Towards multilingual interoperability in automatic speech recognition

Abstract

This communication addresses multilingual aspects in speech recognition and tries to link them to the concept of interoperability. After a tentative definition of multilingual interoperability, the speech recognition components are discussed with a view towards separating language-specific from language-independent elements. An overview gives examples of previous multilingual speech recognition research and developments across different speaking styles (read, prepared and conversational). The problem of adaptation across languages is addressed. In particular there exist language-independent and cross-language acoustic modeling techniques to port recognition systems from one language to another without language-specific acoustic data. However these data remain valuable for acoustic model adaptation. At this time pronunciation dictionaries and text material appear to be the most crucial language-dependent resources. In our opinion fast porting, enabled by the existence of these language-dependent resources, is a step towards multilingual interoperability. On-going efforts to produce multilingual pronunciation dictionaries and to collect multilingual text corpora including speech transcripts, should be extended to the largest possible number of languages. These efforts could be shared with initiatives aiming at the support of minority languages.