arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.06865cs.SDeess.AS
收藏

具有线性注意力的高效的基于顺应者的语音识别

Efficient conformer-based speech recognition with linear attention

Northwestern Polytechnical University(西北工业大学)

Shengqiang Li, Menglong Xu, Xiao-Lei Zhang

摘要:

最近,基于一致性的端到端自动语音识别,它优于基于递归神经网络的,受到了广泛的关注。虽然构象的并行计算比递归神经网络更有效,但其点积自注意的计算复杂性与输入特征的长度成二次关系。为了降低自注意层的计算复杂性,提出了一种多头线性自注意层,将自注意层的计算复杂性降低到线性阶。此外,我们提出了因式分解的前馈模块的构象低秩矩阵因式分解,成功地减少了约50%的参数的数量,几乎没有性能损失。提出的基于线性注意力的整合器模型(LAC)可以与连接主义时态分类目标联合训练和推理,进一步提高了LAC的性能。为了评估LAC的有效性,我们在AISHELL-1和LibriSpeech语料库上进行了实验。实验结果表明,所提出的LAC比最近提出的7种语音识别模型具有更好的识别性能,与现有的一致性识别器相比具有一定的竞争力。同时,建议的LAC有一些参数,只有50%以上的构象与更快的训练速度比后者。

英文摘要:

Recently, conformer-based end-to-end automatic speech recognition, which outperforms recurrent neural network based ones, has received much attention. Although the parallel computing of conformer is more efficient than recurrent neural networks, the computational complexity of its dot-product self-attention is quadratic with respect to the length of the input feature. To reduce the computational complexity of the self-attention layer, we propose multi-head linear self-attention for the self-attention layer, which reduces its computational complexity to linear order. In addition, we propose to factorize the feed forward module of the conformer by low-rank matrix factorization, which successfully reduces the number of the parameters by approximate 50% with little performance loss. The proposed model, named linear attention based conformer (LAC), can be trained and inferenced jointly with the connectionist temporal classification objective, which further improves the performance of LAC. To evaluate the effectiveness of LAC, we conduct experiments on the AISHELL-1 and LibriSpeech corpora. Results show that the proposed LAC achieves better performance than 7 recently proposed speech recognition models, and is competitive with the state-of-the-art conformer. Meanwhile, the proposed LAC has a number of parameters of only 50% over the conformer with faster training speed than the latter.

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。

↑