New Approaches Towards Robust and Adaptive Speech Recognition

Hervé Bourlard, Samy Bengio, Katrin Weber

NeurIPS 2000 pp. 751-757

/neurips/2000/bourlard2000neurips-new/

Abstract

In this paper, we discuss some new research directions in automatic speech recognition (ASR), and which somewhat deviate from the usual approaches. More specifically, we will motivate and briefly describe new approaches based on multi-stream and multi/band ASR. These approaches extend the standard hidden Markov model (HMM) based approach by assuming that the different (frequency) channels representing the speech signal are processed by different (independent) "experts", each expert focusing on a different char(cid:173) acteristic of the signal, and that the different stream likelihoods (or posteriors) are combined at some (temporal) stage to yield a global recognition output. As a further extension to multi-stream ASR, we will finally introduce a new approach, referred to as HMM2, where the HMM emission probabilities are estimated via state spe(cid:173) cific feature based HMMs responsible for merging the stream infor(cid:173) mation and modeling their possible correlation.

PDF NeurIPS Semantic Scholar

Cite

Text

Bourlard et al. "New Approaches Towards Robust and Adaptive Speech Recognition." Neural Information Processing Systems, 2000.

Markdown

[Bourlard et al. "New Approaches Towards Robust and Adaptive Speech Recognition." Neural Information Processing Systems, 2000.](https://mlanthology.org/neurips/2000/bourlard2000neurips-new/)

BibTeX

@inproceedings{bourlard2000neurips-new,
  title     = {{New Approaches Towards Robust and Adaptive Speech Recognition}},
  author    = {Bourlard, Hervé and Bengio, Samy and Weber, Katrin},
  booktitle = {Neural Information Processing Systems},
  year      = {2000},
  pages     = {751-757},
  url       = {https://mlanthology.org/neurips/2000/bourlard2000neurips-new/}
}