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 o -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 de ne 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 rst method, to 24:1% for the second and to 20:6% for the last method, which equals a relative improvement of 29% without adaptation.
[1]
Steve Young,et al.
The HTK book
,
1995
.
[2]
Philip C. Woodland,et al.
Speaker adaptation of HMMs using linear regression
,
1994
.
[3]
Silke M. Witt,et al.
Use of speech recognition in computer-assisted language learning
,
2000
.
[4]
Steve Young,et al.
Bilingual model combination for non-native speech recognition
,
1998
.
[5]
J. Kenworthy.
Teaching English Pronunciation
,
1987
.
[6]
Sanjeev Khudanpur,et al.
Is automatic speech recognition ready for non-native speech? A data collection effort and initial experiments in modelling conversational Hispanic English
,
1998
.
[7]
Lin Lawrance Chase.
Error-responsive feedback mechanisms for speech recognizers
,
1997
.
[8]
J. Flege.
Production and perception of a novel, second-language phonetic contrast.
,
1993,
The Journal of the Acoustical Society of America.