Sonorant segmentation of speech signals is critical in developing Automatic Speech Recognition (ASR) systems, audio search systems and for automatic segmentation of speech corpora. In this work, acoustic features based on excitation source and vocal tract system characteristics of sonorant sounds are proposed for segmentation of sonorant regions in continuous speech. The features are based on zero frequency resonator signal energy, strength of excitation and dominant resonance frequency around epochs. An algorithm is developed to relate these features in hierarchical manner using knowledge-based approach. The performance of the proposed algorithm is studied on three different datasets, at varying levels of degradation. TIMIT database is used to test the validity and AMI meeting corpus and Telugu (an Indian language) dataset are considered to test the utility of the proposed features.
Cite as: Dumpala, S.H., Nellore, B.T., Nevali, R.R., Gangashetty, S.V., Yegnanarayana, B. (2015) Robust features for sonorant segmentation in continuous speech. Proc. Interspeech 2015, 1987-1991, doi: 10.21437/Interspeech.2015-437
@inproceedings{dumpala15_interspeech,
author={Sri Harsha Dumpala and Bhanu Teja Nellore and Raghu Ram Nevali and Suryakanth V. Gangashetty and B. Yegnanarayana},
title={{Robust features for sonorant segmentation in continuous speech}},
year=2015,
booktitle={Proc. Interspeech 2015},
pages={1987--1991},
doi={10.21437/Interspeech.2015-437}
}