S004104-语音信号处理

发布者:沈如达发布时间:2018-04-23浏览次数:14

研究生课程开设申请表

 开课院(系、所):  信息科学与工程学院     

 课程申请开设类型: 新开□     重开     更名□请在内打勾,下同

课程

名称

中文

语音信号处理

英文

Speech Signal Processing

待分配课程编号

S004104

课程适用学位级别

博士


硕士

总学时

40

课内学时

40

学分

2

实践环节


用机小时


课程类别

公共基础     专业基础     专业必修       专业选修

开课院()


开课学期

秋季

考核方式

A.笔试(开卷   闭卷)      B. 口试    

C.笔试与口试结合                 D. □其他

课程负责人

教师

姓名

赵力

职称

教授

e-mail

zhaoli@seu.edu.cn

网页地址


授课语言

汉语

课件地址


适用学科范围

信息类(一级)

所属一级学科名称

信息与通信工程

实验(案例)个数


先修课程

数字信号处理等

教学用书

教材名称

教材编者

出版社

出版年月

版次

主要教材

语音信号处理

赵力

机械工业

20033

1

主要参考书

语音处理与识别

胡光锐

上海科技文献

199412

1

语音信号处理

杨引俊、迟惠生

电子工业

1995

1

语音信号处理

胡  航

哈尔滨工业大学

2000

1


一、课程介绍(含教学目标、教学要求等)300字以内)

 本课程要求掌握语音信号处理的基础、原理、方法和应用,以及该学科领域近年来取得的一些新的研究成果和技术。全课程共分十二个部分。要求掌握的内容包括:语音信号处理的基础知识;语音信号的分析技术;语音信号的矢量量化;隐马尔可夫模型技术;神经网络在语音信号处理中的应用;语音编码;语音合成;语音识别;说话人识别和语种辨识技术;语音信号的情感信息处理技术;语音增强技术。


二、教学大纲(含章节目录):(可附页)

一、绪论

二、语音信号处理的基础知识

1.语音和语言;

2.汉语语言学;

3.语音生成系统和语音感知系统;

4.语音信号生成的数学模型;

5.语音信号生成的数学模型;

6.语音信号的特性分析

三、语音信号分析

1.语音信号的数字化和预处理

2.语音信号的时域分析

3.语音信号的频域分析

4.语音信号的倒谱分析

5.语音信号的线性预测分析

6.语音信号的小波分析

7.基音周期估计

8.共振峰估计


四、矢量量化技术(VQ

1.矢量量化的基本原理

2.矢量量化的失真测度

3.矢量量化器的最佳码本设计


五、隐马尔可夫模型(HMM)

