Xavi Gonzalvo

Learn 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)
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)
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)
—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)
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, so that the final network architecture provably(More)