For the current REF see the REF 2021 website REF 2021 logo

Output details

13 - Electrical and Electronic Engineering, Metallurgy and Materials

University of Surrey

Return to search Previous output Next output
Output 0 of 0 in the submission
Article title

Use of bimodal coherence to resolve the permutation problem in convolutive BSS

Type
D - Journal article
Title of journal
Signal Processing
Article number
-
Volume number
92
Issue number
8
First page of article
1916
ISSN of journal
01651684
Year of publication
2012
URL
-
Number of additional authors
-
Additional information

This paper solves the problem of speech-on-speech audio mixtures in typical (reflective) acoustic conditions by using visual information about a speaker to help extract the relevant speech. This problem is a major obstacle in the wide-spread deployment of source separation techniques, and this process has the potential to improve the performance of speech technologies in applications including: biometric security, speech recognition/localisation/enhancement, surveillance, audio re-mastering and telecommunications.

Interdisciplinary
-
Cross-referral requested
-
Research group
None
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-