課程資訊
課程名稱
數位語音處理概論
Introduction to Digital Speech Processing 
開課學期
100-1 
授課對象
電機資訊學院  電機工程學系  
授課教師
李琳山 
課號
EE4037 
課程識別碼
901 40900 
班次
 
學分
全/半年
半年 
必/選修
選修 
上課時間
星期三2,3,4(9:10~12:10) 
上課地點
 
備註
上課地點:資104
總人數上限:106人 
Ceiba 課程網頁
http://ceiba.ntu.edu.tw/1001ee4037 
課程簡介影片
 
核心能力關聯
核心能力與課程規劃關聯圖
課程大綱
為確保您我的權利,請尊重智慧財產權及不得非法影印
課程概述

This is a first course on computer processing of speech signals for undergraduate students in electrical engineering and computer science. Both theoretical issues and practical problems will be discussed, and both fundamental concepts and research topics will be emphasized. The viewpoints will be centralized on the vision of spoken language processing under-network environment.
Part I: Fundamental Topics
1.Introduction
2.Basic Concepts in Speech Recognition
3.Research Roadmap in this Area
4.More about Hidden Markov Models (HMM)
5.Acoustic Modeling
6.Language Modeling
7.Speech Signals and Front-end Processing
8.Linguistic Decoding and Search Algorithm
Part II: Research Topics
1.Speaker Variabilities: Adaptation and Recognition
2.Latent Semantic Analysis for Linguistic Processing
3.Voice-based Information Retrieval
4.Robustness for Acoustic Environment
5.Spoken Document Understanding and Organization
6.Some Fundamental Problem-solving Approaches
7.Keyword Spotting and Utterance Verification
8.Spoken Dialogues
9.Distributed Speech Recognition and Wireless Environment 

課程目標
本課程所需要的最主要基礎能力是數學模型(機率、線性代數)及軟體程式,前半強調基礎背景知識,後半則著重研究課題,讓修課同學體會由基礎走入研究的歷程。內容深度適合電機系或資工系大三或大四同學選修。 
課程要求
 
預期每週課後學習時數
 
Office Hours
 
參考書目
教科書:
參考書目:1.X. Huang, A. Acero, H. Hon, “Spoken Language Processing”, Prentice Hall, 2001,松瑞
2.C. Becchetti, L. Prina Ricotti, “Speech Recognition- Theory and C++ implementation”, Johy Wiley and Sons, 1999, 民全
3.L. Rabiner, B.H. Juang, “Fundamentals of Speech Recognition”, Prentice Hall, 1993, 民全
4.F. Jelinek, “Statistical Methods for Speech Recognition”, MIT Press, 1999
 
指定閱讀
 
評量方式
(僅供參考)
   
課程進度
週次
日期
單元主題