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 2407.04879cs.SDeess.AS
收藏

全神经低延迟定向语音提取

All Neural Low-latency Directional Speech Extraction

Meta Platforms Inc.(元平台公司)

Ashutosh Pandey, Sanha Lee, Juan Azcarreta, Daniel Wong, Buye Xu

AI总结:

本文提出一种全神经低延迟定向语音提取模型,通过从零训练DOA嵌入并与循环神经网络融合,实现高帧率下对动态声学场景的快速适应和鲁棒提取。

摘要:

我们提出了一种新颖的全神经模型,用于低延迟定向语音提取。该模型使用来自预定义空间网格的到达方向(DOA)嵌入,这些嵌入经过变换并融合到基于循环神经网络的语音提取模型中。这一过程使模型能够有效地从指定的DOA提取语音。与以往依赖手工设计定向特征的方法不同,所提出的模型利用语音增强损失从头训练DOA嵌入,使其适用于低延迟场景。此外,该模型以高帧率运行,在每个输入帧中接收DOA,从而具备在高度动态的真实场景中快速适应变化场景的能力。我们提供了广泛的评估,以证明该模型在定向语音提取中的有效性、对DOA失配的鲁棒性,以及快速适应DOA突变的能力。

英文摘要:

We introduce a novel all neural model for low-latency directional speech extraction. The model uses direction of arrival (DOA) embeddings from a predefined spatial grid, which are transformed and fused into a recurrent neural network based speech extraction model. This process enables the model to effectively extract speech from a specified DOA. Unlike previous methods that relied on hand-crafted directional features, the proposed model trains DOA embeddings from scratch using speech enhancement loss, making it suitable for low-latency scenarios. Additionally, it operates at a high frame rate, taking in DOA with each input frame, which brings in the capability of quickly adapting to changing scene in highly dynamic real-world scenarios. We provide extensive evaluation to demonstrate the model's efficacy in directional speech extraction, robustness to DOA mismatch, and its capability to quickly adapt to abrupt changes in DOA.

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。

↑