Can I read Parameter reduction schemes for loosely coupled HMMs on EtoBox?

Parameter reduction schemes for loosely coupled HMMs by H.J. Nock; M. Ostendorf is a Computer Science article available to read on EtoBox.

What is Parameter reduction schemes for loosely coupled HMMs about?

While Hidden Markov Models (HMMs) have been successful in many speech recognition tasks, performance on conversational speech is somewhat less successful, arguably due in part to the greater variation in timing of articulatory events. Loosely Coupled or Factorial HMMs (FHMMs) represent a family of models that have more flexibility for modeling such variation in speech, but there are tradeoffs to be studied in terms of computation and potential added confusability. This paper investigates two specific instances -Mixed-Memory and Parameter-Tied FHMMs -that can both be thought of as loosely coupled HMMs for modelling multiple time series. The Parameter-Tied FHMM, introduced here, has a potential advantage for speech modelling since it allows a left-to-right topology across the product state space. Experimental results on the ISOLET task show both models are feasible for speech recognition; TI-DIGITS recognition results show the Parameter-Tied FHMM is competitive with Multiband Models. State occupancy and pruning analyses show trends related to asynchrony that hold across the different models.

Who reads Parameter reduction schemes for loosely coupled HMMs?

Author

H.J. Nock; M. Ostendorf

Publisher

Elsevier Science; Elsevier ; Elsevier Inc.; Elsevier BV (ISSN 0885-2308)

Published

2003

Language

EN

Field

Computer Science (Physical Sciences)