Towards unsupervised speech processing

  title={Towards unsupervised speech processing},
  author={James R. Glass},
  journal={2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA)},
The development of an automatic speech recognizer is typically a highly supervised process involving the specification of phonetic inventories, lexicons, acoustic and language models, and requiring annotated training corpora consisting of parallel speech and text data. Although some model parameters may be modified via adaptation, the overall structure of the speech recognizer usually remains relatively static. While this approach has been effective for problems where there is adequate human… CONTINUE READING
Highly Cited
This paper has 35 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 27 extracted citations

A parallelized dynamic programming approach to zero resource spoken term discovery

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2017
View 1 Excerpt

Similar Papers

Loading similar papers…