This paper presents a method for segregating and recognizing concurrent vowels based on the amplitude modulation spectrum. Vowel segregation is accomplished by F0-guided grouping of harmonic components encoded in the amplitude modulation spectrum while vowel recognition is achieved by classifying the segregated vowel spectrum. Main features of the method are (1) the reassigned technique is employed to obtain a high resolution amplitude modulation spectrum and (2) Fisher's linear discriminant analysis is used to improve the performance of vowel classification. The method is tested on a double-vowel identification task and some preliminary results are provided.
Cite as: Yang, D., Meyer, G.F., Ainsworth, W.A. (1998) Vowel separation using the reassigned amplitude-modulation spectrum. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0511, doi: 10.21437/ICSLP.1998-510
@inproceedings{yang98d_icslp,
author={Dekun Yang and Georg F. Meyer and William A. Ainsworth},
title={{Vowel separation using the reassigned amplitude-modulation spectrum}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0511},
doi={10.21437/ICSLP.1998-510}
}