Audio Signal Processing and Recognition (音訊處理與辨識)

Roger Jang (張智星)


您是來自 54.211.148.181 的貴賓,您已點閱本站網頁 1 次。 (從 2005/2/6 至今的點閱次數:1109)
Table of Contents

Chapter 1: Introduction

1-1:About This Book (有關本書)
1-2:Example Programs (如何取得程式碼)
1-3:Web Resources (網路資源)

Chapter 2: MATLAB Basics

2-1:MATLAB Introduction (MATLAB入門簡介)
Chapter 2: Exercises

Chapter 3: Introduction to Audio Signals (音訊的簡介)

[Video][Slides]
3-1:Introduction to Audio Signals (音訊基本介紹)
3-2:Basic Acoustic Features (基本聲學特徵)
3-3:Human Voice Production (人聲的產生)

Chapter 4: MATLAB for Audio Signal Processing

4-1:Introduction
4-2:Reading Wave Files
4-3:Playback of Audio Signals
4-4:Recording from Microphone
4-5:Writing Audio Files
Chapter 4: Exercises

Chapter 5: Basic Acoustic Features of Audio Signals (音訊的基本聲學特徵)

[Video][Slides]
5-1:Introduction (簡介)
5-2:Volume (音量)
5-3:Zero Crossing Rate (過零率)
5-4:Pitch (音高)
5-5:Timbre (音色)
Chapter 5: Exercises

Chapter 6: End-Point Detection (EPD)

6-1:Introduction to End-Point Detection (端點偵測介紹)
6-2:EPD in Time Domain (端點偵測:時域的方法)
6-3:EPD in Frequency Domain (端點偵測:頻域的方法)
Chapter 6: Exercises

Chapter 7: Pitch Tracking

7-1:Introduction to Pitch Tracking (音高追蹤簡介)
7-2:Time-domain: PDF: ACF
7-3:Time-domain: PDF: NSDF
7-4:Time-domain: PDF: AMDF
7-5:Frequency-domain: HPS
7-6:Frequency-domain: Cepstrum
7-7:Preprocessing: Clipping & SIFT
7-8:Postprocessing: Smoothing & Interpolation
7-9:How to Increase Pitch Resolution (音高解析度的提升)
7-10:Software for Pitch Tracking (音高抓取的軟體)
Chapter 7: Exercises

Chapter 8: 音高追蹤的應用

8-1:哼唱選歌
8-2:音調評分
8-3:語音評分
8-4:音腔評分
8-5:國語音調辨識
Chapter 8: Exercises

Chapter 9: Digital Signals and Systems (數位訊號與系統)

9-1:Discrete-Time Signals (離散時間訊號)
9-2:Linear Time-Invariant Systems (線性非時變系統)
9-3:Convolution (旋積)
9-4:Eigen Functions (固有函數)

Chapter 10: Fourier Transform (傅立葉轉換)

10-1:Discrete-Time Fourier Transform (離散時間傅立葉轉換)
10-2:Discrete Fourier Transform (離散傅立葉轉換)
Chapter 10: Exercises

Chapter 11: Digital Filters

11-1:Filter Applications (濾波器應用)
11-2:Filter Design (濾波器設計)
Chapter 11: Exercises

Chapter 12: Speech Features

12-1:共振峰
12-2:MFCC
Chapter 12: Exercises

Chapter 13: Speaker Recognition (語者辨識)

13-1:Speaker Recognition
Chapter 13: Exercises

Chapter 14: Query by Singing/Humming

14-1:Introduction (簡介)
14-2:Key Transposition (音調移位)
14-3:Linear Scaling (線性伸縮)
14-4:DTW of Type-1 and 2
14-5:DTW of Type-3
14-6:LCS and Edit Distance
14-7:哼唱選歌的效能改進
Chapter 14: Exercises

Chapter 15: Query by Tapping

15-1:Introduction
15-2:Feature Extraction
15-3:Comparison Methods
Chapter 15: Exercises

Chapter 16: Audio Fingerprinting

16-1:Landmark Extraction

Chapter 17: HTK

17-1:HTK Introduction (HTK 簡介)
17-2:HTK Example: Digit Recognition (HTK 基本範例一:數字辨識)
17-3:Digit Recognition: Varying MFCC Dimensions (數字辨識:改變MFCC維度)
17-4:Digit Recognition: Changing Acoustic Models (數字辨識:改變Model單位)
17-5:Digit Recognition: Changing MFCC Dimensions and Gaussian Component Numbers (數字辨識:改變MFCC維度和Gaussian個數)
Chapter 17: Exercises

Chapter 18: 語音辨識前處理

18-1:簡介
18-2:文字標音
18-3:辨識網路
18-4:聲學模型

Chapter 19: Speech/Audio Applications in Android

19-1:Introduction

Chapter 20: ASRA Library for Speech Recognition & Assessment

20-1:Introduction
20-2:ASRA for English
20-3:ASRA for Chinese
20-4:Use ASRA within ASR Toolbox
20-5:Format of output.xml

Chapter 21: Application Case Study (應用案例說明)

21-1:Coin Type Recognition
21-2:Singing Type Classification
21-3:Tone recognition
21-4:Music genre classification
21-5:Lexical stress detection
21-6:Text-dependent speaker identification