Robust frame-level speaker localization guided by multi-channel speech enhancement and inter-channel phase-difference losses

计算机科学 频道(广播) 语音识别 麦克风阵列 混响 多输入多输出 帧(网络) 算法 话筒 声学 电信 物理 声压
作者
Shanmukha Srinivas Battula,Hassan Taherian,Ashutosh Pandey,Daniel Fu Keung Wong,Buye Xu,DeLiang Wang
出处
期刊:Journal of the Acoustical Society of America [Acoustical Society of America]
卷期号:158 (1): 790-800 被引量:1
标识
DOI:10.1121/10.0038627
摘要

In the presence of room reverberation and background noise, the performance of frame-level speaker localization is severely limited. To address this challenge, this study performs multi-channel speech enhancement based on complex spectral mapping (CSM), followed by direction-of-arrival (DOA) estimation using weighted generalized cross-correlation with phase transform (GCC-PHAT). The proposed approach differs from prevailing deep learning methods that operate on multi-channel inputs directly for speaker localization. This study initially investigates multi-input single-output (MISO) based speech enhancement models with two loss functions and then extends to multi-input multi-output (MIMO) based modeling for conceptual and computational efficiency. The results demonstrate that the phase estimates obtained from CSM models are reliable for frame-level DOA estimation and MIMO systems outperform MISO systems. In addition, the study proposes new multi-channel loss functions for MIMO systems that incorporate phase differences in order to better preserve inter-channel phase relations, which is key to accurate sound localization. Systematic evaluations with multiple microphone array geometries using both simulated and recorded room impulse responses, as well as real recordings, demonstrate that the proposed model yields excellent frame-level speaker localization results in reverberant and noisy environments and outperforms related methods by a large margin, even surpassing their utterance-level results.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
Sxw完成签到,获得积分10
刚刚
刚刚
糖霜果子完成签到,获得积分10
1秒前
1秒前
勤奋一一发布了新的文献求助10
1秒前
Jasper的应助被cc采纳,获得10
2秒前
sky发布了新的文献求助10
2秒前
英姑的应助被陈懿采纳,获得10
2秒前
2秒前
lay完成签到,获得积分10
2秒前
Hamed22发布了新的文献求助10
3秒前
3秒前
科研通AI6.2的应助被研友_ZragOn采纳,获得10
3秒前
彭于晏的应助被27采纳,获得10
4秒前
4秒前
4秒前
null的应助被LLL采纳,获得10
4秒前
5秒前
lay发布了新的文献求助10
5秒前
6秒前
zzxiao发布了新的文献求助10
6秒前
taoge发布了新的文献求助10
7秒前
领导范儿的应助被Sxw采纳,获得10
7秒前
pluto的应助被菲菲采纳,获得10
8秒前
9秒前
zxk完成签到,获得积分10
9秒前
9秒前
TCA发布了新的文献求助10
10秒前
迷你的飞莲完成签到,获得积分10
11秒前
11秒前
13秒前
13秒前
小困包发布了新的文献求助10
13秒前
15秒前
15秒前
15秒前
16秒前
叶子发布了新的文献求助10
16秒前
18秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Markov Decision Processes and Reinforcement Learning 700
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8171069
求助须知:如何正确求助?哪些是违规求助? 9563791
关于积分的说明 21772202
捐赠科研通 7762628
什么是DOI,文献DOI怎么找? 3430786
关于科研通互助平台的介绍 2554696
邀请新用户注册赠送积分活动 2475672