This course is a required specialized course for the student of Electronic and Information Engineering department in the 6th semester. It covers the basic principles of digital speech processing. Fundamentals of speech production and perception are introduced. Basic techniques for digital speech processing and speech estimation methods are emphasized. The basic techniques include short time energy, magnitude autocorrelation and Fourier analysis, homomorphic methods, linear predictive methods. Speech/non-speech detection, voiced/unvoiced /non-speech segmentation and classification, pitch detection and formant estimation methods are deeply addressed in the part of speech estimation. Applications of speech signal processing include speech coding, speech recognition and speech synthesis are also introduced to the students. A term project will be required for all students taking this course for credit.

The course aims to:
(1)	improve the students’ self-service awareness of applying the intelligent speech technology to the service consciousness of national strategy and social development needs, especially in key industries such as education and medical care, etc. (培养学生主动将智能语音技术灵活运用到国家战略和社会发展需要的服务意识，特别是教育、医疗等重点行业。)
(2)	improve the ability of theory understanding and exploration or innovation of the students by providing lectures about the principle and processing methods of speech signal processing. (通过讲授语音信号处理基本原理和处理方法，提高学生的理论理解和探索或创新能力。)
(3)	improve the students’ engineering implementation ability by introducing how to use computers and related software to finish some actual speech signal processing examples in these lectures. (通过介绍如何使用计算机和相关软件完成课程中一些实际的语音信号处理实例，提高学生的工程实施能力，培养学生服务社会的价值观。)
(4)	improve the students’ ability  of basic data analysis, system design, team working, communication and apply it to practical engineering problem solving, by using the project-based teaching approach. (运用基于项目的教学方法，提高学生基础数据分析、系统设计、团队工作、沟通能力，并将其应用于实际工程问题解决。)