This paper describes a framework for phonological concept, formation, which is the task of acquiring an efficient representation of phonemes from spoken word samples with-out using any transcriptions except for the identification of the words. The phoneme models are represented as networks of segments, each of which forms a compact distribution of spectral features. We call this representation a phonological concept. The learning process is performed by searching in a hypotheses space for which each hypothesis is produced by modifying a set of phoneme models. This system potentially enables us to improve speech recognition performance.
Cite as: Kojima, H., Tanaka, K., Hayamizu, S. (1992) Formation of phonological concept structures from spoken word samples. Proc. 2nd International Conference on Spoken Language Processing (ICSLP 1992), 269-272, doi: 10.21437/ICSLP.1992-86
@inproceedings{kojima92_icslp,
author={Hiroaki Kojima and Kazuyo Tanaka and Satoru Hayamizu},
title={{Formation of phonological concept structures from spoken word samples}},
year=1992,
booktitle={Proc. 2nd International Conference on Spoken Language Processing (ICSLP 1992)},
pages={269--272},
doi={10.21437/ICSLP.1992-86}
}