arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01522eess.AScs.CL
收藏

PDKEEPAAA:用于语音识别的两步非自回归Transformer模型

TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition

NLPR, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所自然语言处理与模式识别实验室(NLPR));School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心)

Zhengkun Tian, Jiangyan Yi, Jianhua Tao, Ye Bai, Shuai Zhang, Zhengqi Wen, Xuefei Liu

摘要:

自回归(AR)模型在语音识别中取得了很大的成功,如基于注意力的编码器-解码器模型和RNN变换器模型。它们根据先前的令牌和声学编码状态来预测输出序列,这在GPU上是低效的。非自回归(NAR)模型可以摆脱输出令牌之间的时间依赖性,并在至少一个步骤中预测整个输出令牌。然而,NAR模型仍然面临两个主要问题。一方面,NAR模型与先进的AR模型在性能上仍有很大差距。另一方面,大多数NAR模型很难进行训练和收敛。为了解决这两个问题,我们提出了一个新的模型命名为两步非自回归Transformer(TSNAT),提高了性能和加速收敛的NAR模型通过学习先验知识的参数共享AR模型。在推理过程中引入了两阶段方法,大大提高了模型的性能。所有的实验都是在公开的汉语普通话数据集ASIEHLL-1上进行的。结果表明,TSNAT可以实现与AR模型竞争的性能,并优于许多复杂的NAR模型。

英文摘要:

The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence conditioned on the previous tokens and acoustic encoded states, which is inefficient on GPUs. The non-autoregressive (NAR) models can get rid of the temporal dependency between the output tokens and predict the entire output tokens in at least one step. However, the NAR model still faces two major problems. On the one hand, there is still a great gap in performance between the NAR models and the advanced AR models. On the other hand, it's difficult for most of the NAR models to train and converge. To address these two problems, we propose a new model named the two-step non-autoregressive transformer(TSNAT), which improves the performance and accelerating the convergence of the NAR model by learning prior knowledge from a parameters-sharing AR model. Furthermore, we introduce the two-stage method into the inference process, which improves the model performance greatly. All the experiments are conducted on a public Chinese mandarin dataset ASIEHLL-1. The results show that the TSNAT can achieve a competitive performance with the AR model and outperform many complicated NAR models.

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。

↑