N. Cahill, R. Cooney, K. Humphreys, and R. Lawlor, “Speech Source Enhancement using a Modified ADRess Algorithm for Applications in Mobile Communications,” in Proc. AES Convention 121, Oct. 2006, pp. 6961:1-10. [Online]. Available: https://aes.org/publications/elibrary-page/?id=13795
Cahill N, Cooney R, Humphreys K, Lawlor R. Speech Source Enhancement using a Modified ADRess Algorithm for Applications in Mobile Communications. In: AES Convention 121. Audio Engineering Society; 2006.pp. 6961:1-10. Available from: https://aes.org/publications/elibrary-page/?id=13795
@inproceedings{Cahill2006_13795,
author = {Cahill, Niall and Cooney, Rory and Humphreys, Kenneth and Lawlor, Robert},
title = {{Speech Source Enhancement using a Modified ADRess Algorithm for Applications in Mobile Communications}},
booktitle = {AES Convention 121},
pages = {6961:1-10},
url = {https://aes.org/publications/elibrary-page/?id=13795},
year = {2006},
month = oct,
publisher = {Audio Engineering Society},
address = {San Francisco}
}
TY - CPAPER
TI - Speech Source Enhancement using a Modified ADRess Algorithm for Applications in Mobile Communications
AU - Cahill, Niall
AU - Cooney, Rory
AU - Humphreys, Kenneth
AU - Lawlor, Robert
T2 - AES Convention 121
SP - 1
EP - 10
M1 - Paper 6961
PY - 2006
DA - 2006/10/06
UR - https://aes.org/publications/elibrary-page/?id=13795
PB - Audio Engineering Society
CY - San Francisco
LA - en
AB - An approach to refine and adapt an existing music sound source separation algorithm to speech enhancement is presented. The existing algorithm has the capability to extract music sources from stereo recordings using the position of the sources in the stereo field. Described in this paper is the ability of a modified Azimuth Discrimination and Resynthesis algorithm (m-ADRess) to enhance speech in the presence of noise using a two-microphone array. Also proposed is a novel extension to the algorithm, which enables further noise removal from speech based on elevation angle of arrival. Objective measures and an informal listening test of processed speech show the suitability of m-ADRess for cleaning noisy speech mixtures in an anechoic environment.
ER -