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 2106.09236cs.SDeess.AS
收藏

基于概率稀疏注意力机制的End-to-EndSpeech识别中的高效构象算子

Efficient Conformer with Prob-Sparse Attention Mechanism for End-to-EndSpeech Recognition

Northwestern Polytechnical University(西北工业大学);Tencent(腾讯)

Xiong Wang, Sining Sun, Lei Xie, Long Ma

摘要:

端到端模型由于其简化的系统结构和优越的性能而在自动语音识别(ASR)中受到青睐。在这些模型中,Transformer和Conformer已经达到了最先进的识别精度,其中自我注意力在捕获重要的全局信息方面起着至关重要的作用。然而,自我注意的时间和记忆复杂性随着句子的长度而增加。本文在Conformer中引入概率稀疏的自注意力机制,使自注意力的计算过程稀疏化,从而加快推理速度,减少空间消耗。具体来说,我们采用Kullback-Leibler分歧为基础的稀疏性测量每个查询,以决定我们是否计算注意力函数在这个查询。通过使用概率稀疏的注意力机制,我们实现了令人印象深刻的8%至45%的推理速度和15%至45%的内存使用减少的自注意模块的构象传感器,而保持相同的水平的出错率。

英文摘要:

End-to-end models are favored in automatic speech recognition (ASR) because of their simplified system structure and superior performance. Among these models, Transformer and Conformer have achieved state-of-the-art recognition accuracy in which self-attention plays a vital role in capturing important global information. However, the time and memory complexity of self-attention increases squarely with the length of the sentence. In this paper, a prob-sparse self-attention mechanism is introduced into Conformer to sparse the computing process of self-attention in order to accelerate inference speed and reduce space consumption. Specifically, we adopt a Kullback-Leibler divergence based sparsity measurement for each query to decide whether we compute the attention function on this query. By using the prob-sparse attention mechanism, we achieve impressively 8% to 45% inference speed-up and 15% to 45% memory usage reduction of the self-attention module of Conformer Transducer while maintaining the same level of error rate.

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。

↑