通过解耦说话人分离与语音识别提升鲁棒性多说话人ASR性能
Elevating Robust Multi-Talker ASR by Decoupling Speaker Separation and Speech Recognition
AI总结：
针对多说话人场景下ASR前端分离引入伪影导致性能下降的问题，提出分离前端与ASR后端训练解耦、后端仅用干净语音训练的方法，在多个基准数据集上取得了最优词错误率，为鲁棒多说话人ASR提供了有效方案。
摘要：
尽管深度学习的引入让自动语音识别（ASR）取得了巨大成功，但在诸多真实世界多说话人场景下，其性能仍不尽如人意。说话人分离技术擅长分离单个说话人语音，但作为前端模块时，它会引入处理伪影，导致在干净语音上训练的ASR后端性能下降。因此，主流的鲁棒性ASR系统会在带噪语音上训练后端，以规避处理伪影问题。本研究提出将说话人分离前端与ASR后端的训练解耦，其中ASR后端仅在干净语音上训练。我们的解耦系统在Libri2Mix开发/测试集上取得了5.1%的词错误率（WER），显著优于其他多说话人ASR基线模型。在单通道和6通道SMS-WSJ数据集上，该系统分别取得了7.60%和5.74%的WER，达到了当前最优水平，进一步验证了其有效性。此外，在录制的LibriCSS数据集上，我们取得了2.92%的带说话人属性词错误率。这些当前最优结果表明，解耦说话人分离与识别是提升鲁棒性多说话人ASR性能的有效途径。
英文摘要：
Despite the tremendous success of automatic speech recognition (ASR) with the introduction of deep learning, its performance is still unsatisfactory in many real-world multi-talker scenarios. Speaker separation excels in separating individual talkers but, as a frontend, it introduces processing artifacts that degrade the ASR backend trained on clean speech. As a result, mainstream robust ASR systems train the backend on noisy speech to avoid processing artifacts. In this work, we propose to decouple the training of the speaker separation frontend and the ASR backend, with the latter trained on clean speech only. Our decoupled system achieves 5.1% word error rates (WER) on the Libri2Mix dev/test sets, significantly outperforming other multi-talker ASR baselines. Its effectiveness is also demonstrated with the state-of-the-art 7.60%/5.74% WERs on 1-ch and 6-ch SMS-WSJ. Furthermore, on recorded LibriCSS, we achieve the speaker-attributed WER of 2.92%. These state-of-the-art results suggest that decoupling speaker separation and recognition is an effective approach to elevate robust multi-talker ASR.
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。
