ISCA Archive Interspeech 2008
ISCA Archive Interspeech 2008

Towards unsupervised training of the classifier-based speech translator

Emil Ettelaie, Panayiotis G. Georgiou, Shrikanth S. Narayanan

Concept classification has been proven to be a useful translation method for speech-to-speech translation applications. However, preparing training data for classifier is a cumbersome task for human annotators. An unsupervised training method is introduced here that is based on utterance clustering. A technique to measure the distance between two utterances, based on the concepts they express, along with an appropriate clustering method has been adapted.


doi: 10.21437/Interspeech.2008-679

Cite as: Ettelaie, E., Georgiou, P.G., Narayanan, S.S. (2008) Towards unsupervised training of the classifier-based speech translator. Proc. Interspeech 2008, 2739-2742, doi: 10.21437/Interspeech.2008-679

@inproceedings{ettelaie08_interspeech,
  author={Emil Ettelaie and Panayiotis G. Georgiou and Shrikanth S. Narayanan},
  title={{Towards unsupervised training of the classifier-based speech translator}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={2739--2742},
  doi={10.21437/Interspeech.2008-679}
}