Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages

Understand

This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages.

• Two approaches are considered.
• The first constructs four separate bilingual automatic speech recognisers (ASRs) corresponding to four different language pairs between which speakers switch frequently.
• The second uses a single, unified, five-lingual ASR system that represents all the languages (English, isiZulu, isiXhosa, Setswana and Sesotho).