This paper explores the use of two dimensional cepstral-time features for the utilisation of correlation among successive speech spectral vectors, within a hidden Markov model (HMM) framework. A cepstral-time feature matrix is obtained from a two dimensional discrete cosine transform of a spectral-time matrix. Advantages of cepstral-time features are : a) a cepstral-time feature matrix is a simple and robust method for representation of short-time variation of speech spectral parameters, b) a cepstral-time matrix contains information on the transitional dynamics of feature vectors within the matrix, c) speech recognition based on cepstral time matrices is more robust in noisy environments, and d) using a matrix of M cepstral vectors implies a minimum HMM-state duration constraint of M vector units. A simple framework investigated in this paper for applications of cepstral-time features is a Finite State Matrix Quantiser (FSMQ). The FSMQ is a special case of the HMM and is used for initialisation of the training phase of HMMs.