The authors describes the Lwazi corpus for automatic speech recognition (ASR), a new telephone speech corpus which includes data from nine Southern Bantu languages. 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.
Reference:
Badenhorst, JAC,Van Heerden, C, Davel, M et al. 2009. Collecting and evaluating speech recognition corpora for nine Southern Bantu languages. EACL Workshop on Language Technologies for African Languages, Athens, Greece, 31 March 2009, pp 1-8
Badenhorst, J., Van Heerden, C., Davel, M., & Barnard, E. (2009). Collecting and evaluating speech recognition corpora for nine Southern Bantu languages. Association for Computational Linguistics. http://hdl.handle.net/10204/4128
Badenhorst, JAC, C Van Heerden, M Davel, and E Barnard. "Collecting and evaluating speech recognition corpora for nine Southern Bantu languages." (2009): http://hdl.handle.net/10204/4128
Badenhorst J, Van Heerden C, Davel M, Barnard E, Collecting and evaluating speech recognition corpora for nine Southern Bantu languages; Association for Computational Linguistics; 2009. http://hdl.handle.net/10204/4128 .
ResearchSpace
