In this paper we present some ideas and preliminary results on how to move phoneme recognition techniques from speech to the singing voice to solve the low-delay alignment problem. The work focus mainly on searching the most appropriate Hidden Markov Model (HMM) architecture and suitable input features for the singing voice, and reducing the delay of the phonetic aligner without reducing its ac...

A method to express Profile Hidden Markov Model (Profile HMM) parameters with compressing matrix is presented, which is obtained by imposing the characteristics of both the state transfer and the character output in the Profile HMM.

The differences between formants of British, Australian and American English accents are analysed and ranked. An improved formant model based on linear prediction (LP) feature analysis and a two-dimensional(2D) hidden Markov model (HMM) of formants is employed for estimation of the formant frequencies and bandwidths of vowels and diphthongs. Comparative analysis of the formant trajectories, the...

We present the design and development of a Hidden Markov Model for the division of news broadcasts into story segments. Model topology, and the textual features used, are discussed, together with the non-parametric estimation techniques that were employed for obtaining estimates for both transition and observation probabilities. Visualization methods developed for the analysis of system perform...

To determine the possibility of predicting viewer’s internal states using the hidden Markov model, several features of eye movements were introduced to the model. Performance was measured using the data from a set of eye movement features recorded during recall tests which consisted of observations of three levels of task difficulty. The features were the temporal appearances of fixations and s...

This paper describes the use of phonological knowledge to enhance current audio word spotting technology based on Hidden Markov Model. It reports on the result of an word-spotting experiment done on an audio data recorded from a live conference. The result of the experiment demonstrates the positive contribution of phonological knowledge towards audio word-spotting.