ISCA Archive ICSLP 1994
ISCA Archive ICSLP 1994

Hidden Markov models and selectively trained neural networks for connected confusable word recognition

Jean-Frangois Mari, Dominique Fohr, Yolande Anglade, Jean-Claude Junqua

This paper presents a new method for connected-word recognition with confusable vocabularies, such as connected letters. The recognition process is performed in two steps. First, a second-order HMM provides N-best word strings. Then, the strings of confusable letters are discriminated by a procedure based on acoustic knowledge and artificial neural networks (ANN). This method has been tested on an American-English database containing spelled names collected through the telephone network. The results obtained with the first HMM pass and the improvements made with the ANN are presented and discussed. When a 3,300 name dictionary and a retrieval procedure based on a DTW alignment algorithm were used, 96% recognition accuracv was obtained.


Cite as: Mari, J.-F., Fohr, D., Anglade, Y., Junqua, J.-C. (1994) Hidden Markov models and selectively trained neural networks for connected confusable word recognition. Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994), 1519-1522

@inproceedings{mari94b_icslp,
  author={Jean-Frangois Mari and Dominique Fohr and Yolande Anglade and Jean-Claude Junqua},
  title={{Hidden Markov models and selectively trained neural networks for connected confusable word recognition}},
  year=1994,
  booktitle={Proc. 3rd International Conference on Spoken Language Processing (ICSLP 1994)},
  pages={1519--1522}
}