Connectionist language modeling for large vocabulary continuous speech recognition

@article{Schwenk2002ConnectionistLM,
  title={Connectionist language modeling for large vocabulary continuous speech recognition},
  author={Holger Schwenk and J. Gauvain},
  journal={2002 IEEE International Conference on Acoustics, Speech, and Signal Processing},
  year={2002},
  volume={1},
  pages={I-765-I-768}
}
  • Holger Schwenk, J. Gauvain
  • Published 2002
  • Computer Science
  • 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • This paper describes ongoing work on a new approach for language modeling for large vocabulary continuous speech recognition. [...] Key Method A neural network is used to learn the projection of the words onto a continuous space and to estimate the n-gram probabilities. The connectionist language model is being evaluated on the DARPA HUB5 conversational telephone speech recognition task and preliminary results show consistent improvements in both perplexity and word error rate.Expand Abstract

    Figures, Tables, and Topics from this paper.

    Continuous space language models
    • 489
    • PDF
    Efficient training of large neural networks for language modeling
    • 37
    • PDF
    Neural network language models for conversational speech recognition
    • 45
    • PDF
    Training Neural Network Language Models on Very Large Corpora
    • 123
    • PDF
    USING CONTINUOUS SPACE LANGUAGE MODELS FOR CONVERSATIONAL SPEECH RECOGNITION
    • 9
    • PDF
    Building continuous space language models for transcribing european languages
    • 14
    • PDF
    Large Vocabulary SOUL Neural Network Language Models
    • 28
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 15 REFERENCES
    The LIMSI Broadcast News transcription system
    • 481
    Fast decoding for indexation of broadcast data
    • 25
    • PDF
    Neural Networks for Pattern Recognition
    • 12,898
    • PDF
    Language Model Adaptation
    • 43
    I
    • 67,184
    • PDF
    A neural probabili stic language model
    • 2001
    Compaq Extended Math Library (CXML)
      Fast decoding for indexatio n of broadcast data
      • 2000