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… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 32 CITATIONS

Point process models for event-based speech recognition

  • Speech Communication
  • 2009
VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Fixed-dimensional acoustic embeddings of variable-length segments in low-resource settings

  • 2013 IEEE Workshop on Automatic Speech Recognition and Understanding
  • 2013
VIEW 1 EXCERPT
CITES BACKGROUND