Third Workshop on Spoken Language Technologies for Under-resourced Languages

Cape Town, South Africa
May 7-9, 2012

Hausa Large Vocabulary Continuous Speech Recognition

Tim Schlippe, Edy Guevara Komgang Djomgang, Ngoc Thang Vu, Sebastian Ochs, Tanja Schultz

Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany

We report on our efforts toward an LVCSR system for the African language Hausa. We describe the Hausa text and speech database recently collected as a part of our Global- Phone corpus [1]. The data was complemented by a large collection of text data crawled from various Hausa websites. We achieve significant improvement by automatically substituting inconsistent or flawed pronunciation dictionary entries, including tone and vowel length information, applying stateof- the art techniques for acoustic modeling, and crawling large quantities of text material from the Internet for language modeling. A system combination of the best grapheme- and phoneme-based 2-pass systems achieves a word error rate of 13.16% on the development set and 16.26% on the test set on read newspaper speech.

Index Terms: speech recognition, rapid language adaptation, Hausa, African language

Reference

  1. T. Schultz, “GlobalPhone: A Multilingual Speech and Text Database Developed at Karlsruhe University,” in ICSLP, 2002

Full Paper

Bibliographic reference.  Schlippe, Tim / Djomgang, Edy Guevara Komgang / Vu, Ngoc Thang / Ochs, Sebastian / Schultz, Tanja (2012): "Hausa large vocabulary continuous speech recognition", In SLTU-2012, 11-14.