Target Speaker Localization Based on the Complex Watson Mixture Model and Time-Frequency Selection Neural Network

Author:

Wang Ziteng,Li Junfeng,Yan Yonghong

Abstract

Common sound source localization algorithms focus on localizing all the active sources in the environment. While the source identities are generally unknown, retrieving the location of a speaker of interest requires extra effort. This paper addresses the problem of localizing a speaker of interest from a novel perspective by first performing time-frequency selection before localization. The speaker of interest, namely the target speaker, is assumed to be sparsely active in the signal spectra. The target speaker-dominant time-frequency regions are separated by a speaker-aware Long Short-Term Memory (LSTM) neural network, and they are sufficient to determine the Direction of Arrival (DoA) of the target speaker. Speaker-awareness is achieved by utilizing a short target utterance to adapt the hidden layer outputs of the neural network. The instantaneous DoA estimator is based on the probabilistic complex Watson Mixture Model (cWMM), and a weighted maximum likelihood estimation of the model parameters is accordingly derived. Simulative experiments show that the proposed algorithm works well in various noisy conditions and remains robust when the signal-to-noise ratio is low and when a competing speaker exists.

Funder

National Natural Science Foundation of China

Publisher

MDPI AG

Subject

Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. LOCSELECT: Target Speaker Localization with an Auditory Selective Hearing Mechanism;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. A DNN Based Normalized Time-Frequency Weighted Criterion for Robust Wideband DoA Estimation;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

3. GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

4. A stacked self-attention network for two-dimensional direction-of-arrival estimation in hands-free speech communication;The Journal of the Acoustical Society of America;2022-12

5. Sound source localization for auditory perception of a humanoid robot using deep neural networks;Neural Computing and Applications;2022-11-29

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3