The aim of the research described in this paper is to overcome important speech-modeling limitations of conventional hidden Markov models (HMMs), by developing a dynamic segmental HMM which models the changing pattern of speech over the duration of some phoneme-type unit. As a first step towards this goal, a static segmental HMM [3] has been implemented and tested, This model reduces the influe...

We propose to control intonation in unit selection speech synthesis with a mixed CART-HMM intonation model. The Finite State Machine (FSM) formulation is suited to incorporate the intonation model in the unit selection framework because it allows for combination of models with different unit types and handling competing intonative variants. Subjective experiments have been carried out to compar...

Currently, AT&T Labs’ Natural Voices multilingual TTS system produces high-quality synthetic speech with a largescale speech corpus [1]. In the development of such systems, automatic segmentation constitutes a major component technology. The prevalent approach for automatic segmentation in speech synthesis is Hidden Markov Model (HMM) based. Even though an HMM-based approach is the most automat...

This paper describes how non-linear formant trajectories, based on ‘trajectory HMM’ proposed by Tokuda et al., can be exploited under the framework of multiple-level segmental HMMs. In the resultant model, named a non-linear/linear multiple-level segmental HMM, speech dynamics are modeled as non-linear smooth trajectories in the formant-based intermediate layer. These formant trajectories are m...

In the Laboratory of Speech Acoustics ASR research has been prepared, in which we were searching for the possibility to contribute to the higher linguistic processing levels of ASR – at syntactic, and semantic level – by acoustical preprocessing of the supra-segmental (prosodic) features. The subject of our current article is a semantic level processing, built on supra-segmental parameters. HMM...

It is often expedient to consider using more than one single HMM to characterize a speech unit. In this paper, we suggest a new speech units modeling method based on analysis of parameters of HMMs obtained by preliminary training. By analyzing the emission probability function of a state of a HMM obtained by segmental k-means training, we can obtain the distribution of the source data and deter...

Recently the initial attempt has been made to use segment-based direct models on their own for phone classification and recognition without the aid of an HMM lattice. This paper follows this line of research to further investigate these one-pass segmental direct models on phone recognition using posteriors as input. We make the first direct comparison between a frame-based system and a segmenta...

This research reports the development of an HMM-based speech synthesis system for Malay, which is an underresourced language with few resources including recorded speech and segmental labels. We propose the cross-lingual use of resources for developing a Malay HMM-based speech synthesis system. We used the Festival English speech synthesis system to generate time-aligned phone transcriptions fo...

Hidden State Shape Models (HSSMs) [2], a variant of Hidden Markov Models (HMMs) [9], were proposed to detect shape classes of variable structure in cluttered images. In this paper, we formulate a probabilistic framework for HSSMs which provides two major improvements in comparison to the previous method [2]. First, while the method in [2] required the scale of the object to be passed as an inpu...

To achieve high quality synthetic emotional speech, unitselection is the state-of-the-art technique. Nevertheless, a large expensive phonetically-segmented corpus is needed, and cost-effective automatic techniques should be studied. According to the HMM experiments in this paper: segmentation performance can depend heavily on the segmental or prosodic nature of the intended emotion (segmental e...