SPEECH MODELING USING CEPSTRAL-TIME FEATURE MATRICES IN HIDDEN MARKOV-MODELS

The paper explores the use of 2-dimensional cepstral-time features for the utilisation of correlation among successive speech spectral vecto rs, within a hidden-Markov-mode (HMM) framework. A cepstral-time-featu re matrix is obtained from a 2-dimensional discrete cosine transform o f a spectral-time matrix. Advantages of cepstral-time features are tha t cepstral-time-feature matrices are a simple and robust method of rep resenting short-time variation of speech spectral parameters; a cepstr al-time matrix contains information on the transitional dynamics of fe ature vectors within the matrix; speech recognition based on cepstral time matrices is more robust in noisy environments; and use of a matri x of M cepstral vectors implies a minimum HMM-state duration constrain t of M vector units. A simple framework investigated in the paper for applications of cepstral-time features is a finite-state-matrix quanti ser (FSMQ), a special case of the HMM. It is used for initialisation o f the training phase of HMMs.