Title :
Training of across-word phoneme models for large vocabulary continuous speech recognition
Author :
Sixtus, Achim ; Ney, Hermann
Author_Institution :
Lehrstuhl für Informatik VI, RWTH Aachen, University of Technology, 52056, Germany
Abstract :
Today´s speech recognition systems use across-word context dependent phoneme models to capture coarticulation across word boundaries. While there are several publications about the organization of across-word model search, there are hardly any descriptions about the training of across-word models.
Keywords :
Automata; Computational modeling; Context; Hidden Markov models; Speech recognition; Training; Variable speed drives;
Conference_Titel :
Acoustics, Speech, and Signal Processing (ICASSP), 2002 IEEE International Conference on
Conference_Location :
Orlando, FL, USA
Print_ISBN :
0-7803-7402-9
DOI :
10.1109/ICASSP.2002.5743872
