A novel algorithm for HMM word spotting performance evaluation and error analysis

A hidden Markov model (HMM) wordspotter is described. The emphasis is on the algorithms for HMM scoring and performance evaluation, which offer several advantages over those currently used. These advantages include the ability to: determine both the beginning and ending points of a spotted word, generate a smooth receiver operating characteristic (ROC) in a computationally efficient manner, and compare word spotters on the same task using a nonparametric significance test.<<ETX>>

[1]  L. R. Rabiner,et al.  On the application of vector quantization and hidden Markov models to speaker-independent, isolated word recognition , 1983, The Bell System Technical Journal.

[2]  Jeffrey Neil Marcus.  Word and subword modelling in a segment-based HMM word spotter using a data analytic approach , 1992 .

[3]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[4]  Richard Rose,et al.  A hidden Markov model based keyword recognition system , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[5]  Stephen Cox,et al.  Some statistical issues in the comparison of speech recognition algorithms , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[6]  W. Russell,et al.  Continuous hidden Markov modeling for speaker-independent word spotting , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[7]  Chin-Hui Lee,et al.  Automatic recognition of keywords in unconstrained speech using hidden Markov models , 1990, IEEE Trans. Acoust. Speech Signal Process..

[8]  R. Schwartz,et al.  A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[9]  Victor W. Zue,et al.  A variable duration acoustic segment HMM for hard-to-recognize words and phrases , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[10]  L. G. Miller,et al.  Improvements and applications for key word recognition using hidden Markov modeling techniques , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.