1.隐马尔可夫模型的引入

2.隐马尔可夫模型的定义

3.隐马尔可夫模型的基本算法

4.隐马尔可夫模型的各种结构类型


六、人工神经网络初步

1.人工神经网络简介

2.人工神经网络的构成

3.几种用于模式识别的神经网络模型及其主要算法

4.用神经网络进行模式识别的典型做法

5.人工神经网络模型的应用举例


七、语音编码

1.语音信号压缩编码的原理和压缩系统评价

2.语音信号的波形编码

3.语音信号的参数编码


八、语音合成

1.共振峰合成法

2.线性预测合成法

3.语音合成专用硬件简介


九、语音识别

1.语音识别原理和识别系统的组成

2.动态时间规整DTW

3.孤立字()识别系统

4.连续语音识别系统


十、说话人识别与语种辨识

1.说话人识别方法和系统结构

2.应用DTW的说话人确认系统

3.应用VQ的说话人识别系统

4.应用HMM的说话人识别系统

5.应用GMM的说话人识别系统

6.语种辨识的原理和应用

十一、语音信号中的情感信息处理

1.语音信号中的情感分类和情感特征分析

2.语音情感识别方法

3.情感语音的合成

十二、语音增强

1.语音特性、人耳感知特性及噪声特性

2.滤波法语音增强技术

3.利用相关特性的语音增强技术

4.非线性处理法语音增强技术

5.减谱法语音增强技术



三、教学周历

 周次

 教学内容

 教学方式

1

 第一章;第二章第1-3小节

 讲授

2

 第二章第4-6小节

 讲授

3

 第三章第1-3小节

 讲授

4

 第三章第4-5小节

 讲授

5

 第三章第6-7小节

 讲授

6

 第四章第1-3小节

 讲授

7

 第五章第1-4小节

 讲授

8

 第六章第1-2小节

 讲授

9

 第六章第3-5小节

 讲授

10

 第七章第1-3小节

 讲授

11

 第八章第1-3小节

 讲授

12

 第九章第1-2小节

 讲授

13

 第九章第3-4小节

 讲授

14

 第十章第1-3小节

 讲授

15

 第十章第4-6小节

 讲授

16

 第十一章第1-3小节

 讲授

17

 第十二章第1-3小节

 讲授

18

 第十二章第4-5小节

 讲授

 注:1.以上一、二、三项内容将作为中文教学大纲,在研究生院中文网页上公布,四、五内容将保存在研究生院。2.开课学期为:春季、秋季或春秋季。3.授课语言为:汉语、英语或双语教学。4.适用学科范围为:公共,一级,二级,三级。5.实践环节为:实验、调研、研究报告等。6.教学方式为:讲课、讨论、实验等。7.学位课程考试必须是笔试。8.课件地址指在网络上已经有的课程课件地址。9.主讲教师简介主要为基本信息(出生年月、性别、学历学位、专业职称等)、研究方向、教学与科研成果,以100500字为宜。

四、主讲教师简介:

 赵力,男,1958年出生。现工作于东南大学信息科学与工程学院,教授。主要从事语音、声频和视频信号处理、情感信息处理等方面的研究工作。


五、任课教师信息(包括主讲教师):

 任课

 教师

 学科

 (专业)

 办公

 电话

 住宅

 电话

 手机

 电子邮件

 通讯地址

 邮政

 编码

 赵力

 信号与信息处理

83793791

3694370


Zhaoli@seu.edu.cn

 东南大学信息科学与工程学院

210096



研究生院    2003.12






Application Form For Opening Graduate Courses

School (Department/Institute)School of Information Science and Engineering

Course Type: New Open □   Reopen √    Rename □Please tick in □, the same below

Course Name

Chinese

语音信号处理

English

Speech Signal Processing

Course Number

S004104

Type of Degree

Ph. D


Master

Total Credit Hours

40

In Class Credit Hours

40

Credit

2

Practice


Computer-using Hours


Course Type

Public Fundamental    □Major Fundamental    □Major Compulsory     √Major Elective

School (Department)

Information science and engineering

Term

Autumn

Examination

A. √PaperOpen-book   □ Closed-bookB. □Oral   

C. □Paper-oral Combination                       D. □ Others

Chief

Lecturer

Name

Zhao Li

Professional Title

Professor

E-mail

zhaoli@seu.edu.cn

Website


Teaching Language used in Course

Chinese

Teaching Material Website


Applicable Range of Discipline

Information

Name of First-Class Discipline

Information and communication engineering

Number of Experiment


Preliminary Courses

Digital Signal Processing

Teaching Books

Textbook Title

Author

Publisher

Year of Publication

Edition Number

Main Textbook

Speech Signal Processing

Zhao Li

mechanical industry

March, 2003

1

Main Reference Books

Speech Processing and recognition

Hu Guangrui

Shanghai technical literature

Dec. 1194

1

Speech Signal Processing

Yang Yinjun, Chi Huisheng

Electronic industry

1995

1

Speech Signal Processing

Hu Hang

Harbin institute of technology

2000

1


  1. Course Introduction (including teaching goals and requirements) within 300 words:

This course require students master the foundation, principle, method, applications of speech signal processing and new research achievements and technologies. The whole course can be divided into twelve parts which include: elementary knowledge of speech signal processing; analysis technique of speech signal; VQ; HMM; application of neutral networks in speech signal; speech coding; speech synthesis; speech recognition; speaker recognition; emotion information processing of speech signal; speech enhancement.



