ASR 2018-19 | News Archive | Lectures | Labs | Coursework | Piazza
This lecture covered multilingual and low-resource speech recognition - how to develop speech recognition systems for a diversity of languages, most of which have very limited resources.
Besaciera et al's Speech Communication article gives a good introduction to the general problem of speech recognition of low-resource languages. There is no single paper which gives good coverage of more recent DNN approaches, but Huang et al's ICASSP-2013 paper is as good as any.
Copyright (c) University of Edinburgh 2015-2019
The ASR course material is licensed under the
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License
licence.txt
This page maintained by Steve Renals.
Last updated: 2019/04/23 17:41:15UTC
Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail: school-office@inf.ed.ac.uk Please contact our webadmin with any comments or corrections. Logging and Cookies Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh |