Search
Now showing items 1-8 of 8
Linguistic and Mixed Excitation Improvements on a HMM-based speech synthesis for Castilian Spanish
(6th ISCA Workshop on Speech Synthesis, Bonn, 22-24 of August 2007, 2007-08)
HiddenMarkov 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 ...
La Conversión de Texto en Habla Multidominio: principios y portabilidad
(Universidad de Zaragoza, 2006-11-08)
La conversión de texto en habla (CTH) multidominio per-sigue conseguir una calidad sintética cercana a la de lossistemas de CTH diseñados para un determinado ámbi-to o aplicación, aumentando su flexibilidad ...
GTM-URL Contribution to the INTERSPEECH 2009 Emotion Challenge
(10th Annual Conference of the International Speech Communication Associations, Brighton, 6-10 of September 2009, 2009-09)
This paper describes our participation in the INTERSPEECH
2009 Emotion Challenge [1]. Starting from our previous
experience in the use of automatic classification for the
validation of an expressive ...
Local minimum generation error criterion for hybrid HMM speech synthesis
(10th Annual Conference of the International Speech Communication Associations, Brighton, 6-10 of September 2009, 2009-09)
This paper presents an HMM-driven hybrid speech synthesis
approach in which unit selection concatenative synthesis is used
to improve the quality of the statistical system using a Local
Minimum Generation ...
A Pitch Marks Filtering Algorithm Based on Restricted Dynamic Programming
(Ninth International Conference on Spoken Language Processing. INTERSPEECH 2006, 2006-09-17)
In this paper, a generic pitch marks filtering algorithm (PMFA) is introduced in order to achieve reliable and smooth pitch marks
from any input pitch tracking or marking algorithm. The proposed PMFA ...
HMM-based Spanish speech synthesis using CBR as F0 estimator
(ITRW on Nonlinear Speech Processing, Paris, 22-25 of May 2007, 2007-05)
Hidden Markov Models based text-to-speech (HMM-TTS) syn thesis is a technique for generating speech from trained statisti cal models where spectrum, pitch and durations of basic speech
units are modelled ...
Multi-domain Text-to-Speech Synthesis by Automatic Text Classification
(Ninth International Conference on Spoken Language Processing. INTERSPEECH 2006, 2006-09-17)
This paper describes a multi-domain text-to-speech (MD-TTS)synthesis strategy for generating speech among different domainsand so increasing the flexibility of high quality TTS systems. Tothat ...
Text Classification based on Associative Relational Networks for Multi-Domain Text-to-Speech Synthesis
(The SIGIR Workshop on Directions in Computational Analysis of Stylistics in Text Retrieval, Seattle, August 2006, 2006-08)
This work is a step further in our research towards developing a new strategy for high quality text-to-speech (TTS)
synthesis among different domains. In this context, it is
necessary to select the most ...