Hidden Markov models and selectively trained neural networks for connected confusable word recognition
Jean-Frangois Mari, Dominique Fohr, Yolande Anglade, Jean-Claude Junqua · 1994
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 accuracy was obtained. I. INTRODUCTION The performances of HMM recognizers are now quite satisfactory for small vocabularies. However, in the case of confusable words, results are not sufficient for real-world applications, especially in adverse conditions like noisy or tele...