TY - GEN
T1 - Arabic code-switching speech recognition using monolingual data
AU - Ali, Ahmed
AU - Chowdhury, Shammur
AU - Hussein, Amir
AU - Hifny, Yasser
N1 - Publisher Copyright:
Copyright © 2021 ISCA.
PY - 2021
Y1 - 2021
N2 - Code-switching in automatic speech recognition (ASR) is an important challenge due to globalization. Recent research in multilingual ASR shows potential improvement over monolingual systems. We study key issues related to multilingual modeling for ASR through a series of large-scale ASR experiments. Our innovative framework deploys a multi-graph approach in the weighted finite state transducers (WFST) framework. We compare our WFST decoding strategies with a transformer sequence to sequence system trained on the same data. Given a code-switching scenario between Arabic and English languages, our results show that the WFST decoding approaches were more suitable for the intersentential codeswitching datasets. In addition, the transformer system performed better for intrasentential code-switching task. With this study, we release an artificially generated development and test sets, along with ecological code-switching test set, to benchmark the ASR performance.
AB - Code-switching in automatic speech recognition (ASR) is an important challenge due to globalization. Recent research in multilingual ASR shows potential improvement over monolingual systems. We study key issues related to multilingual modeling for ASR through a series of large-scale ASR experiments. Our innovative framework deploys a multi-graph approach in the weighted finite state transducers (WFST) framework. We compare our WFST decoding strategies with a transformer sequence to sequence system trained on the same data. Given a code-switching scenario between Arabic and English languages, our results show that the WFST decoding approaches were more suitable for the intersentential codeswitching datasets. In addition, the transformer system performed better for intrasentential code-switching task. With this study, we release an artificially generated development and test sets, along with ecological code-switching test set, to benchmark the ASR performance.
KW - Code-switching
KW - Speech recognition
UR - http://www.scopus.com/inward/record.url?scp=85119170769&partnerID=8YFLogxK
U2 - 10.21437/Interspeech.2021-2231
DO - 10.21437/Interspeech.2021-2231
M3 - Conference contribution
AN - SCOPUS:85119170769
T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
SP - 1101
EP - 1105
BT - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
PB - International Speech Communication Association
T2 - 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
Y2 - 30 August 2021 through 3 September 2021
ER -