Corpus ID: 5805177

Active and unsupervised learning for automatic speech recognition

@inproceedings{Riccardi2003ActiveAU,
  title={Active and unsupervised learning for automatic speech recognition},
  author={G. Riccardi and Dilek Z. Hakkani-T{\"u}r},
  booktitle={INTERSPEECH},
  year={2003}
}
  • G. Riccardi, Dilek Z. Hakkani-Tür
  • Published in INTERSPEECH 2003
  • Computer Science
  • State-of-the-art speech recognition systems are trained using human transcriptions of speech utterances. In this paper, we describe a method to combine active and unsupervised learning for automatic speech recognition (ASR). The goal is to minimize the human supervision for training acoustic and language models and to maximize the performance given the transcribed and untranscribed data. Active learning aims at reducing the number of training examples to be labeled by automatically processing… CONTINUE READING
    65 Citations
    Active learning: theory and applications to automatic speech recognition
    • 136
    • PDF
    Unsupervised and active learning in automatic speech recognition for call classification
    • 44
    • PDF
    Unsupervised training and directed manual transcription for LVCSR
    • 61
    • Highly Influenced
    • PDF
    A confusion network based confidence measure for active learning in speech recognition
    • Wei Chen, Gang Liu, J. Guo
    • Computer Science
    • 2008 International Conference on Natural Language Processing and Knowledge Engineering
    • 2008
    • 2
    Post-dialogue confidence scoring for unsupervised statistical language model training
    • 6
    Efficient use of training data for sinhala speech recognition using active learning
    • 3

    References

    SHOWING 1-10 OF 23 REFERENCES
    Learning to Recognize Speech by Watching Television
    • 41
    Lightly supervised and unsupervised acoustic model training
    • 262
    • PDF
    Unsupervised training of a speech recognizer using TV broadcasts
    • 35
    • PDF
    On-line learning of language models with word error probability distributions
    • R. Gretter, G. Riccardi
    • Computer Science
    • 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)
    • 2001
    • 43
    • PDF
    A training procedure for verifying string hypotheses in continuous speech recognition
    • R. Rose, B. Juang, C. Lee
    • Computer Science
    • 1995 International Conference on Acoustics, Speech, and Signal Processing
    • 1995
    • 79
    Utilizing untranscribed training data to improve perfomance
    • 69
    Stochastic automata for language modeling
    • 111
    • PDF
    Improving generalization with active learning
    • 1,395
    • PDF