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

Output details

11 - Computer Science and Informatics

University of East Anglia

Return to search Previous output Next output
Output 35 of 70 in the submission
Article title

Language identification using visual features

Type
D - Journal article
Title of journal
IEEE Transactions on Audio, Speech, and Language Processing
Article number
-
Volume number
20
Issue number
7
First page of article
1936
ISSN of journal
1558-7924
Year of publication
2012
URL
-
Number of additional authors
1
Additional information

<22> We were the first to study identification of language using visual-only information, a technology useful as the initial stage of a visual speech processing system. This is challenging when multi-lingual speakers are used, as care is required to ensure that the reported performance of the recogniser is not due to, e.g. language familiarity of the speaker, which affects speaking rate. This extends our conference paper: Automatic Visual-Only Language Identification: A Preliminary Study (Proc. ICASSP 2009) which attracted worldwide media coverage when it was published, including New Scientist, Science Codex, Science Daily and others.

Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
0
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-