Phoneme recognition in connected speech using both static and dynamic properties of spectrum described by vector quantization
- 24 March 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 11, 2243-2246
- https://doi.org/10.1109/icassp.1986.1168553
Abstract
This paper describes an approach for a phoneme recognition based on a clustering method which considers phonemic features in each frame. In the clustering, both acoustic and phonemic features of speech are used. The acoustic features are LPC cepstral coefficients, the cepstral changes between adjacent frames and the power changes. The combination of these features shows both the static and dynamic properties of the spectrum. The phonemic feature in a frame is composed of a triplet of phonemic symbols. A vector quantization method is applied for the clustering. Experiment of extracting phonemic label sequences is performed, considering a contiguity of code sequences between the input and the reference phonemic patterns.Keywords
This publication has 6 references indexed in Scilit:
- A clustering experiment of the spectra and the spectral changes of speech to extract phonemic featuresSignal Processing, 1986
- A Vector Quantizer Combining Energy and LPC Parameters and Its Application to Isolated Word RecognitionAT&T Bell Laboratories Technical Journal, 1984
- On the Application of Vector Quantization and Hidden Markov Models to Speaker-Independent, Isolated Word RecognitionBell System Technical Journal, 1983
- Vector quantization of speech and speech-like waveformsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1982
- Speech coding based upon vector quantizationIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980
- An Algorithm for Vector Quantizer DesignIEEE Transactions on Communications, 1980