In this section
@inproceedings{Tokala:2022:10.1109/IWAENC53105.2022.9914744,
author = {Tokala, V and Brookes, M and Naylor, P},
doi = {10.1109/IWAENC53105.2022.9914744},
pages = {1--5},
publisher = {IEEE},
title = {Binaural speech enhancement using STOI-optimal masks},
url = {http://dx.doi.org/10.1109/IWAENC53105.2022.9914744},
year = {2022}
}
TY - CPAPER
AB - STOI-optimal masking has been previously proposed and developed for single-channel speech enhancement. In this paper, we consider the extension to the task of binaural speech enhancement in which the spatial information is known to be important to speech understanding and therefore should bepreserved by the enhancement processing. Masks are estimated for each of the binaural channels individually and a ‘better-ear listening’ mask is computed by choosing the maximum of the two masks. The estimated mask is used to supply probability information about the speech presence in eachtime-frequency bin to an Optimally-modified Log Spectral Amplitude (OM-LSA) enhancer. We show that using the pro-posed method for binaural signals with a directional noise not only improves the SNR of the noisy signal but also preserves the binaural cues and intelligibility.
AU - Tokala,V
AU - Brookes,M
AU - Naylor,P
DO - 10.1109/IWAENC53105.2022.9914744
EP - 5
PB - IEEE
PY - 2022///
SP - 1
TI - Binaural speech enhancement using STOI-optimal masks
UR - http://dx.doi.org/10.1109/IWAENC53105.2022.9914744
UR - https://ieeexplore.ieee.org/document/9914744
UR - http://hdl.handle.net/10044/1/100080
ER -
Speech and Audio Processing Lab
CSP Group, EEE Department
Imperial College London
Exhibition Road, London, SW7 2AZ, United Kingdom