TY - GEN
T1 - Supervised imbalanced multi-domain adaptation for text-independent speaker verification
AU - Chen, Zhiyong
AU - Ren, Zongze
AU - Xu, Shugong
N1 - Publisher Copyright:
© 2020 ACM.
PY - 2020/10/30
Y1 - 2020/10/30
N2 - Speaker verification is an important recognition task in speech signal processing. Domain adaptation for speaker verification is challenging and it is one of the practical problems put forward in the INTERSPEECH2020 Short-duration Speaker Verification (SdSV) Challenge 2020. Although there are several previous researches focused on the domain mismatch problem of the speaker verification task, many methods are not easy to show effectiveness in the real conditions. This is due to the suboptimal loss design, as well as the real-world datasets could contain multiple domains and imbalanced data in each domain. We have explored various domain adaptation methods and proposed one that is both effective and robust in this task by optimizing loss design and explicitly considering the data-imbalance problem. The proposed method is also designed to fit the scenarios where the datasets contain multiple domains. Significant single-model performance improvements have been observed by evaluating on the SdSV20 challenge testbench with our proposed method.
AB - Speaker verification is an important recognition task in speech signal processing. Domain adaptation for speaker verification is challenging and it is one of the practical problems put forward in the INTERSPEECH2020 Short-duration Speaker Verification (SdSV) Challenge 2020. Although there are several previous researches focused on the domain mismatch problem of the speaker verification task, many methods are not easy to show effectiveness in the real conditions. This is due to the suboptimal loss design, as well as the real-world datasets could contain multiple domains and imbalanced data in each domain. We have explored various domain adaptation methods and proposed one that is both effective and robust in this task by optimizing loss design and explicitly considering the data-imbalance problem. The proposed method is also designed to fit the scenarios where the datasets contain multiple domains. Significant single-model performance improvements have been observed by evaluating on the SdSV20 challenge testbench with our proposed method.
KW - Automatic speaker verification
KW - Domain adaptation
KW - Transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85099882789&partnerID=8YFLogxK
U2 - 10.1145/3436369.3437407
DO - 10.1145/3436369.3437407
M3 - Conference Proceeding
AN - SCOPUS:85099882789
T3 - ACM International Conference Proceeding Series
SP - 431
EP - 438
BT - ICCPR 2020 - Proceedings of 2020 9th International Conference on Computing and Pattern Recognition
PB - Association for Computing Machinery
T2 - 9th International Conference on Computing and Pattern Recognition, ICCPR 2020
Y2 - 30 October 2020 through 1 November 2020
ER -