Selection of the most significant parameters for duration modelling in a Spanish text-to-speech system using neural networks

Abstract

Accurate prediction of segmental duration from text in a text-to-speech system is difficult for several reasons. One which is especially relevant is the great quantity of contextual factors that affect timing and it is difficult to find the right way to model them. There are many parameters that affect duration, but not all of them are always relevant and some can even be counterproductive because of the possibility of overtraining.The main motivation of this paper has been to reduce the error in the duration estimation. To this end, it is of the utmost importance to find the factors that most influence duration in a given language. The approach we have taken is to use a neural network, which is completely configurable, and experiment with the different combinations of parameters that yield the minimum error in the estimation.We have oriented our work mainly towards the following aspects: the most significant parameters that can be used as input to the automatic model, and the best way to code these parameters. We have studied first the effect of each parameter alone and, after that, we have included all parameters together to have our final system.Another important aspect of this study is the generation of a suite of software tools and design protocols that will be used in future tasks with different speakers and databases. The applications for automatic modelling are obvious: adapt the prosody to a new speaker, to a new environment, to "restricted-domain" sentences, etc., in a fast, semi-automatic and inexpensive way. After the database labelling, it is a matter of minutes to prepare the inputs to the network for the new situation, and the network is trained in 1 h.The result has been a system that predicts duration with very good results (19 ms in RMS) and that clearly improves our previous rule-based system.

Research of the coating textiles’ coating Gram weight measurement system based on infrared

“…The speech synthesis module is a male voice text to speech system developed in by GTH-UPM (BORIS [3]). This module uses a diaphone unit concatenating algorithm, able to modify the speaking rate and speaker pitch.…”

Role of neural network models for developing speech systems

“…Several models based on neural network principles are described in the literature for predicting the durations of syllables in continuous speech (Campbell 1990;Campbell & Isard 1991;Campbell 1992Campbell , 1993Barbosa & Bailly 1994Cordoba et al 1999;Hifny & Rashwan 2002;Sonntag et al 1997;Teixeira & Freitas 2003). Campbell (1992) used a feedforward neural network trained with feature vectors, each representing six features of a syllable.…”

Segmental Duration Modeling for Greek Speech Synthesis

“…Duration modeling techniques can be divided into two major categories, the rule-based approaches [3,4,5] and the corpus-based [6,7,8,9]. With regard to rule-based approaches the most well known and widely used is the one proposed by Dennis Klatt [3].…”

“…Concerning machine learning based duration models the need of a large annotated speech corpus is mandatory. In previous research such models have been constructed with the application of machine learning approaches such as decision trees [6], Artificial Neural Networks [7], Bayesian models [9] or linear statistical models [8].…”