论文信息 - Speech recognition with difficult dictionaries

Speech recognition with difficult dictionaries

In this paper we introduce a new generalization of the Generalized Linear Discriminant Function, in which the dimension of the representation space depends on the class. This generalization is applied to Speech Recognition with Difficult Dictionaries, leading to a (preliminary) error rate reduction over 50% with respect to the standard approach.

Francisco Casacuberta | Enrique Vidal

[1] Lawrence R. Rabiner,et al. Isolated word recognition using a two-pass pattern recognition approach , 1981, ICASSP.

[2] Enrique Vidal Ruiz,et al. Utilización de funciones discriminantes lineales generalizadas en el reconocimiento de palabras aisladas con ciertos diccionarios difíciles , 1987 .

[3] Roger K. Moore,et al. Locally constrained dynamic programming in automatic speech recognition , 1982, ICASSP.

[4] Francisco Casacuberta,et al. Is the DTW "distance" really a metric? An algorithm reducing the number of DTW comparisons in isolated word recognition , 1985, Speech Commun..

[5] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[6] George R. Doddington,et al. Frame-specific statistical features for speaker independent speech recognition , 1986, IEEE Trans. Acoust. Speech Signal Process..

[7] M. Tomlinson,et al. The discriminative network: A mechanism for focusing recognition in whole-word pattern matching , 1983, ICASSP.

[8] Enrique Vidal Ruiz,et al. Reconocimiento de palabras muy semajantes basado en la minimización del criterio perceptron , 1988 .