arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.01713cs.SDeess.AS
收藏

SAN-M:用于端到端语音识别的具有记忆的自注意

SAN-M: Memory Equipped Self-Attention for End-to-End Speech Recognition

Alibaba DAMO Academy(阿里巴巴达摩院);Singapore Institute of Technology(新加坡理工学院)

Zhifu Gao, Shiliang Zhang, Ming Lei, Ian McLoughlin

摘要:

端到端语音识别近年来已经变得流行,因为它可以将声学、发音和语言模型集成到单个神经网络中。在端到端的方法中,基于注意力的方法已经成为优越的。例如,采用编码器-解码器架构的Transformer。Transformer引入的关键改进是利用自注意而不是递归机制,使编码器和解码器都能够以较低的计算复杂性捕获长程依赖关系。在这项工作中,我们提出了DFSMN存储块增强自注意能力,形成拟议的记忆装备自注意(SAN-M)机制。理论和实证的比较表明,自我注意和DFSMN记忆块之间的相关性和互补性。此外,拟议的SAN-M提供了一个有效的机制来集成这两个模块。我们已经在公共AISHELL-1基准和工业级20,000小时普通话语音识别任务上评估了我们的方法。在这两项任务上,SAN-M系统的性能都比基于自我注意的Transformer基线系统好得多。特别是,即使不使用任何外部LM,它也可以在AISHELL-1任务中实现6.46%的CER,轻松超越其他最先进的系统。

英文摘要:

End-to-end speech recognition has become popular in recent years, since it can integrate the acoustic, pronunciation and language models into a single neural network. Among end-to-end approaches, attention-based methods have emerged as being superior. For example, Transformer, which adopts an encoder-decoder architecture. The key improvement introduced by Transformer is the utilization of self-attention instead of recurrent mechanisms, enabling both encoder and decoder to capture long-range dependencies with lower computational complexity.In this work, we propose boosting the self-attention ability with a DFSMN memory block, forming the proposed memory equipped self-attention (SAN-M) mechanism. Theoretical and empirical comparisons have been made to demonstrate the relevancy and complementarity between self-attention and the DFSMN memory block. Furthermore, the proposed SAN-M provides an efficient mechanism to integrate these two modules. We have evaluated our approach on the public AISHELL-1 benchmark and an industrial-level 20,000-hour Mandarin speech recognition task. On both tasks, SAN-M systems achieved much better performance than the self-attention based Transformer baseline system. Specially, it can achieve a CER of 6.46% on the AISHELL-1 task even without using any external LM, comfortably outperforming other state-of-the-art systems.

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。

↑