Sixth European Conference on Speech Communication and Technology
This paper introduces a family of three techniques to improve non-native speaker-independent recognition if the type of accent, i.e. the mother tongue of a non-native speaker is known. These techniques permit the computation of non-native models without requiring adaptation data, that is, they can be computed off-line. The improved recognition performance of these approaches is obtained by combining speaker-independent hidden Markov models of the target language, i.e. the language to be taught, and of the source language, i.e. the speaker's native language. All three combination techniques require a mapping between the two languages to define which source model state combines with each target model state. A method has been developed to derive such a mapping automatically. Recognition results are given for all three techniques applied to the two cases of Spanish accented British English and Japanese accented British English. The average baseline word error rate of 28:3% can be decreased to 22:9% for the first method, to 24:1% for the second and to 20:6% for the last method, which equals a relative improvement of 29% without adaptation.
Full Paper (PDF) Gnu-Zipped Postscript
Bibliographic reference. Witt, Silke / Young, Steve (1999): "Off-line acoustic modelling of non-native accents", In EUROSPEECH'99, 1367-1370.