7Speech Recognition Contd - PowerPoint PPT Presentation

Loading...

PPT – 7Speech Recognition Contd PowerPoint presentation | free to view - id: 1d9073-NTkyN



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

7Speech Recognition Contd

Description:

Speech Recognition Concepts. NLP. Speech. Processing. Text. Speech. NLP. Speech. Processing ... To obtain a global distance between two speech patterns a time ... – PowerPoint PPT presentation

Number of Views:94
Avg rating:3.0/5.0
Slides: 29
Provided by: Moh147
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: 7Speech Recognition Contd


1
7-Speech Recognition (Contd)
  • HMM Calculating Approaches
  • Neural Components
  • Three Basic HMM Problems
  • Viterbi Algorithm
  • State Duration Modeling
  • Training In HMM

2
Speech Recognition Concepts
Speech recognition is inverse of Speech Synthesis
Speech
Text
NLP
Speech Processing
Speech Synthesis
Understanding
NLP
Speech Processing
Speech
Phone Sequence
Text
Speech Recognition
3
Speech Recognition Approaches
  • Bottom-Up Approach
  • Top-Down Approach
  • Blackboard Approach

4
Bottom-Up Approach
Signal Processing
Voiced/Unvoiced/Silence
Feature Extraction
Segmentation
Sound Classification Rules
Signal Processing
Knowledge Sources
Phonotactic Rules
Feature Extraction
Lexical Access
Segmentation
Language Model
Segmentation
Recognized Utterance
5
Top-Down Approach
Inventory of speech recognition units
Word Dictionary
Task Model
Grammar
Semantic Hypo thesis
Syntactic Hypo thesis
Unit Matching System
Lexical Hypo thesis
Feature Analysis
Utterance Verifier/ Matcher
Recognized Utterance
6
Blackboard Approach
Acoustic Processes
Lexical Processes
Black board
Environmental Processes
Semantic Processes
Syntactic Processes
7
top down
An overall view of a speech recognition system
bottom up
From Ladefoged 2001
8
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

9
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 word
    sequence having Acoustic symbols

10
Recognition Problem
  • A Acoustic Symbols
  • W Word Sequence
  • we should find so that

11
Bayse Rule
12
Bayse Rule (Contd)
13
Simple Language Model
Computing this probability is very difficult and
we need a very big database. So we use from
Trigram and Bigram models.
14
Simple Language Model (Contd)
Trigram
Bigram
Monogram
15
Simple Language Model (Contd)
Computing Method
Number of happening W3 after W1W2
Total number of happening W1W2
AdHoc Method
16
7-Speech Recognition
  • Speech Recognition Concepts
  • Speech Recognition Approaches
  • Recognition Theories
  • Bayse Rule
  • Simple Language Model
  • P(AW) Network Types

17
From Ladefoged 2001
18
P(AW) Computing Approaches
  • Dynamic Time Warping (DTW)
  • Hidden Markov Model (HMM)
  • Artificial Neural Network (ANN)
  • Hybrid Systems

19
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
20
Recognition Tasks
  • Isolated Word Recognition (IWR) And Continuous
    Speech Recognition (CSR)
  • Speaker Dependent And Speaker Independent
  • Vocabulary Size
  • Small lt20
  • Medium gt100 , lt1000
  • Large gt1000, lt10000
  • Very Large gt10000

21
Error Production Factor
  • Prosody (Recognition should be Prosody
    Independent)
  • Noise (Noise should be prevented)
  • Spontaneous Speech

22
Artificial Neural Network
. . .
Simple Computation Element of a Neural Network
23
Artificial Neural Network (Contd)
  • Neural Network Types
  • Perceptron
  • Time Delay
  • Time Delay Neural Network Computational Element
    (TDNN)

24
Artificial Neural Network (Contd)
Single Layer Perceptron
. . .
. . .
25
Artificial Neural Network (Contd)
Three Layer Perceptron
. . .
. . .
. . .
. . .
26
Hybrid Methods
  • Hybrid Neural Network and Matched Filter For
    Recognition

Acoustic Features
Output Units
Speech
Delays
PATTERN CLASSIFIER
27
Neural Network Properties
  • The system is simple, But too much iterative
  • Doesnt determine a specific structure
  • Regardless of simplicity, the results are good
  • Training size is large, so training should be
    offline
  • Accuracy is relatively good

28
Hidden Markov Model
Sj
Si
  • Observation O1,O2, . . .
  • States in time q1, q2, . . .
  • All states s1, s2, . . .
About PowerShow.com