TY - JOUR
T1 - Topic and keyword identification for low-resourced speech using cross-language transfer learning
AU - Chen, Wenda
AU - Hasegawa-Johnson, Mark
AU - Chen, Nancy F.
N1 - Funding Information:
This work is funded by the Agency for Science, Technology and Research (A*STAR) Graduate Scholarship.
Publisher Copyright:
© 2018 International Speech Communication Association. All rights reserved.
PY - 2018
Y1 - 2018
N2 - This paper studies topic and keyword identification for languages in which we have no transcribed speech data. We adopt a transfer learning framework to transfer what is learned from rich-resourced languages (RRL) to low-resourced languages (LRL). Specifically, we propose that a convolutional neural network (CNN) trained as a topic classifier in an RRL learns features (hidden layer activations) that can be used for the same purpose in an LRL. The CNN observes acoustic features, RRL phones, or segment clusters generated by an unsupervised phone clustering system; its hidden layers are retained, and its output layer re-trained from scratch on the LRL. Our results are compared with the state-of-the-art topic classification methods on cross-language ASR transcripts. We also discuss the successful detection of topic dependent keywords and the use of unsupervised learning based clusters in our approach for low-resourced language topic detection.
AB - This paper studies topic and keyword identification for languages in which we have no transcribed speech data. We adopt a transfer learning framework to transfer what is learned from rich-resourced languages (RRL) to low-resourced languages (LRL). Specifically, we propose that a convolutional neural network (CNN) trained as a topic classifier in an RRL learns features (hidden layer activations) that can be used for the same purpose in an LRL. The CNN observes acoustic features, RRL phones, or segment clusters generated by an unsupervised phone clustering system; its hidden layers are retained, and its output layer re-trained from scratch on the LRL. Our results are compared with the state-of-the-art topic classification methods on cross-language ASR transcripts. We also discuss the successful detection of topic dependent keywords and the use of unsupervised learning based clusters in our approach for low-resourced language topic detection.
KW - Low-resourced languages
KW - Speech recognition
KW - Topic detection
UR - http://www.scopus.com/inward/record.url?scp=85054976924&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85054976924&partnerID=8YFLogxK
U2 - 10.21437/Interspeech.2018-1283
DO - 10.21437/Interspeech.2018-1283
M3 - Conference article
AN - SCOPUS:85054976924
SN - 2308-457X
VL - 2018-September
SP - 2047
EP - 2051
JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
T2 - 19th Annual Conference of the International Speech Communication, INTERSPEECH 2018
Y2 - 2 September 2018 through 6 September 2018
ER -