Xavi Gonzalvo

Learn More
A restricted domain text-to-speech system oriented to a weather forecast application is presented. This TTS system is embedded in a multimedia interactive service accessible from different media, such as TV, Internet and mobile devices. The requirements of this application give rise to several particularities in the design and implementation of the TTS(More)
Hidden Markov Models based text-to-speech (HMM-TTS) synthesis is one of the techniques for generating speech from trained statistical models where spectrum and prosody of basic speech units are modelled altogether. This paper presents the advances in our Spanish HMM-TTS and a perceptual test is conducted to compare it with an extended PSOLA-based(More)
—This paper is a contribution to the recent advancements in the development of high-quality next generation text-to-speech (TTS) synthesis systems. Two of the hottest research topics in this area are oriented towards the improvement of speech ex-pressiveness and flexibility of synthesis. In this context, this paper presents a new TTS strategy called(More)
This paper describes a multi-domain text-to-speech (MD-TTS) synthesis strategy for generating speech among different domains and so increasing the flexibility of high quality TTS systems. To that effect, the MD-TTS introduces a flexible TTS architecture that includes an automatic domain classification module, which allows MD-TTS systems to be implemented by(More)
We present a new theoretical framework for analyzing and learning artificial neural networks. Our approach simultaneously and adaptively learns both the structure of the network as well as its weights. The methodology is based upon and accompanied by strong data-dependent theoretical learning guarantees. We present some preliminary results to show that the(More)
This paper introduces a text classification system tuned to cope with the requirements of multi-domain text-to-speech synthesis. This method, based on a previous system which represents texts by means of a weighted graph, has been developed to improve the classification efficiency for small texts and to minimize its computational cost. To that effect, the(More)
This work presents an automatic acronyms transcription system in order to increase the synthetic speech quality of text-to-speech systems, in the presence of acronyms in the input text. The acronyms transcription is conducted by using a decision tree (C4.5 algorithm). The work presents the results obtained for different algorithm configurations, validating(More)