DocumentCode :
3540140
Title :
On the performance of ITU-T G.723.1 and AMR-NB codecs for large vocabulary distributed speech recognition in Brazilian Portuguese
Author :
De Alencar, Vladimir Fabregas Surigué ; Alcaim, Abraham
Author_Institution :
PUC/RIO, CETUC, Rio de Janeiro, Brazil
fYear :
2009
fDate :
4-6 Aug. 2009
Firstpage :
693
Lastpage :
697
Abstract :
In this paper, we present the accuracy for large vocabulary distributed continuous speech recognition systems over ITU-T G.723.1 and AMRNB speech codecs. Experiments were conducted using LPC and LSF-derived speech recognition features, CDHMM acoustic models, triphone units and trigram language models for the Brazilian Portuguese.
Keywords :
linear predictive coding; natural languages; speech codecs; speech coding; speech recognition; vocabulary; AMR-NB codecs; Brazilian Portuguese; CDHMM acoustic model; ITU-T G.723.1; LPC; LSF-derived speech recognition; large vocabulary distributed speech recognition; linear predictive coding; triphone units; Automatic speech recognition; Decoding; Feature extraction; GSM; IP networks; Interpolation; Linear predictive coding; Speech codecs; Speech recognition; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Applications of Digital Information and Web Technologies, 2009. ICADIWT '09. Second International Conference on the
Conference_Location :
London
Print_ISBN :
978-1-4244-4456-4
Electronic_ISBN :
978-1-4244-4457-1
Type :
conf
DOI :
10.1109/ICADIWT.2009.5273968
Filename :
5273968
Link To Document :
بازگشت