DocumentCode :
431345
Title :
A Study on Knowledge Source Integration for Candidate Rescoring in Automatic Speech Recognition
Author :
Li, Jinyu ; Tsao, Yu ; Lee, Chin-Hui
Author_Institution :
Sch. of Electr. & Comput. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
Volume :
1
fYear :
2005
fDate :
March 18-23, 2005
Firstpage :
837
Lastpage :
840
Keywords :
acoustic signal processing; hidden Markov models; knowledge based systems; neural nets; signal classification; speech recognition; HMM-based speech recognizers; LVSCR; acoustic phonetic knowledge sources; articulation manners; articulation places; automatic speech recognition; candidate rescoring; candidate strings; context-dependent phone models; context-independent phone models; continuous phone recognition; knowledge source integration; large vocabulary continuous speech recognition; lattice rescoring; neural network based classifiers; Artificial neural networks; Automatic speech recognition; Context modeling; Databases; Feature extraction; Hidden Markov models; Lattices; Neural networks; 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.2005.1415244
Filename :
1415244
Link To Document :
بازگشت