Multi-Speaker Direction of Arrival Estimation using SRP-PHAT Algorithm with a Weighted Histogram

2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE) Pub Date : 2018-12-01 DOI:10.1109/ICSEE.2018.8646206

E. Hadad, S. Gannot

{"title":"Multi-Speaker Direction of Arrival Estimation using SRP-PHAT Algorithm with a Weighted Histogram","authors":"E. Hadad, S. Gannot","doi":"10.1109/ICSEE.2018.8646206","DOIUrl":null,"url":null,"abstract":"A direction of arrival (DOA) estimator for concurrent speakers in a reverberant environment is presented. The DOA estimation task is formulated in the short-time Fourier transform (STFT) in two stages. In the first stage, a single narrow-band DOA per time-frequency (T-F) is selected, since the speech sources are assumed to exhibit disjoint activity in the STFT domain. The narrow-band DOA is obtained as the maximum of the narrow-band steered response power phase transform (SRP-PHAT) localization spectrum at that T-F bin. In addition, for each narrow-band DOA, a quality measure is calculated, which provides the confidence in the estimated decision. In the second stage, the wide-band localization spectrum is calculated using a weighted histogram of the narrow-band DOAs with the quality measures as weight. Finally, the wide-band DOA estimation is obtained by selecting the peaks in the wide-band localization spectrum. The results of our experimental study demonstrate the benefit of the proposed algorithm as compared to the wide-band SRP-PHAT algorithm in a reverberant environment.","PeriodicalId":254455,"journal":{"name":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSEE.2018.8646206","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 6

Abstract

A direction of arrival (DOA) estimator for concurrent speakers in a reverberant environment is presented. The DOA estimation task is formulated in the short-time Fourier transform (STFT) in two stages. In the first stage, a single narrow-band DOA per time-frequency (T-F) is selected, since the speech sources are assumed to exhibit disjoint activity in the STFT domain. The narrow-band DOA is obtained as the maximum of the narrow-band steered response power phase transform (SRP-PHAT) localization spectrum at that T-F bin. In addition, for each narrow-band DOA, a quality measure is calculated, which provides the confidence in the estimated decision. In the second stage, the wide-band localization spectrum is calculated using a weighted histogram of the narrow-band DOAs with the quality measures as weight. Finally, the wide-band DOA estimation is obtained by selecting the peaks in the wide-band localization spectrum. The results of our experimental study demonstrate the benefit of the proposed algorithm as compared to the wide-band SRP-PHAT algorithm in a reverberant environment.

查看原文本刊更多论文

加权直方图SRP-PHAT算法的多说话人到达方向估计

提出了一种混响环境下并发扬声器到达方向估计方法。在短时傅里叶变换(STFT)中，DOA估计任务分为两个阶段。在第一阶段，选择单个窄带DOA /时频(T-F)，因为假设语音源在STFT域中表现出不接合的活动。窄带DOA是窄带导向响应功率相位变换(SRP-PHAT)定位谱在该T-F帧处的最大值。此外，对于每个窄带DOA，计算了一个质量度量，为估计决策提供了置信度。在第二阶段，使用以质量度量为权重的窄带doa加权直方图计算宽带定位谱。最后，通过选取宽带定位谱中的峰值，得到宽带DOA估计。我们的实验研究结果表明，与宽带SRP-PHAT算法相比，该算法在混响环境中具有优势。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2018 IEEE International Conference on the Science of Electrical Engineering in Israel (ICSEE)

自引率

0.00%

发文量