eess.AS - 2023-07-09

IANS: Intelligibility-aware Null-steering Beamforming for Dual-Microphone Arrays

  • paper_url: http://arxiv.org/abs/2307.04179
  • repo_url: None
  • paper_authors: Wen-Yuan Ting, Syu-Siang Wang, Yu Tsao, Borching Su
  • for: 提高杂音干扰 speech 的 intelligibility
  • methods: 使用 STOI-Net 智能预测模型,并结合 null-steering beamformer (NSBF) 生成一系列 beamformed 输出,以提高 speech 的 intelligibility
  • results: 实验结果表明,IANS 可以使用小型双麦克麦array 生成有 inteligibility 提高的 signal,与 known DOAs 的 null-steering beamformers 的结果相似
    Abstract Beamforming techniques are popular in speech-related applications due to their effective spatial filtering capabilities. Nonetheless, conventional beamforming techniques generally depend heavily on either the target's direction-of-arrival (DOA), relative transfer function (RTF) or covariance matrix. This paper presents a new approach, the intelligibility-aware null-steering (IANS) beamforming framework, which uses the STOI-Net intelligibility prediction model to improve speech intelligibility without prior knowledge of the speech signal parameters mentioned earlier. The IANS framework combines a null-steering beamformer (NSBF) to generate a set of beamformed outputs, and STOI-Net, to determine the optimal result. Experimental results indicate that IANS can produce intelligibility-enhanced signals using a small dual-microphone array. The results are comparable to those obtained by null-steering beamformers with given knowledge of DOAs.
    摘要 <> simultrare il testo in Cinese semplificato.<>Beamforming 技术在语音相关应用中很受欢迎,因为它们可以提供有效的空间滤波功能。然而,传统的 beamforming 技术通常具有依赖于目标的方向 arrival (DOA)、相对转移函数 (RTF) 或 covariance matrix 的缺点。这篇论文提出了一种新的方法——智能可识别 beamforming 框架 (IANS),它使用 STOI-Net 智能可识别模型来提高语音可识别性,无需先知道语音信号参数。IANS 框架将 null-steering beamformer (NSBF) 与 STOI-Net 结合,生成一组扩展出的输出,并使用 STOI-Net 确定最佳结果。实验结果表明,IANS 可以使用小型双 микрофон阵列生成具有可识别性的信号,与 null-steering beamformers 的结果相似。