Second International Conference on Spoken Language Processing (ICSLP'92)

Banff, Alberta, Canada
October 13-16, 1992

Selectively Trained Neural Networks for the Discrimination of Normal and Lombard Speech

Yolande Anglade (1,2), Dominique Fohr (1), Jean-Claude Junqua (3)

(1) CRJN-CNRS / INRIA Lorraine, Vandoeuvre-les-Nancy, France

(2) SOLLAC, Florange, France

(3) Speech Technology Laboratory, Div. of Panasonic Technologies, Inc., Santa Barbara, California, USA

The purpose of this work is to improve the automatic recognition of confusable words, considering such typical examples as French and American-English Alphabets. Our study proposes a comparison between global methods like DTW or HMM and a new method using neural networks. This method is based on the search for 2 discriminative frames inside the confusable words bearing the distinction between them. Then a parametrization is done and resulting vectors are given to neural networks. The tests conducted on normal speech, Lombard speech without additive noise and Lombard speech with additive noise show a general improvement of the recognition accuracy.

Full Paper

Bibliographic reference.  Anglade, Yolande / Fohr, Dominique / Junqua, Jean-Claude (1992): "Selectively trained neural networks for the discrimination of normal and lombard speech", In ICSLP-1992, 595-598.