aslp@nwpu

中文版

only search Dr. Lei Xie's homepage

Last Modified: Nov 9, 2009

 

Lei Xie > Course > Introduction to Audio, Speech & Language Processing

URL: http://www.npu-aslp.org/lxie/intro2aslp.htm

2009 Spring Course for Postgraduate Students

2009年春季研究生课程:音频、语音与语言处理技术导论

Contact: lxie AT nwpu.edu.cn or xielei21st AT gmail.com (convert AT to @)

Please feel free to contact me if you have any questions.

Course Description:

This course gives postgraduate students a broad picture in issues surrouding audio, speech & language processing. Lecture topics involve basic concepts of acoustics, phonetics, speech production and perception, automatic speech recognition (ASR), speaker recognition, speech synthesis, audio-visual speech processing, basic concepts in natural language processing (NLP), language models, audio scene anaysis and audio information retrieval. The course will span from brief history of the each technology to the cutting-edge development and the state-of-the-art performance.

本课程将提供给研究生有关音频、语音与语言处理的相关的、广泛的基础知识,使学生对该领域有一个全面的了解和认识。课程讲座主题包括声学语音学基础、语音产生与感知、语音识别、说话人识别、语音合成、音视频语音处理、自然语言处理综论、语言模型、音频场景分析、音频检索等内容。课程将涉及各个研究领域的简史、基础理论与基础技术、当前技术性能与最新发展动态等。

Venue & Time:

  • Venue: Room 210, East Acadamic Bldg. (JiaoDong) Block B, Chang'an Campus, NWPU
  • Time: 2:00PM-3:40PM Thursday

Syllabus:

Lecture #
Slides
Supporting materials & readings

Lecture 1:

Introduction to the course

Acoustics & Phonetics Basics, Speech Prodcution & Perception

课程简介

声学、语音学基础,语音产生与语音感知

 

Subsonic & Utrasonic

Phonetics (from Wikipedia)

Phoneme (from Wikipedia)

IPA (from Wikipedia)

Spectrogram (from Wikipedia)

Speech Perception: Loudness, Pitch & Timbre

 

Lecture 2:

Speech Recognition

语音识别

Microphones

Speech Recogntion on Wikipedia

Victor Zue's HIT Lecture on Human Langugae Technology

Rabinar's Classic Tutorial on Hidden Markov Models

Guest Lecture 1:

A Very Brief Tutorial on HTK

特邀讲座 (杨玉莲)

HTK工具包简介

HTK Website

Lecture 3:

Speaker Recognition

说话人识别

A Tutorial on Text-Independent Speaker Verification

An overview of automatic speaker recognition technology

Alize: speaker recognition toolkit

Lecture 4:

Speech Synthesis

语音合成

HTS: HMM-based speech synthesis

Normalization of Non-Standard Words

UNIT SELECTION IN A CONCATENATIVE SPEECH SYNTHESIS SYSTEM USING A LARGE SPEECH DATABASE

Lecture 5:

Multimodal & Audio-Visual speech Processing

多模态及音视频语音处理

N.A.

Note: You may need password to access to the slides. Please contact me if you need the password.

Disclaimer The videos played in class are used for teaching purpose only. The copyrights are solely belong to the original orgnizations or companies. Special thanks to these orgnizations or companies. Any questions, plz contact me by lxie at nwpu.edu.cn. Comments and Suggestions are more than welcome.

Back to Dr. Lei Xie's Homepage