Accurate estimation of segmental durations is crucial for naturalsounding text-to-speech (TTS) synthesis. This paper presents a model of vowel duration used in the Bell Labs Japanese TTS system. We describe the constraints on vowel devoicing, and effects of factors such as phone identity, surrounding phone identities, accentuation, syllabic structure, and phrasal position on the duration of bot...

Current speech synthesis efforts, both in research and in applications, are dominated by methods based on concatenation of spoken units. New progress in the concatenative text-to-speech (TTS) technology can be made mainly from two directions, either by reducing the memory footprint to integrate the system into embedded system, or by improving the synthesized speech quality in terms of intelligi...

This paper describes a phone duration model applied to speech recognition. The model is based on a decision tree that finds clusters of phones in various contexts that tend to have similar durations. Wide contexts with rich linguistic and phonetic features are used. To better model varying and non-stationary speaking rates, the contextual features also include the observed duration values of pr...

Yu Zhang 1, Vijay P. Singh 1,2,* and Aaron R. Byrd 3 1 Department of Biological and Agricultural Engineering, Texas A&M University, College Station, TX 77840, USA; [email protected] 2 Zachry Department of Civil Engineering, Texas A&M University, College Station, TX 77843-2117, USA 3 Hydrologic Systems Branch, Coastal and Hydraulics Laboratory, Engineer Research Development Center, U.S. Arm...

This paper describes the construction and evaluation of a segmental duration prediction model for Greek language with the application of CART (Classification and Regression Tree) machine learning approach. A ToBI annotated prosodic speech corpus was utilized for the construction of training and testing sets. Our phoneme category was composed of 34 phonemes distributed in 32.072 instances (in 5....

The application of “Multivariate Adaptive Regression Splines”(MARS) to the problem of modeling duration of a set of segments used in a text-to-speech system for German is presented. MARS is a technique to estimate general functions of high-dimensional arguments given sparse data. It automatically selects the parameters and the structure of the model based on data available. The result is a mode...

This paper describes a study on using explicit duration models in hidden Markov model (HMM) based Cantonese connecteddigit recognition. An HMM does not give explicit control to the temporal structure of speech. As a result, the recognition output may exhibit unreasonable duration pattern, which is often accompanied with the presence of recognition errors. We propose to use a duration model that...

An accurate estimation of segmental durations is needed for natural sounding textto-speech (TTS) synthesis. This paper propose multi-models based on production aspects of vowels. In this work four multi-models are developed based on vowel length, vowel height, vowel frontness and vowel roundness. In each multimodel, syllables are divided into groups based on specific vowel articulation characte...

This paper describes a series of experiments that have been conducted to investigate the effect of duration modeling in a hidden Markov model (HMM) based online handwriting recognition system. The issues discussed include parametric vs. non-parametric distributions to model duration, different methods for training transition probabilities and the effect of weighting on duration terms.

This paper describes a novel technique to exploit duration information for low resource speech recognition systems. Using explicit duration models significantly increases computational cost due to a large search space. To avoid this problem, most of techniques using duration information adopt two-pass and N-best re-scoring approaches. Meanwhile, we propose an algorithm using word duration model...