DocumentCode :
431392
Title :
A New ASR Evaluation Measure and Minimum Bayes-Risk Decoding for Open-domain Speech Understanding
Author :
Nanjo, H. ; Kawahara, Toshio
Volume :
1
fYear :
2005
fDate :
March 18-23, 2005
Firstpage :
1053
Lastpage :
1056
Keywords :
Bayes methods; decoding; error statistics; information retrieval; pattern classification; signal classification; speech recognition; ASR evaluation measure; WER; information retrieval; key sentence indexing; keyword; minimum Bayes-risk decoding; open-domain speech understanding; speech recognition; weighted keyword error rate; word error rate; Automatic speech recognition; Decoding; Error analysis; Information retrieval; Machine assisted indexing; Natural languages; Speech analysis; Speech processing; Speech recognition; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
0-7803-8874-7
Type :
conf
DOI :
10.1109/ICASSP.2005.1415298
Filename :
1415298
Link To Document :
بازگشت