Topic outline

  • General

    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 (first 5 weeks on Wednesdays and after that both Wednesdays and Fridays) are online. The Thursday exercise sessions (the first 5 weeks) are on campus and Friday exercises (the first 5 weeks) are online. The content of Thursday and Friday exercises are identical. There will be a mandatory participation survey (open 19 - 31 Oct) to submit your preferences for project work groups and home exercise sessions. 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.