arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.02774eess.AScs.CLcs.SD
收藏

基于门机制的多口音自适应

Multi-Accent Adaptation based on Gate Mechanism

Institute of Acoustics(声学研究所);University of Chinese Academy of Sciences(中国科学院大学);Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences(中国科学院新疆理化技术研究所)

Han Zhu, Li Wang, Pengyuan Zhang, Yonghong Yan

摘要:

当只有有限数量的口音语音数据可用时,为了提高多口音语音识别性能,传统的方法是口音特定的自适应,其独立地使基线模型适应多个目标口音。为了简化自适应过程,我们探讨了多口音混合数据同时适应多个目标口音的基线模型。因此,我们建议使用口音特定的顶层与门机制(AST-G)来实现多口音适应。与基线模型和口音适应相比,AST-G分别实现了9.8%和1.9%的平均相对WER降低。然而,在实际应用中,我们无法预先获得重音类别标签进行推理。因此,我们应用重音分类器来预测重音标签。为了联合训练声学模型和口音分类器,我们提出了多任务学习与门机制(MTL-G)。由于重音标签预测可能不准确,因此它的性能比特定于重音的自适应更差。然而,与基线模型相比,MTL-G实现了5.1%的平均相对WER降低。

英文摘要:

When only a limited amount of accented speech data is available, to promote multi-accent speech recognition performance, the conventional approach is accent-specific adaptation, which adapts the baseline model to multiple target accents independently. To simplify the adaptation procedure, we explore adapting the baseline model to multiple target accents simultaneously with multi-accent mixed data. Thus, we propose using accent-specific top layer with gate mechanism (AST-G) to realize multi-accent adaptation. Compared with the baseline model and accent-specific adaptation, AST-G achieves 9.8% and 1.9% average relative WER reduction respectively. However, in real-world applications, we can't obtain the accent category label for inference in advance. Therefore, we apply using an accent classifier to predict the accent label. To jointly train the acoustic model and the accent classifier, we propose the multi-task learning with gate mechanism (MTL-G). As the accent label prediction could be inaccurate, it performs worse than the accent-specific adaptation. Yet, in comparison with the baseline model, MTL-G achieves 5.1% average relative WER reduction.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