GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios

Guanjun Li; Wei Xue; Wenju Liu; Jiangyan Yi; Jianhua Tao

doi:10.1109/ICASSP49357.2023.10095551

GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios

Guanjun Li^*
, Wei Xue
, Wenju Liu
, Jiangyan Yi
, Jianhua Tao

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

5 Citations (Scopus)

Abstract

Existing noise-robust and reverberant-robust localization algorithms fail to localize the target speaker when interfering speakers are present. In this paper, we address the problem of localizing only the target speaker in multi-speaker scenarios and propose a target speaker localization algorithm, called GCC-speaker. Specifically, we modify the weighting of the generalized cross-correlation with phase transform (GCC-PHAT) algorithm and propose an optimal speaker-dependent weighting based on a novel localization-related loss function and data-driven training. The speaker-dependent weighting is responsible for guiding the GCC algorithm to obtain the optimal target speaker localization results. As for the loss function, we constrain the estimated GCC angular spectrum and the estimated direction of arrival (DOA) to be close to their ground truth values, respectively. The experimental results show the superiority of GCC-speaker compared to the existing target speaker localization algorithms for different signal-to-interference ratios, reverberation times and array geometries.

Original language	English
Title of host publication	ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
Publisher	IEEE
Pages	1-5
Number of pages	5
ISBN (Electronic)	9781728163277
ISBN (Print)	9781728163284
DOIs	https://doi.org/10.1109/ICASSP49357.2023.10095551
Publication status	Published - Jun 2023
Event	48th IEEE International Conference on Acoustics, Speech and Signal Processing - Rodos Palace Luxury Convention Resort, Rhodes Island, Greece Duration: 4 Jun 2023 → 10 Jun 2023 https://ieeexplore.ieee.org/xpl/conhome/10094559/proceeding (Conference proceeding) https://2023.ieeeicassp.org/ (Conference website) https://2023.ieeeicassp.org/program-at-a-glance/ (Conference program)

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2023-June
ISSN (Print)	1520-6149
ISSN (Electronic)	2379-190X

Conference

Conference	48th IEEE International Conference on Acoustics, Speech and Signal Processing
Abbreviated title	ICASSP 2023
Country/Territory	Greece
City	Rhodes Island
Period	4/06/23 → 10/06/23
Internet address	https://ieeexplore.ieee.org/xpl/conhome/10094559/proceeding (Conference proceeding) https://2023.ieeeicassp.org/ (Conference website) https://2023.ieeeicassp.org/program-at-a-glance/ (Conference program)

User-Defined Keywords

generalized cross-correlation
speaker-dependent weighting
Target speaker localization

Access to Document

10.1109/ICASSP49357.2023.10095551

Fingerprint

Dive into the research topics of 'GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios'. Together they form a unique fingerprint.

Cite this

Li, G., Xue, W., Liu, W., Yi, J., & Tao, J. (2023). GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings (pp. 1-5). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2023-June). IEEE. https://doi.org/10.1109/ICASSP49357.2023.10095551

Li, Guanjun ; Xue, Wei ; Liu, Wenju et al. / GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios : Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. IEEE, 2023. pp. 1-5 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{bdcd8751e3d24c988612bdd87651eb05,

title = "GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios",

abstract = "Existing noise-robust and reverberant-robust localization algorithms fail to localize the target speaker when interfering speakers are present. In this paper, we address the problem of localizing only the target speaker in multi-speaker scenarios and propose a target speaker localization algorithm, called GCC-speaker. Specifically, we modify the weighting of the generalized cross-correlation with phase transform (GCC-PHAT) algorithm and propose an optimal speaker-dependent weighting based on a novel localization-related loss function and data-driven training. The speaker-dependent weighting is responsible for guiding the GCC algorithm to obtain the optimal target speaker localization results. As for the loss function, we constrain the estimated GCC angular spectrum and the estimated direction of arrival (DOA) to be close to their ground truth values, respectively. The experimental results show the superiority of GCC-speaker compared to the existing target speaker localization algorithms for different signal-to-interference ratios, reverberation times and array geometries.",

keywords = "generalized cross-correlation, speaker-dependent weighting, Target speaker localization",

