Title :
Context-dependent acoustic modeling using graphemes for large vocabulary speech recognition
Author :
Kanthak, S. ; Ney, H.
Author_Institution :
Lehrstuhl für Informatik VI, Computer Science Department, RWTH Aachen - University of Technology, 52056, Germany
Abstract :
In this paper we propose to use a decision tree based on graphemic acoustic sub-word units together with phonetic questions. We also show that automatic question generation can be used to completely eliminate any manual effort.
Keywords :
Europe; Hidden Markov models; Ions; Pipelines; Speech; Speech recognition; Vocabulary;
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.2002.5743871
