In this paper, we describe a method to detect syllabic nuclei in continuous speech. It employs two basic and robust acoustic features, periodicity and energy, to detect syllable landmarks. This method is evaluated on TIMIT, noise additive TIMIT and NTIMIT datasets with typical total error rates of around 30% in all the datasets, except for extremely adverse 0dB signal-noise-ratio environments, while HMMbased systems degrade rigorously. Based on the landmarks, a vowel classifier is further constructed and achieves the same performance as HMM-based systems.
Cite as: Xie, Z., Niyogi, P. (2006) Robust acoustic-based syllable detection. Proc. Interspeech 2006, paper 1327-Wed1BuP.6, doi: 10.21437/Interspeech.2006-440
@inproceedings{xie06_interspeech,
author={Zhimin Xie and Partha Niyogi},
title={{Robust acoustic-based syllable detection}},
year=2006,
booktitle={Proc. Interspeech 2006},
pages={paper 1327-Wed1BuP.6},
doi={10.21437/Interspeech.2006-440}
}