A new method for recognising plosives in isolated Mandarin syllables is discussed in the Letter. After automatically detecting the plosive segment of the input utterance, some dynamic features are extracted from its spectral parameter contours using orthonormal polynomial transforms. Next, an MLP trained with an algorithm based on a minimum error criterion is employed to distinguish plosives using these features. A promising recognition rate of 73.6% is achieved in a speaker-independent test using a database containing utterances of 110 syllables uttered by 100 speakers.
- Neural networks
- Speech recognition