针对远场语音识别，提出多说话人分离与识别系统，性能较基线提升57%。
NTT Multi-Speaker ASR System for the DASR Task of CHiME-8 Challenge
- 先语音分离后识别，用端到端聚类+目标说话人检测优化
- 自研多通道说话人计数，适配不同人数场景，开发集宏平均词错误率21.3%
- 结合强预训练模型，适合复杂环境下的多人远场语音识别任务
我们为CHiME-8挑战赛的远场自动语音识别（DASR）任务提出了一套系统。该系统采用先说话人分离的流程：首先使用端到端说话人聚类（EEND-VC）进行说话人分离，并通过目标说话人语音活动检测（TS-VAD）进行精细化处理；为应对不同数量的说话人，我们提出了新的多通道说话人计数方法；随后对基线系统进行了改进的引导源分离（GSS）；最后利用多个基于强预训练模型构建的ASR系统进行融合。所提系统在开发集上实现了21.3%的宏平均词错误率（macro tcpWER），相比基线系统相对提升57%。
原文摘要 · Abstract (English)
We present a distant automatic speech recognition (DASR) system developed for the CHiME-8 DASR track. It consists of a diarization first pipeline. For diarization, we use end-to-end diarization with vector clustering (EEND-VC) followed by target speaker voice activity detection (TS-VAD) refinement. To deal with various numbers of speakers, we developed a new multi-channel speaker counting approach. We then apply guided source separation (GSS) with several improvements to the baseline system. Finally, we perform ASR using a combination of systems built from strong pre-trained models. Our proposed system achieves a macro tcpWER of 21.3 % on the dev set, which is a 57 % relative improvement over the baseline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。