Exploring wav2vec 2.0 on speaker verification and language identification
文献类型:会议论文
作者 | Fan ZY(范志赟)1,2; Li M(李蒙)2; Zhou SY(周世玉)2; Xu B(徐波)2 |
出版日期 | 2021-09 |
会议日期 | 2021-8-30 |
会议地点 | 线上会议 |
关键词 | self-supervised speaker verification language identification multi-task learning wav2vec 2.0 |
英文摘要 | Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning. It follows a two-stage training process of pre-training and fine-tuning, and performs well in speech recognition tasks especially ultra-low resource cases. In this work, we attempt to extend the self-supervised framework to speaker verification and language identification. First, we use some preliminary experiments to indicate that wav2vec 2.0 can capture the information about the speaker and language. Then we demonstrate the effectiveness of wav2vec 2.0 on the two tasks respectively. For speaker verification, we obtain a competitive result with the Equal Error Rate (EER) of 3.61% on the VoxCeleb1 dataset. For language identification, we obtain an EER of 12.02% on the 1 second condition and an EER of 3.47% on the full-length condition of the AP17-OLR dataset. Finally, we utilize one model to achieve the unified modeling by the multi-task learning for the two tasks. |
源URL | [http://ir.ia.ac.cn/handle/173211/49730] |
专题 | 数字内容技术与服务研究中心_听觉模型与认知计算 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 2.Institute of Automation, Chinese Academy of Sciences, China |
推荐引用方式 GB/T 7714 | Fan ZY,Li M,Zhou SY,et al. Exploring wav2vec 2.0 on speaker verification and language identification[C]. 见:. 线上会议. 2021-8-30. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。