SPEAKER INDEPENDENT PHONETIC RECOGNITION USING AUDITORY MODELLING AND RECURRENT NEURAL NETWORKS
作者： P. Cosi
DOI:
关键词:
摘要: Two speaker independent speech recognition experiments, regarding the automatic discrimination of Italian alphabet I-set and E-set, two very difficult phonetic classes, will be described. The signal is analyzed by a recently developed joint synchrony/mean-rate auditory processing scheme fully-connected feed-forward recurrent BP network was used for classification stage. achieved mean rate 65%, Iset 88% E-set showing rather satisfactory results given difficulty both tasks.
cnr.it参考文章(3)
Stephanie Seneff, A joint synchrony/mean-rate model of auditory speech processing Journal of Phonetics. ,vol. 16, pp. 101- 111 ,(1990) , 10.1016/S0095-4470(19)30466-8
Piero Cosi, SLAM: segmentation and labelling automatic module. conference of the international speech communication association. ,(1993)
A. J. Fourcin, V. Hazan, G. Harland, W. Barry, Speech input and output assessment: multilingual methods and standards Halsted Press. ,(1989)