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 2107.02670eess.AS
收藏

利用单通道语音实现多通道端到端语音识别

Exploiting Single-Channel Speech For Multi-channel End-to-end Speech Recognition

Keyu An, Zhijian Ou

摘要:

最近,神经波束形成器支持的多通道ASR的端到端训练方法在多通道语音识别中显示出其有效性。然而,多个模块的集成使得执行端到端训练变得更加困难,特别是考虑到在真实环境中记录的具有相当大数据规模的多通道语音语料库相对有限。本文探讨了如何利用单通道数据改进多通道端到端语音识别系统。具体来说,我们设计了三种方案来利用单通道数据,即预训练,数据调度和数据模拟。在CHiME 4和AISHELL-4数据集上的大量实验表明,这三种方法都提高了多通道端到端训练的稳定性和语音识别性能,而数据调度方法保持了更简单的流水线(与预训练相比)和更少的计算成本(与数据模拟相比)。此外,我们对我们的系统进行了全面的分析,包括前端的选择,数据增强,训练策略和单通道数据大小如何影响性能。

英文摘要:

Recently, the end-to-end training approach for neural beamformer-supported multi-channel ASR has shown its effectiveness in multi-channel speech recognition. However, the integration of multiple modules makes it more difficult to perform end-to-end training, particularly given that the multi-channel speech corpus recorded in real environments with a sizeable data scale is relatively limited. This paper explores the usage of single-channel data to improve the multi-channel end-to-end speech recognition system. Specifically, we design three schemes to exploit the single-channel data, namely pre-training, data scheduling, and data simulation. Extensive experiments on CHiME4 and AISHELL-4 datasets demonstrate that all three methods improve the multi-channel end-to-end training stability and speech recognition performance, while the data scheduling approach keeps a much simpler pipeline (vs. pre-training) and less computation cost (vs. data simulation). Moreover, we give a thorough analysis of our systems, including how the performance is affected by the choice of front-end, the data augmentation, training strategy, and single-channel data size.

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。

↑