內容大綱：（中或英文）
This is a first course on computer processing of speech signals. 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 user-network voice interaction for future wireless world.
Part I: Fundamental Topics
1. Digital Speech Processing
2. Fundamentals of Speech Recognition
3. Map of Subject Areas
4. More about Hidden Markov Models
5. Acoustic Modeling
6. Language Modeling
7. Speech Signals and Front-end Processing
8. Search Algorithms for Speech Recognition
Part II: Research Topics
9. Some Fundamental Problem-solving Approaches
10. Utterance Verification and Keyword/Key Phrase Spotting
11. Speaker Variabilities: Adaption and Recognition
12. Latent Semantic Analysis for Linguistic Processing
13. Speech-based Information Retrieval
14. Robustness for Acoustic Environment
15. Spoken Dialogues
16. Distributed Speech Recognition and Wireless Environment
教科書： 無
主要參考書
1. X. Huang, A. Acero, H. Hon, “Spoken Language Processing”, Prentice Hall, 2001,松瑞
2. F. Jelinek, “Statistical Methods for Speech Recognition”, MIT Press, 1999
3. L. Rabiner, B.H. Juang, “Fundamentals of Speech Recognition”, Prentice Hall, 1993, 民全
4. C. Becchetti, L. Prina Ricotti, “Speech Recognition- Theory and C++ implementation”, Johy Wiley and Sons, 1999, 民全
備註
無線通訊技術下的手機、PDA、車用電子、資訊家電等新型電子設備為硬體世界開創了全新的空間，也使網路的終端設備徹底多元化。這些多元的終端設備將逐步取代今日的個人電腦。在輕薄短小的硬體及多元的應用環境下，原有的鍵盤、滑鼠等個人電腦的上網介面將不再方便，而語音預期將成為是最方便自然的網路介面。屆時語音訊號處理技術將為新一代硬體技術的關鍵部份。本課程著重前瞻性，理論基礎與實際問題並重，基礎知識與深入研究並重，雖然未來主要的應用必將在硬體（例如晶片）上，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、大四或電信所、資工所、網媒所、電機所碩一。