课程名称 (Course Name) ： Intelligent Speech Technology

课程代码 (Course Code)： CS26001

学分/学时 (Credits/Credit Hours)： 3.0/48

开课时间 (Course Term )：  Spring

开课学院（School Providing the Course）:  Computer Science Department

任课教师（Teacher）:  Kai Yu

课程讨论时数（Course Discussion Hours）:  4

课程实验数（Lab Hours）:   4

课程内容简介(Course Introduction):

This course introduces the basic theory and tools for intelligent speech technology, with a focus on automatic speech recognition. It includes fundamental theories of pattern recognition and machine learning, acoustic modeling (hidden Markov model), language model (N-gram model), and advanced techniques of large vocabulary continuous speech recognition.

教学大纲(Course Teaching Outline):

1.    Overview Intelligent Speech Technology

2.    Probability and Stochastic Process

3.    Pattern Recognition

4.    Bayesian decision theory

5.    Expectation Algorithm and Gaussian Mixture Model

6.    Speech Processing and Feature Extraction

7.    Hidden Markov Model

8.    Statistical language model

9.    Decoding algorithm

10. Issues of large vocabulary continuous speech recognition

课程进度计划(Course Schedule):

Week 1-5: Pattern Recognition and Bayesian decision theory

Week 6: EM algorithm and Gaussian mixture model

Week 7-8: Speech processing and feature extraction

Week 9-10: hidden Markov model

Week 11: Statistical language model

Week 12: Advanced techniques of LVCSR

课程考核要求(Course Assessment Requirements)：

Evaluation will be based on two course works and one group presentation.

参考文献(Course References)：

Xuedong Huang, Alex Acero, Raj Reddy and Hsiao-Wuen Hon, Spoken Language Processing: A Guide to Theory, Algorithm and System Development. Prentice Hall, 2001.

S. J. Young, D. Kershaw, J. J. Odell, D. Ollason, V. Valtchev, and P. C. Woodland. The HTK Book (for HTK version 3.0). Cambridge University Engineering Department, 2000.

预修课程（Prerequisite Course）

Calculus, Probability, Linear Algebra