach Blackboard Approach

Voiced/Unvoiced/Silence Sound Classification Rules Bottom-Up Approach Signal Processing Voiced/Unvoiced/Silence Feature Extraction Segmentation Sound Classification Rules Knowledge Sources Signal Processing Phonotactic Rules Feature Extraction Lexical Access Segmentation Language Model Segmentation Recognized Utterance

Inventory of speech recognition units Top-Down Approach Inventory of speech recognition units Word Dictionary Task Model Grammar Unit Matching System Lexical Hypo thesis Syntactic Hypo thesis Semantic Hypo thesis Feature Analysis Utterance Verifier/ Matcher Recognized Utterance

Blackboard Approach Acoustic Processes Lexical Processes Black board Environmental Processes Semantic Processes Syntactic Processes

Recognition Theories Articulatory Based Recognition Use from Articulatory system for recognition This theory is the most successful until now Auditory Based Recognition Use from Auditory system for recognition Hybrid Based Recognition Is a hybrid from the above theories Motor Theory Model the intended gesture of speaker

Recognition Problem We have the sequence of acoustic symbols and we want to find the words that expressed by speaker Solution : Finding the most probable of word sequence by having Acoustic symbols

Recognition Problem A : Acoustic Symbols W : Word Sequence we should find so that

Bayse Rule

Bayse Rule (Cont’d)

Simple Language Model Computing this probability is very difficult and we need a very big database. So we use from Trigram and Bigram models.

Simple Language Model (Cont’d) Trigram : Bigram : Monogram :

Simple Language Model (Cont’d) Computing Method : Number of happening W3 after W1W2 Total number of happening W1W2 AdHoc Method :

Recognition Tasks Isolated Word Recognition (IWR) Connected Word (CW) , And Continuous Speech Recognition (CSR) Speaker Dependent, Multiple Speaker, And Speaker Independent Vocabulary Size Small <20 Medium >100 , <1000 Large >1000, <10000 Very Large >10000

Error Production Factor Prosody (Recognition should be Prosody Independent) Noise (Noise should be prevented) Spontaneous Speech

P(A|W) Computing Approaches Dynamic Time Warping (DTW) Hidden Markov Model (HMM) Artificial Neural Network (ANN) Hybrid Systems

Dynamic Time Warping Method (DTW) To obtain a global distance between two speech patterns a time alignment must be performed Ex : A time alignment path between a template pattern “SPEECH” and a noisy input “SsPEEhH”

Artificial Neural Network . Simple Computation Element of a Neural Network

Artificial Neural Network (Cont’d) Neural Network Types Perceptron Time Delay Time Delay Neural Network Computational Element (TDNN)

Artificial Neural Network (Cont’d) Single Layer Perceptron . . . . . .

Artificial Neural Network (Cont’d) Three Layer Perceptron . . . . . . . . . . . .

Hybrid Methods Hybrid Neural Network and Matched Filter For Recognition Acoustic Features Speech Output Units Delays PATTERN CLASSIFIER

Neural Network Properties The system is simple, But too much iteration is needed for training Doesn’t determine a specific structure Regardless of simplicity, the results are good Training size is large, so training should be offline Accuracy is relatively good

Hidden Markov Model Si Sj Observation : O1,O2, . . . States in time : q1, q2, . . . All states : s1, s2, . . .

Hidden Markov Model (Cont’d) Discrete Markov Model Degree 1 Markov Model

Hidden Markov Model (Cont’d) : Transition Probability from Si to Sj ,

Hidden Markov Model Example S1 : The weather is rainy S2 : The weather is cloudy S3 : The weather is sunny rainy cloudy sunny rainy cloudy sunny

Hidden Markov Model Example (Cont’d) Question 1:How much is this probability: Sunny-Sunny-Sunny-Rainy-Rainy-Sunny-Cloudy-Cloudy

Hidden Markov Model Example (Cont’d) The probability of being in state i in time t=1 Question 2:The probability of staying in a state for d days if we are in state Si? d Days

HMM Components N : Number Of States M : Number Of Outputs A : State Transfer Probability Matrix B : Output Occurrence Probability in each state : Primary Occurrence Probability : Set of HMM Parameters

Three Basic HMM Problems Given an HMM and a sequence of observations O,what is the probability ? Given a model and a sequence of observations O, what is the most likely state sequence in the model that produced the observations? Given a model and a sequence of observations O, how should we adjust model parameters in order to maximize ?

First Problem Solution We Know That: And

First Problem Solution (Cont’d) Account Order :

Forward Backward Approach Computing 1) Initialization

Forward Backward Approach (Cont’d) 2) Induction : 3) Termination : Computation Order :

Backward Variable Approach 1) Initialization 2)Induction

Second Problem Solution Finding the most likely state sequence Individually most likely state :

Viterbi Algorithm Define : P is the most likely state sequence with this conditions : state i , time t and observation o

Viterbi Algorithm (Cont’d) 1) Initialization Is the most likely state before state i at time t-1

Viterbi Algorithm (Cont’d) 2) Recursion

Viterbi Algorithm (Cont’d) 3) Termination: 4)Backtracking:

Third Problem Solution Parameters Estimation using Baum-Welch Or Expectation Maximization (EM) Approach Define:

Third Problem Solution (Cont’d) : Expectation value of the number of jumps from state i : Expectation value of the number of jumps from state i to state j

Third Problem Solution (Cont’d)

Baum Auxiliary Function By this approach we will reach to a local optimum

Restrictions Of Reestimation Formulas

Continuous Observation Density We have amounts of a PDF instead of We have Mixture Coefficients Average Variance

Continuous Observation Density Mixture in HMM M1|1 M2|1 M1|2 M2|2 M1|3 M2|3 M3|1 M4|1 M3|2 M4|2 M3|3 M4|3 S1 S2 S3 Dominant Mixture:

Continuous Observation Density (Cont’d) Model Parameters: 1×N N×M N×M×K N×M×K×K N×N N : Number Of States M : Number Of Mixtures In Each State K : Dimension Of Observation Vector

Continuous Observation Density (Cont’d)

Continuous Observation Density (Cont’d) Probability of event j’th state and k’th mixture at time t

State Duration Modeling Si Sj Probability of staying d times in state i :

State Duration Modeling (Cont’d) HMM With clear duration ……. ……. Si Sj

State Duration Modeling (Cont’d) HMM consideration with State Duration : Selecting using ‘s Selecting using Selecting Observation Sequence using in practice we assume the following independence: Selecting next state using transition probabilities . We also have an additional constraint:

Training In HMM Maximum Likelihood (ML) Maximum Mutual Information (MMI) Minimum Discrimination Information (MDI)

Training In HMM Maximum Likelihood (ML) . Observation Sequence

Training In HMM (Cont’d) Maximum Mutual Information (MMI) Mutual Information

Training In HMM (Cont’d) Minimum Discrimination Information (MDI) Observation : Auto correlation :