This paper proposes a phoneme recognizer without any language model. The system is realized as an integration of spectrogram reading knowledge and Time-Delay Neural Networks. The system mainly consists of two parts: a consonant recognition part and a vowel recognition part, in which a sophisticated integration of knowledge and TDNN, is proposed. The knowledge part is mainly used for verification of ciitegories and boundaries. An experiment of speaker-dependent phoneme recognition without any language model, using 2,620 words, showed a 91. 4% recognition rate, a 3. 6% deletion error rate, a 5. 0% substitution error rate and a 20. 7% insertion error rate, for all Japanese phonemes. Keywords: Speech recognition; Spectrogram reading knowledge; Time-Delay Neural Networks; Expert system
Cite as: Komori, Y., Hatazaki, K. (1991) An integration of knowledge and neural networks toward a phoneme typewriter without a language model. Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991), 1423-1426, doi: 10.21437/Eurospeech.1991-146
@inproceedings{komori91_eurospeech, author={Yasuhiro Komori and Kaichiro Hatazaki}, title={{An integration of knowledge and neural networks toward a phoneme typewriter without a language model}}, year=1991, booktitle={Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991)}, pages={1423--1426}, doi={10.21437/Eurospeech.1991-146} }