ACL RD-TEC 1.0 Summarization of H90-1063

Paper Title:
IMPROVED HIDDEN MARKOV MODELING FOR SPEAKER-INDEPENDENT CONTINUOUS SPEECH RECOGNITION

Authors: Xuedong Huang and Fil Alleva and Satoru Hayamizu and Hsiao-Wuen Hon and Mei-Yuh Hwang and Kai-Fu Lee

Other assigned terms:

  • approach
  • cluster
  • clusters
  • codebook
  • coefficient
  • computational complexity
  • continuous speech
  • correlation
  • data set
  • density function
  • error rate
  • evaluation test
  • feature
  • feature sets
  • frame
  • generation
  • grammar
  • hypotheses
  • implementation
  • independence assumption
  • interpolation
  • large-vocabulary system
  • markov models
  • measure
  • measures
  • method
  • modeling power
  • perplexity
  • posterior
  • priori
  • probabilistic framework
  • probabilities
  • probability
  • probability density
  • probability density function
  • procedure
  • recognition accuracy
  • recognition error rate
  • resource management task
  • segment boundary
  • segments
  • sentence
  • sentences
  • sources of information
  • speech research
  • spoken language
  • technique
  • temporal information
  • test set
  • training
  • training corpus
  • training data
  • training data set
  • transformation
  • triphone
  • word
  • word level
  • word pair
  • word pair grammar
  • word-pair grammar
  • words

Extracted Section Types:


This page last edited on 10 May 2017.

*** ***