arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.03088eess.AS
收藏

标签同步神经转换器用于端到端自动语音识别

Label-Synchronous Neural Transducer for End-to-End ASR

Keqi Deng, Philip C. Woodland

AI总结:

本文提出标签同步神经转换器(LS-Transducer),通过AIF机制生成标签级编码器表示,消除空白标记,实现文本数据自适应,并在多个数据集上显著降低词错误率。

摘要:

神经转换器提供了一种自然的流式自动语音识别(ASR)方式。然而,它们用空白标记扩充输出序列,这给使用文本数据进行领域自适应带来了挑战。本文提出了一种标签同步神经转换器(LS-Transducer),它在将标签级编码器表示与预测网络输出结合之前提取该表示。因此,不再需要空白标记,预测网络可以很容易地使用文本数据进行自适应。提出了一种自回归积分-触发(AIF)机制来生成标签级编码器表示,同时保留流式属性。此外,设计了一种流式联合解码方法以提高ASR准确性。实验表明,与标准神经转换器相比,所提出的LS-Transducer在领域内Librispeech-100h数据上实现了10%的相对词错误率降低(WERR),在跨领域TED-LIUM2和AESRC2020数据上,使用自适应预测网络分别实现了17%和19%的相对WERR。

英文摘要:

Neural transducers provide a natural way of streaming ASR. However, they augment output sequences with blank tokens which leads to challenges for domain adaptation using text data. This paper proposes a label-synchronous neural transducer (LS-Transducer), which extracts a label-level encoder representation before combining it with the prediction network output. Hence blank tokens are no longer needed and the prediction network can be easily adapted using text data. An Auto-regressive Integrate-and-Fire (AIF) mechanism is proposed to generate the label-level encoder representation while retaining the streaming property. In addition, a streaming joint decoding method is designed to improve ASR accuracy. Experiments show that compared to standard neural transducers, the proposed LS-Transducer gave a 10% relative WER reduction (WERR) for intra-domain Librispeech-100h data, as well as 17% and 19% relative WERRs on cross-domain TED-LIUM2 and AESRC2020 data with an adapted prediction network.

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。

↑