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

Output details

15 - General Engineering

University of Cambridge

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

Language model cross adaptation for LVCSR system combination

Type
D - Journal article
Title of journal
Computer Speech and Language
Article number
-
Volume number
27
Issue number
4
First page of article
928
ISSN of journal
0885-2308
Year of publication
2013
Number of additional authors
2
Additional information

The novel use of language model cross adaptation was included in the best performing AGILE system in the 2009 and 2010 evaluations of spoken Chinese translation in the DARPA GALE program. The AGILE Chinese speech recognition system uses the Cambridge developed component system with cross-adaptation to outputs generated by BBN and LIMSI. This paper is an extended version of the conference paper that won a best paper award at the Interspeech 2010 conference (top 3% of papers).

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
-