A unified beamforming and source separation model for static and dynamic human-robot interaction

Jorge Wuth; Rodrigo Mahu; Israel Cohen; Richard M. Stern; Néstor Becerra Yoma

doi:https://doi.org/10.1121/10.0025238

A unified beamforming and source separation model for static and dynamic human-robot interaction

Jorge Wuth, Rodrigo Mahu, Israel Cohen, Richard M. Stern, Néstor Becerra Yoma

Technion - Israel Institute of Technology

Research output: Contribution to journal › Article › peer-review

Abstract

This paper presents a unified model for combining beamforming and blind source separation (BSS). The validity of the model's assumptions is confirmed by recovering target speech information in noise accurately using Oracle information. Using real static human-robot interaction (HRI) data, the proposed combination of BSS with the minimum-variance distortionless response beamformer provides a greater signal-to-noise ratio (SNR) than previous parallel and cascade systems that combine BSS and beamforming. In the difficult-to-model HRI dynamic environment, the system provides a SNR gain that was 2.8 dB greater than the results obtained with the cascade combination, where the parallel combination is infeasible.

Original language	English
Article number	035203
Journal	JASA Express Letters
Volume	4
Issue number	3
DOIs	https://doi.org/10.1121/10.0025238
State	Published - 1 Mar 2024

All Science Journal Classification (ASJC) codes

Music
Arts and Humanities (miscellaneous)
Acoustics and Ultrasonics

Access to Document

https://doi.org/10.1121/10.0025238

Cite this

@article{9c6a52e113b34e5d934da7d465621b66,

title = "A unified beamforming and source separation model for static and dynamic human-robot interaction",

abstract = "This paper presents a unified model for combining beamforming and blind source separation (BSS). The validity of the model's assumptions is confirmed by recovering target speech information in noise accurately using Oracle information. Using real static human-robot interaction (HRI) data, the proposed combination of BSS with the minimum-variance distortionless response beamformer provides a greater signal-to-noise ratio (SNR) than previous parallel and cascade systems that combine BSS and beamforming. In the difficult-to-model HRI dynamic environment, the system provides a SNR gain that was 2.8 dB greater than the results obtained with the cascade combination, where the parallel combination is infeasible.",

author = "Jorge Wuth and Rodrigo Mahu and Israel Cohen and Stern, {Richard M.} and Yoma, {N{\'e}stor Becerra}",

note = "Publisher Copyright: {\textcopyright} 2024 Author(s).",

year = "2024",

month = mar,

day = "1",

doi = "https://doi.org/10.1121/10.0025238",

language = "الإنجليزيّة",

volume = "4",

journal = "JASA Express Letters",

issn = "2691-1191",

publisher = "American Institute of Physics",

number = "3",

}

TY - JOUR

T1 - A unified beamforming and source separation model for static and dynamic human-robot interaction

AU - Wuth, Jorge

AU - Mahu, Rodrigo

AU - Cohen, Israel

AU - Stern, Richard M.

AU - Yoma, Néstor Becerra

PY - 2024/3/1

Y1 - 2024/3/1

N2 - This paper presents a unified model for combining beamforming and blind source separation (BSS). The validity of the model's assumptions is confirmed by recovering target speech information in noise accurately using Oracle information. Using real static human-robot interaction (HRI) data, the proposed combination of BSS with the minimum-variance distortionless response beamformer provides a greater signal-to-noise ratio (SNR) than previous parallel and cascade systems that combine BSS and beamforming. In the difficult-to-model HRI dynamic environment, the system provides a SNR gain that was 2.8 dB greater than the results obtained with the cascade combination, where the parallel combination is infeasible.

AB - This paper presents a unified model for combining beamforming and blind source separation (BSS). The validity of the model's assumptions is confirmed by recovering target speech information in noise accurately using Oracle information. Using real static human-robot interaction (HRI) data, the proposed combination of BSS with the minimum-variance distortionless response beamformer provides a greater signal-to-noise ratio (SNR) than previous parallel and cascade systems that combine BSS and beamforming. In the difficult-to-model HRI dynamic environment, the system provides a SNR gain that was 2.8 dB greater than the results obtained with the cascade combination, where the parallel combination is infeasible.

UR - http://www.scopus.com/inward/record.url?scp=85186975349&partnerID=8YFLogxK

U2 - https://doi.org/10.1121/10.0025238

DO - https://doi.org/10.1121/10.0025238

M3 - مقالة

SN - 2691-1191

VL - 4

JO - JASA Express Letters

JF - JASA Express Letters

IS - 3

M1 - 035203

ER -

A unified beamforming and source separation model for static and dynamic human-robot interaction

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this