An evaluation of cross-language adaptation for rapid HMM development in a new language

Abstract

The feasibility of cross-language transfer of speech technology is of increasing concern as the demand for recognition systems in multiple languages grows. The paper presents a systematic study of the relative effectiveness of different methods for seeding and training HMMs in a new language, using transfer from English to Japanese for small vocabulary speaker independent continuous speech recognition as a test case. Effects of limited training data are also explored. The study found that cross-language adaptation produced better models than alternative approaches with relatively little effort, and that the number of speakers is more critical than the number of utterances for small training data sets.<>