Universal use of speech synthesis in different applications would require an easy development of new voices with little manual intervention. Considering the amount of multimedia data available on internet and media, one interesting goal is to develop tools and methods to automatically build multi-style voices from them. In a previous paper a methodology for constructing such tools was sketched, and preliminary experiments with a multi-style database were presented. In this paper we further investigate such approach and propose several improvements to it based on the selection of the appropriate number of initial speakers, the use or not of noise reduction filters, the use of the F0 feature and the use of a music detection algorithm. We have...
Este trabajo de Tesis ha abordado el objetivo de dar robustez y mejorar la Detección de Actividad de...
This thesis focuses on the control of a singing voice synthesizer to achieve natural expression simi...
Traditional Text-To-Speech (TTS) systems have been developed using especially-designed non-expressiv...
El uso universal de síntesis de voz en diferentes aplicaciones requeriría un desarrollo sencillo de ...
Comunicació i pòster presentats a l'Interspeech 2017 celebrat del 20 al 24 d'agost a Estocolm, Suèci...
This paper describes the first TTS evaluation campaign designed for Spanish. Seven research institut...
In this work the results of the design and development of an algorithm based on artificial intellige...
Proceedings of: 15th Annual Conference of the International Speech Communication Association. Singap...
This paper deals with the creation of multiple voices from a Hidden Markov Model based speech synthe...
We study in this thesis the joint construction of speech recognition and synthesis systems for new l...
La veu cantada és probablement l'instrument musical més complex i més ric en matisos expressius. Al ...
Por otro lado, se presenta un método para el cambio realista de intensidad de voz cantada. Esta tran...
Speech and singing voice discrimination is an important task in the speech processing area given tha...
This paper describes the first TTS evaluation campaign designed for Spanish. Seven research institut...
Implementation of new discriminative techniques for the improvemente of the UPC speaker tracking sys...
Este trabajo de Tesis ha abordado el objetivo de dar robustez y mejorar la Detección de Actividad de...
This thesis focuses on the control of a singing voice synthesizer to achieve natural expression simi...
Traditional Text-To-Speech (TTS) systems have been developed using especially-designed non-expressiv...
El uso universal de síntesis de voz en diferentes aplicaciones requeriría un desarrollo sencillo de ...
Comunicació i pòster presentats a l'Interspeech 2017 celebrat del 20 al 24 d'agost a Estocolm, Suèci...
This paper describes the first TTS evaluation campaign designed for Spanish. Seven research institut...
In this work the results of the design and development of an algorithm based on artificial intellige...
Proceedings of: 15th Annual Conference of the International Speech Communication Association. Singap...
This paper deals with the creation of multiple voices from a Hidden Markov Model based speech synthe...
We study in this thesis the joint construction of speech recognition and synthesis systems for new l...
La veu cantada és probablement l'instrument musical més complex i més ric en matisos expressius. Al ...
Por otro lado, se presenta un método para el cambio realista de intensidad de voz cantada. Esta tran...
Speech and singing voice discrimination is an important task in the speech processing area given tha...
This paper describes the first TTS evaluation campaign designed for Spanish. Seven research institut...
Implementation of new discriminative techniques for the improvemente of the UPC speaker tracking sys...
Este trabajo de Tesis ha abordado el objetivo de dar robustez y mejorar la Detección de Actividad de...
This thesis focuses on the control of a singing voice synthesizer to achieve natural expression simi...
Traditional Text-To-Speech (TTS) systems have been developed using especially-designed non-expressiv...