Lecture 1 - Introduction
This lecture was an introduction to the ASR course.
- Basic logistics for the course
- Necessary background
- The problem of automatic speech recognition, and why it is difficult
- Hierarchical modelling of speech and the basic components of an ASR system - signal analysis, acoustic modelling, lexicon, language modelling, search.
- Frame-based representation of recorded speech
- Labelling recorded speech
- Phones and phonemes
- The TIMIT corpus
- Evaluating speech recognition using word error rate - substitutions, insertions, deletions
This page maintained by Steve Renals.
Last updated: 2017/03/19 18:58:49UTC
|Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail:
Please contact our webadmin with
any comments or corrections. Logging and Cookies
Unless explicitly stated otherwise, all material is copyright ©
The University of Edinburgh