Title :
Adaptive Training Using Simple Target Models
Author :
Stemmer, Georg ; Brugnara, Fabio ; Giuliani, Diego
Author_Institution :
Centro per la Ricerca Scientifica a Tecnologia, ITC-irst, Povo, Italy
fDate :
March 18-23, 2005
Keywords :
Gaussian distribution; adaptive signal processing; hidden Markov models; maximum likelihood estimation; regression analysis; speech recognition; CMLLR; GMM target models; Gaussian mixture model; HMM; WER reduction; acoustic models; acoustic normalization; adaptive training; channel variability; constrained maximum likelihood linear regression; environment variability; phonetically irrelevant acoustic variability reduction; speaker variability; text-independent procedure; Acoustic testing; Contracts; Hidden Markov models; Loudspeakers; Maximum likelihood linear regression; Radio broadcasting; Radio network; Speech recognition; TV broadcasting; Target recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415284
