Title :
Variation of features of interframe dependent HMM for speech recognition
Author :
Hanna, P. ; Harte, N. ; Ming, J. ; Vaseghi, S. ; Smith, F.J.
Author_Institution :
Sch. of Electr. Eng. & Comput. Sci., Queen´´s Univ., Belfast, UK
fDate :
4/30/1998 12:00:00 AM
Abstract :
The effects are explored of using different dynamic features in conjunction with an HMM that permits a dependency on both preceeding and succeeding frames. In particular, features which capture dynamic information are varied in the interframe dependent HMM. A recognition accuracy of 93.9% for the Connex speaker-independent E-set was obtained using tied states
Keywords :
hidden Markov models; speech recognition; Connex speaker-independent E-set; dynamic features; interframe dependent HMM; speech recognition; tied states;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19980640