  1. Teaching Syllabus (including the content of chapters and sections. A sheet can be attached):


. Introduction


.Elementary knowledge of speech signal processing

1.speech and language

2.chinese linguistics

3.speech generation system and perception system

4. mathematical model of speech signal generation

5.characteristic analysis of speech signal


. Speech signal analysis

1. digitalization and preprocessing

2. time-domain analysis

3. frequency-domain analysis

4.cepstrum analysis

5. linear prediction analysis

6. wavelet analysis

7. pitch period estimation

8. resonance peak estimation


. Vector quantificationVQ

1. principle of VQ

2.distortion measurement of VQ

3. optimal code book design of VQ


. Hidden Markov Model (HMM)

1.introduction of HMM

2.definition of HMM

3.basic algorithm of HMM

4.several structure type of HMM


. Elementary of Artificial Neutral Network

1.introduction of ANN

2.constitution of ANN

3.several ANN model used to pattern recognition and main algorithms

4.typical method when using ANN to pattern recognition

5.application examples of ANN models


. Speech coding

1.principle and evaluation of speech signal compress coding

2.wave coding of speech signal

3.parameters coding of speech signal


. Speech synthesis

1. resonance peak synthesis method

2. linear prediction synthesis method

3.special hardware of speech synthesisi


. Speech recognition

1.principle of speech recognition and recognition system

2.dynamic time wrapping

3.isolated words recognition system

4.continuous speech recognition system


. Speaker recognition and language recognition

1. speaker recognition method and system structure

2.speaker recognition system of DTW

3.speaker recognition system of VQ

4.speaker recognition system of HMM

5.speaker recognition system of GMM

6. principle of language recognition


. Emotional information processing of speech signal

1. emotion participation of speech signal and emotional character analysis

2. speech emotion recognition methods

3.synthesis of emotional speech


 Ⅻ. Speech enhancement

1.speech and noise characteristics

2. filter method of enhancement

3.correlation application of enhancement

4.non-linear processing of enhancement

5.spectrum substitute of enhancement


  1. Teaching Schedule:


Week

Course Content

Teaching Method

1

ChapⅠ; ChapⅡ Section1-Section3

lecture

2

ChapⅡ Section4-Section6

lecture

3

ChapⅢ Section1-Section3

lecture

4

ChapⅢ Section4-Section5

lecture

5

ChapⅢ Section6-Section7

lecture

6

ChapⅣ Section1-Section3

lecture

7

ChapⅤ Section1-Section4

lecture

8

ChapⅥ Section1-Section2

lecture

9

ChapⅥ Section3-Section5

lecture

10

ChapⅦ Section1-Section3

lecture

11

ChapⅧ Section1-Section3

lecture

12

ChapⅨ Section1-Section2

lecture

13

ChapⅨ Section3-Section4

lecture

14

ChapⅩ Section1-Section3

lecture

15

ChapⅩ Section4-Section6

lecture

16

ChapⅪ Section1-Section3

lecture

17

ChapⅫ Section1-Section3

lecture

18

ChapⅫ Section4-Section5

lecture

Note: 1.Above one, two, and three items are used as teaching Syllabus in Chinese and announced on the Chinese website of Graduate School. The four and five items are preserved in Graduate School.


2. Course terms: Spring, Autumn , and Spring-Autumn term.  

3. The teaching languages for courses: Chinese, English or Chinese-English.

4. Applicable range of discipline: public, first-class discipline, second-class discipline, and third-class discipline.

5. Practice includes: experiment, investigation, research report, etc.

6. Teaching methods: lecture, seminar, practice, etc.

7. Examination for degree courses must be in paper.

8. Teaching material websites are those which have already been announced.

9. Brief introduction of chief lecturer should include: personal information (date of birth, gender, degree achieved, professional title), research direction, teaching and research achievements. (within 100-500 words)


  1. Brief Introduction of Chief lecturer:

Zhao Li, male, born in 1958, work at school of information science and engineering, Southeast University, Professor, Research at speech, audio and video signal processing and emotional information processing.



  1. Lecturer Information (include chief lecturer)


Lecturer

Discipline

(major)

Office

Phone Number

Home Phone Number

Mobile Phone Number

Email

Address

Postcode

Zhao Li

Signal and Information processing

83793791

3694370


Zhaoli@seu.edu.cn

school of information science and engineering

210096







9