Title :
Speech recognition using dynamical model of speech production
Author_Institution :
NEC Corp., Miyamae-ku, Kawasaki, Japan
Abstract :
The model consists of an articulator and its control command sequences. The latter has linguistic information of speech and the former has the articulatory information which determines the transformation from linguistic intentions to speech signals. This separation allows the speech recognition model to be more controllable. It also provides new approaches to coarticulation modeling. The effectiveness of the proposed model was examined by speaker-independent letter recognition experiments.<>
Keywords :
controllability; learning (artificial intelligence); neural nets; physiological models; speech recognition; articulator; coarticulation modeling; control command sequences; dynamical model of speech production; effectiveness; linguistic intentions; speaker-independent letter recognition; speech recognition model; speech signals;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1993. ICASSP-93., 1993 IEEE International Conference on
Conference_Location :
Minneapolis, MN, USA
Print_ISBN :
0-7803-7402-9
DOI :
10.1109/ICASSP.1993.319291
