Knowledge Transfer from Pre-Trained Language Models to CIF-Based Speech Recognizers via Hierarchical Distillation | |
Minglun Han2,3; Feilong Chen1,3; Jing Shi3; Shuang Xu3; Bo Xu1,2,3 | |
2023-05 | |
会议日期 | 2023-8-20 |
会议地点 | Dublin, Ireland |
英文摘要 | Large-scale pre-trained language models (PLMs) have shown great potential in natural language processing tasks. Leveraging the capabilities of PLMs to enhance automatic speech recognition (ASR) systems has also emerged as a promising research direction. However, previous works may be limited by the inflexible structures of PLMs and the insufficient utilization of PLMs. To alleviate these problems, we propose the hierarchical knowledge distillation (HKD) on the continuous integrate-and-fire (CIF) based ASR models. To transfer knowledge from PLMs to the ASR models, HKD employs cross-modal knowledge distillation with contrastive loss at the acoustic level and knowledge distillation with regression loss at the linguistic level. Compared with the original CIF-based model, our method achieves 15% and 9% relative error rate reduction on the AISHELL-1 and LibriSpeech datasets, respectively. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/52064] |
专题 | 数字内容技术与服务研究中心_听觉模型与认知计算 |
通讯作者 | Jing Shi |
作者单位 | 1.School of Future Technology, University of Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Minglun Han,Feilong Chen,Jing Shi,et al. Knowledge Transfer from Pre-Trained Language Models to CIF-Based Speech Recognizers via Hierarchical Distillation[C]. 见:. Dublin, Ireland. 2023-8-20. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论