Cluster-based modeling for ubiquitous speech recognition

  title={Cluster-based modeling for ubiquitous speech recognition},
  author={Sadaoki Furui and Tomohisa Ichiba and Takahiro Shinozaki and Edward W. D. Whittaker and Koji Iwano},
In order to realize speech recognition systems that can achieve high recognition accuracy for ubiquitous speech, it is crucial to make the systems flexible enough to cope with a large variability of spontaneous speech. This paper investigates two speech recognition methods that can adapt to speech variation using a large number of models trained based on clustering techniques; one automatically builds a model adapted to input speech using recognition hypotheses and clustered models, and the… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 13 references

Analysis recognition of spontaneous speech using Corpus of ntaneous Japanese

M. Nakamura Furui, T. Ichiba, K. Iwano
Speech Communication • 2005

Spontaneous speech gnition using a massively parallel decoder

S. Furui
Proc . ERSPEECH • 2004

Sugimura and S . Furui , “ A treestructured tering method integrating noise and SNR for piecewise artransformationbased noise adaptation

T. Zhang
Proc . SSP • 2004

Furui , supervised class - based language model adaptation for ntaneous speech recognition

T. Shinozaki Yokoyama, S.

Furui , supervised language model adaptation using word ses for spontaneous speech recognition

T. Shinozaki Yokoyama, S.

Automatic sublanguage identification for a text

T. Kawahara, H. Nanjo
Proc . Second Annual Workshop on Very Large pora

Similar Papers

Loading similar papers…