author = "Guanjun Li and Wei Xue and Wenju Liu and Jiangyan Yi and Jianhua Tao",

note = "This work is supported by the National Key Research and Development Plan of China (No.2020AAA0140003), the National Natural Science Foundation of China (NSFC) (No.U21B2010, No.61831022, No.62101553, No.61971419, No.62006223, No.62276259, No.62201572, No.62206278), Beijing Municipal Science\&Technology Commission,Administrative Commission of Zhongguancun Science Park(No.Z211100004821013), Open Research Projects of Zhejiang Lab (NO. 2021KH0AB06). Publisher Copyright: {\textcopyright} 2023 IEEE.; 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",

year = "2023",

month = jun,

doi = "10.1109/ICASSP49357.2023.10095551",

language = "English",

isbn = "9781728163284",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "IEEE",

pages = "1--5",

booktitle = "ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings",

address = "United States",

url = "https://ieeexplore.ieee.org/xpl/conhome/10094559/proceeding, https://2023.ieeeicassp.org/, https://2023.ieeeicassp.org/program-at-a-glance/",

}

Li, G, Xue, W, Liu, W, Yi, J & Tao, J 2023, GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2023-June, IEEE, pp. 1-5, 48th IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10095551

GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios. / Li, Guanjun; Xue, Wei; Liu, Wenju et al.
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. IEEE, 2023. p. 1-5 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2023-June).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios

T2 - 48th IEEE International Conference on Acoustics, Speech and Signal Processing

AU - Li, Guanjun

AU - Xue, Wei

AU - Liu, Wenju

AU - Yi, Jiangyan

AU - Tao, Jianhua

N1 - This work is supported by the National Key Research and Development Plan of China (No.2020AAA0140003), the National Natural Science Foundation of China (NSFC) (No.U21B2010, No.61831022, No.62101553, No.61971419, No.62006223, No.62276259, No.62201572, No.62206278), Beijing Municipal Science&Technology Commission,Administrative Commission of Zhongguancun Science Park(No.Z211100004821013), Open Research Projects of Zhejiang Lab (NO. 2021KH0AB06). Publisher Copyright: © 2023 IEEE.

PY - 2023/6

Y1 - 2023/6

N2 - Existing noise-robust and reverberant-robust localization algorithms fail to localize the target speaker when interfering speakers are present. In this paper, we address the problem of localizing only the target speaker in multi-speaker scenarios and propose a target speaker localization algorithm, called GCC-speaker. Specifically, we modify the weighting of the generalized cross-correlation with phase transform (GCC-PHAT) algorithm and propose an optimal speaker-dependent weighting based on a novel localization-related loss function and data-driven training. The speaker-dependent weighting is responsible for guiding the GCC algorithm to obtain the optimal target speaker localization results. As for the loss function, we constrain the estimated GCC angular spectrum and the estimated direction of arrival (DOA) to be close to their ground truth values, respectively. The experimental results show the superiority of GCC-speaker compared to the existing target speaker localization algorithms for different signal-to-interference ratios, reverberation times and array geometries.

AB - Existing noise-robust and reverberant-robust localization algorithms fail to localize the target speaker when interfering speakers are present. In this paper, we address the problem of localizing only the target speaker in multi-speaker scenarios and propose a target speaker localization algorithm, called GCC-speaker. Specifically, we modify the weighting of the generalized cross-correlation with phase transform (GCC-PHAT) algorithm and propose an optimal speaker-dependent weighting based on a novel localization-related loss function and data-driven training. The speaker-dependent weighting is responsible for guiding the GCC algorithm to obtain the optimal target speaker localization results. As for the loss function, we constrain the estimated GCC angular spectrum and the estimated direction of arrival (DOA) to be close to their ground truth values, respectively. The experimental results show the superiority of GCC-speaker compared to the existing target speaker localization algorithms for different signal-to-interference ratios, reverberation times and array geometries.

KW - generalized cross-correlation

KW - speaker-dependent weighting

KW - Target speaker localization

UR - https://www.scopus.com/pages/publications/85177572050

U2 - 10.1109/ICASSP49357.2023.10095551

DO - 10.1109/ICASSP49357.2023.10095551

M3 - Conference proceeding

AN - SCOPUS:85177572050

SN - 9781728163284

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1

EP - 5

BT - ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings

PB - IEEE

Y2 - 4 June 2023 through 10 June 2023

ER -

Li G, Xue W, Liu W, Yi J, Tao J. GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. IEEE. 2023. p. 1-5. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP49357.2023.10095551

GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this