TY - GEN
T1 - Adapting ASR for under-resourced languages using mismatched transcriptions
AU - Liu, Chunxi
AU - Jyothi, Preethi
AU - Tang, Hao
AU - Manohar, Vimal
AU - Sloan, Rose
AU - Kekona, Tyler
AU - Hasegawa-Johnson, Mark
AU - Khudanpur, Sanjeev
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/5/18
Y1 - 2016/5/18
N2 - Mismatched transcriptions of speech in a target language refers to transcriptions provided by people unfamiliar with the language, using English letter sequences. In this work, we demonstrate the value of such transcriptions in building an ASR system for the target language. For different languages, we use less than an hour of mismatched transcriptions to successfully adapt baseline multilingual models built with no access to native transcriptions in the target language. The adapted models provide up to 25% relative improvement in phone error rates on an unseen evaluation set.
AB - Mismatched transcriptions of speech in a target language refers to transcriptions provided by people unfamiliar with the language, using English letter sequences. In this work, we demonstrate the value of such transcriptions in building an ASR system for the target language. For different languages, we use less than an hour of mismatched transcriptions to successfully adapt baseline multilingual models built with no access to native transcriptions in the target language. The adapted models provide up to 25% relative improvement in phone error rates on an unseen evaluation set.
KW - ASR adaptation
KW - ASR for under-resourced languages
KW - mismatched transcriptions
UR - http://www.scopus.com/inward/record.url?scp=84973281876&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84973281876&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2016.7472797
DO - 10.1109/ICASSP.2016.7472797
M3 - Conference contribution
AN - SCOPUS:84973281876
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 5840
EP - 5844
BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Y2 - 20 March 2016 through 25 March 2016
ER -