Topic outline

  • The goal of this course is to become familiar with speech recognition methods and applications. Additionally, to learn to understand the structure of a typical speech recognition system and to know how to construct one in practice.

    Topics include:

    • Preprocessing and feature extraction for speech
    • Phoneme models
    • Decoding
    • Lexicon and language models
    • Recognition and retrieval of continuous speech

    All lectures are held on campus. Additional TA support for home assignments will be provided via a Zulip chat. There will be a mandatory participation survey (open 25 Sep - 24 Oct) to submit your preferences for project work groups. All lectures will have lecture exercises, quizzes and feedback surveys which will give activity points for the course grade.

    See the Course Practicalities section for more information on course organization and timetable.