Saved in:
Bibliographic Details
Main Authors: Yang, Yang, Sung, George, Shih, Shao-Fu, Erdogan, Hakan, Lee, Chehung, Grundmann, Matthias
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.08864
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917569415348224
author Yang, Yang
Sung, George
Shih, Shao-Fu
Erdogan, Hakan
Lee, Chehung
Grundmann, Matthias
author_facet Yang, Yang
Sung, George
Shih, Shao-Fu
Erdogan, Hakan
Lee, Chehung
Grundmann, Matthias
contents We propose a neural network model that can separate target speech sources from interfering sources at different angular regions using two microphones. The model is trained with simulated room impulse responses (RIRs) using omni-directional microphones without needing to collect real RIRs. By relying on specific angular regions and multiple room simulations, the model utilizes consistent time difference of arrival (TDOA) cues, or what we call delay contrast, to separate target and interference sources while remaining robust in various reverberation environments. We demonstrate the model is not only generalizable to a commercially available device with a slightly different microphone geometry, but also outperforms our previous work which uses one additional microphone on the same device. The model runs in real-time on-device and is suitable for low-latency streaming applications such as telephony and video conferencing.
format Preprint
id arxiv_https___arxiv_org_abs_2401_08864
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Binaural Angular Separation Network
Yang, Yang
Sung, George
Shih, Shao-Fu
Erdogan, Hakan
Lee, Chehung
Grundmann, Matthias
Audio and Speech Processing
Machine Learning
Sound
We propose a neural network model that can separate target speech sources from interfering sources at different angular regions using two microphones. The model is trained with simulated room impulse responses (RIRs) using omni-directional microphones without needing to collect real RIRs. By relying on specific angular regions and multiple room simulations, the model utilizes consistent time difference of arrival (TDOA) cues, or what we call delay contrast, to separate target and interference sources while remaining robust in various reverberation environments. We demonstrate the model is not only generalizable to a commercially available device with a slightly different microphone geometry, but also outperforms our previous work which uses one additional microphone on the same device. The model runs in real-time on-device and is suitable for low-latency streaming applications such as telephony and video conferencing.
title Binaural Angular Separation Network
topic Audio and Speech Processing
Machine Learning
Sound
url https://arxiv.org/abs/2401.08864