论文信息 - On modeling duration in context in speech recognition

On modeling duration in context in speech recognition

A clustering algorithm is introduced that allows clustering of HMM (hidden Markov models) models directly. This clustering algorithm determines the appropriate duration profile for a recognition unit. High-performance speaker-independent digit recognition on a studio-quality connected-digit database is demonstrated using this algorithm.<<ETX>>

Joseph Picone

[1] R. G. Leonard,et al. A database for speaker-independent digit recognition , 1984, ICASSP.

[2] Michael R. Anderberg,et al. Cluster Analysis for Applications , 1973 .

[3] Biing-Hwang Juang,et al. A model-based connected-digit recognition system using either hidden Markov models or templates , 1986 .

[4] G. Doddington,et al. Low rate speech coding using contour quantization , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5] G. Doddington,et al. The LPC trace as an HMM development tool , 1988 .

[6] Aaron E. Rosenberg,et al. Interactive clustering techniques for selecting speaker-independent reference templates for isolated word recognition , 1979 .