Spotting Japanese CV-Syllables and Phonemes Using Time-Delay Neural Networks

Syllable or phoneme spotting if reliably achieved, provides a good solution to the spoken word andlor continuous speech recognition problem, . We previously showed tha t the Time-Delay Neural Network (TDNN) provided excellent recognition performance (98.6%) of the "BDG" consonant task. We would also like to extend the encouraging performance of TDNN to wordlcontinuous speech recognition. In this paper, we show techniques for spotting Japanese CV syllableslphonemes in input speech based on TDNNs. We constructed the TDNN which can discriminate a single CV-syllable or phoneme group. In Japanese, there are only about one hundred syllables, or less than thirty phonemes, which makes i t feasible to prepare and train the TDNN to spot all possible syllables or phonemes extracted as training tokens from training words. Syllable and phoneme spotting experiments show excellent results, including a syllable spotting rate of better than 96.7% correct. These spotting techniques are proved to be a good step toward continuous speech recognition.