Domain adaptation with clustered language models

A method of domain adaptation for clustered language models is developed. It is based on a previously developed clustering algorithm (Ueberla, 1994), but with a modified optimisation criterion. The results are shown to be slightly superior to the previously published 'Fillup' method (Besling and Meier, 1995), which can be used to adapt standard n-gram models. However, the improvement both methods give compared to models built from scratch on the adaptation data is quite small (less than 11% relative improvement in word error rate). This suggests that both methods are still unsatisfactory from a practical point of view.

• Publication year

  1997

• Venue

  IEEE International Conference on Acoustics, Speech, and Signal Processing

• Publication date

  1997-03-04

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICASSP.1997.596052arXiv cmp-lg/9703001
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Modeling long distance dependence in language: topic mixtures vs. dynamic cache models

  1996cited by this paper
• Bayesian estimation methods for n-gram language model adaptation

  1996cited by this paper
• A maximum entropy approach to adaptive statistical language modelling

  1996cited by this paper
• Language model speaker adaptation

  1995influential reference
• Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models

  1995cited by this paper
• On the Estimation of 'Small' Probabilities by Leaving-One-Out

  1995cited by this paper
• More efficient clustering of n-grams for statistical language modeling

  1995cited by this paper
• An extended clustering algorithm for statistical language models

  1994cited by this paper
• On structuring probabilistic dependences in stochastic language modelling

  1994cited by this paper
• Estimating 'small' probabilities by leaving-one-out

  1993cited by this paper
• On the dynamic adaptation of stochastic language models

  1993cited by this paper
• Adaptive Language Modeling Using Minimum Discriminant Estimation

  1992cited by this paper
• Task adaptation in stochastic language models for continuous speech recognition

  1992cited by this paper
• A Dynamic Language Model for Speech Recognition

  1991cited by this paper
• A Cache-Based Natural Language Model for Speech Recognition

  1990cited by this paper

• Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100

  2020cites this paper
• TWO-STAGE MODEL SELECTION WITH PARAMETERS WEIGHTED HIDDEN MARKOV MODELS AND LIKELIHOOD RATIO FOR PART-OF-SPEECH TAGGING

  2012cites this paper
• Predictive hidden Markov model selection for speech recognition

  2005cites this paper
• A class based approach to domain adaptation and constraint integration for empirical m-gram models

  1997cites this paper
• Towards an Improved Performance Measure for Language Models

  1997cites this paper
• Work in Progress on Adaptive Language Models

  1997cites this paper
• Experiments in adaptation of language models for commercial applications

  1997cites this paper
• The Effects of Corpus Size and Homogeneity on Language Model Quality

  1997cites this paper