arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.06458eess.AScs.SD
收藏

基于多分辨率位置训练的多通道连续语音分离

Multi-resolution location-based training for multi-channel continuous speech separation

Department of Computer Science and Engineering, The Ohio State University, USA(美国俄亥俄州立大学计算机科学与工程系);Center for Cognitive and Brain Sciences, The Ohio State University, USA(美国俄亥俄州立大学认知与脑科学中心)

Hassan Taherian, DeLiang Wang

摘要:

当多说话人语音重叠时,自动语音识别(ASR)系统的性能会严重下降。在会议环境中,通常执行语音分离以提高ASR系统的鲁棒性。最近,基于位置的训练(LBT)被提出作为一种新的训练标准,用于多通道说话人无关的说话人分离。假设固定的阵列几何形状,LBT在完全重叠的话语和匹配的混响条件下优于广泛使用的置换不变训练。本文将LBT扩展到会话多声道说话人分离。我们引入多分辨率LBT来估计从低到高的时间和频率分辨率的复杂频谱图。使用多分辨率LBT,卷积核是基于物理空间中的扬声器位置一致地分配的。评估结果表明,多分辨率LBT在记录的LibriCSS语料库上始终优于其他竞争方法。

英文摘要:

The performance of automatic speech recognition (ASR) systems severely degrades when multi-talker speech overlap occurs. In meeting environments, speech separation is typically performed to improve the robustness of ASR systems. Recently, location-based training (LBT) was proposed as a new training criterion for multi-channel talker-independent speaker separation. Assuming fixed array geometry, LBT outperforms widely-used permutation-invariant training in fully overlapped utterances and matched reverberant conditions. This paper extends LBT to conversational multi-channel speaker separation. We introduce multi-resolution LBT to estimate the complex spectrograms from low to high time and frequency resolutions. With multi-resolution LBT, convolutional kernels are assigned consistently based on speaker locations in physical space. Evaluation results show that multi-resolution LBT consistently outperforms other competitive methods on the recorded LibriCSS corpus.

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。

↑