From HMMS to Segment Models: Stochastic Modeling for CSR

@inproceedings{Ostendorf1996FromHT,
  title={From HMMS to Segment Models: Stochastic Modeling for CSR},
  author={Mari Ostendorf},
  year={1996}
}
In recent years, several alternative models have been proposed to address some of the shortcomings of the hidden Markov model (HMM), currently the most popular approach to speech recognition. Many of these models, which attempt to represent trends or correlation of observations over time, can broadly be classified as segment models. This chapter describes a general probabilistic framework for segment models, including HMMs as a special case, giving options for modeling assumptions in terms of… Expand
27 Citations
A combined model of statics-dynamics of speech optimized using maximum mutual information
  • 1
  • PDF
Point process models for event-based speech recognition
  • 19
  • PDF
Multi-rate and variable-rate modeling of speech at phone and syllable time scales [speech recognition applications]
  • Ö. Çetin, Mari Ostendorf
  • Computer Science
  • Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.
  • 2005
  • 9
  • PDF
Speech trajectory discrimination using the minimum classification error learning
  • 61
  • PDF
Recognition method with parametric trajectory generated from mixture distribution HMMs
  • 8
Computational Models for Speech Production
  • 63
  • PDF
A phone recognizer helps to recognize words better
  • 7
  • PDF
An extension of the state-observation dependency in partly hidden Markov models and its application to continuous speech recognition
...
1
2
3
...

References

SHOWING 1-10 OF 51 REFERENCES
A segmental HMM for speech pattern modelling
  • M. Russell
  • Computer Science
  • 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1993
  • 69
Stochastic trajectory modeling for speech recognition
  • Y. Gong, J. Haton
  • Computer Science
  • Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing
  • 1994
  • 61
A segmental speech model with applications to word spotting
  • H. Gish, Kenney Ng
  • Computer Science
  • 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1993
  • 131
A linear predictive HMM for vector-valued observations with applications to speech recognition
  • 142
Experimental evaluation of segmental HMMs
  • W. Holmes, M. Russell
  • Computer Science
  • 1995 International Conference on Acoustics, Speech, and Signal Processing
  • 1995
  • 14
  • PDF
...
1
2
3
4
5
...