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 correlation structure and parameter tying and outlining the extensions to HMM recognition and training algorithms needed to handle segment models.
CITATION STYLE
Ostendorf, M. (1996). From HMMS to Segment Models: Stochastic Modeling for CSR (pp. 185–210). https://doi.org/10.1007/978-1-4613-1367-0_8
Mendeley helps you to discover research relevant for your work.