arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.09807eess.AS
收藏

CUSIDE-array:一种结合真实评估的流式多通道端到端语音识别系统

CUSIDE-array: A Streaming Multi-Channel End-to-End Speech Recognition System with Realistic Evaluations

Xiangzhu Kong, Tianqi Ning, Hao Huang, Zhijian Ou

AI总结:

针对流式多通道端到端ASR探索不足及分布外泛化弱的问题,提出CUSIDE-array方法,将CUSIDE整合进神经波束形成器,实现402ms延迟的流式处理,在分布内/外测试均表现优异,还可通过单通道数据训练提升泛化能力。

摘要:

近年来,多通道端到端(ME2E)自动语音识别(ASR)系统不断涌现。尽管流式单通道端到端ASR已得到广泛研究,但流式ME2E ASR的探索仍较为有限。此外,近期研究提醒学界关注分布内(ID)测试与分布外(OOD)测试之间的差距,以及开展真实评估的必要性。本文聚焦两个研究问题:实现流式ME2E ASR,以及提升OOD泛化能力。我们提出CUSIDE-array方法,将最新的CUSIDE方法(分块、模拟未来上下文与解码)整合到ME2E ASR的神经波束形成器架构中,实现前端与后端的流式处理,总延迟为402ms。实验表明,CUSIDE-array ME2E模型在ID和OOD测试中均取得了优异的流式识别结果。真实评估证实了CUSIDE-array的优势:它可利用单通道数据,通过后端预训练与ME2E微调提升OOD泛化能力。

英文摘要:

Recently multi-channel end-to-end (ME2E) ASR systems have emerged. While streaming single-channel end-to-end ASR has been extensively studied, streaming ME2E ASR is limited in exploration. Additionally, recent studies call attention to the gap between in-distribution (ID) and out-of-distribution (OOD) tests and doing realistic evaluations. This paper focuses on two research problems: realizing streaming ME2E ASR and improving OOD generalization. We propose the CUSIDE-array method, which integrates the recent CUSIDE methodology (Chunking, Simulating Future Context and Decoding) into the neural beamformer approach of ME2E ASR. It enables streaming processing of both front-end and back-end with a total latency of 402ms. The CUSIDE-array ME2E models are shown to achieve superior streaming results in both ID and OOD tests. Realistic evaluations confirm the advantage of CUSIDE-array in its capability to consume single-channel data to improve OOD generalization via back-end pre-training and ME2E fine-tuning.

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。

↑