TY - GEN
T1 - The SLT 2021 Children Speech Recognition Challenge
T2 - 2021 IEEE Spoken Language Technology Workshop, SLT 2021
AU - Yu, Fan
AU - Yao, Zhuoyuan
AU - Wang, Xiong
AU - An, Keyu
AU - Xie, Lei
AU - Ou, Zhijian
AU - Liu, Bo
AU - Li, Xiulin
AU - Miao, Guanqiong
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/1/19
Y1 - 2021/1/19
N2 - Automatic speech recognition (ASR) has been significantly advanced with the use of deep learning and big data. How-ever improving robustness, including achieving equally good performance on diverse speakers and accents, is still a challenging problem. In particular, the performance of children speech recognition (CSR) still lags behind due to 1) the speech and language characteristics of children's voice are substantially different from those of adults and 2) sizable open dataset for children speech is still not available in the research community. To address these problems, we launch the Children Speech Recognition Challenge (CSRC), as a flagship satellite event of IEEE SLT 2021 workshop. The challenge will release about 400 hours of Mandarin speech data for registered teams and set up two challenge tracks and provide a common testbed to benchmark the CSR performance. In this paper, we introduce the datasets, rules, evaluation method as well as baselines.
AB - Automatic speech recognition (ASR) has been significantly advanced with the use of deep learning and big data. How-ever improving robustness, including achieving equally good performance on diverse speakers and accents, is still a challenging problem. In particular, the performance of children speech recognition (CSR) still lags behind due to 1) the speech and language characteristics of children's voice are substantially different from those of adults and 2) sizable open dataset for children speech is still not available in the research community. To address these problems, we launch the Children Speech Recognition Challenge (CSRC), as a flagship satellite event of IEEE SLT 2021 workshop. The challenge will release about 400 hours of Mandarin speech data for registered teams and set up two challenge tracks and provide a common testbed to benchmark the CSR performance. In this paper, we introduce the datasets, rules, evaluation method as well as baselines.
KW - audio
KW - Automatic speech recognition
KW - children speech recognition
KW - datasets
KW - deep learning
UR - http://www.scopus.com/inward/record.url?scp=85103971663&partnerID=8YFLogxK
U2 - 10.1109/SLT48900.2021.9383608
DO - 10.1109/SLT48900.2021.9383608
M3 - 会议稿件
AN - SCOPUS:85103971663
T3 - 2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings
SP - 1117
EP - 1123
BT - 2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 January 2021 through 22 January 2021
ER -