Collecting and evaluating speech recognition corpora for 11 South African languages

TitleCollecting and evaluating speech recognition corpora for 11 South African languages
Publication TypeJournal Article
Year of Publication2011
AuthorsBadenhorst, J., Van Heerden C., Davel M. H., and Barnard Etienne
Journal TitleLanguage Resources and Evaluation
Journal Date09/2011
Volume45
Issue3
Pagination289-309
ISSN1574-020X
Abstract

We describe the Lwazi corpus for automatic speech recognition (ASR), a new telephone speech corpus which contains data from the eleven official languages of South Africa. Because of practical constraints, the amount of speech per language is relatively small compared to major corpora in world languages, and we report on our investigation of the stability of the ASR models derived from the corpus. We also report on phoneme distance measures across languages, and describe initial phone recognisers that were developed using this data. We find that a surprisingly small number of speakers (fewer than 50) and around 10 to 20 h of speech per language are sufficient for the purposes of acceptable phone-based recognition.

URLhttp://www.springerlink.com/content/m772051343jg875k/
DOI10.1007/s10579-011-9152-1