J
Juana M. Gutiérrez-Arriola
Researcher at Technical University of Madrid
Publications - 35
Citations - 370
Juana M. Gutiérrez-Arriola is an academic researcher from Technical University of Madrid. The author has contributed to research in topics: Speech synthesis & Prosody. The author has an hindex of 9, co-authored 33 publications receiving 349 citations.
Papers
More filters
Proceedings Article
Emotional speech synthesis: from speech database to TTS.
Juan Manuel Montero,Juana M. Gutiérrez-Arriola,Sira E. Palazuelos,Emilia Enríquez,Santiago Aguilera,José Manuel Pardo +5 more
TL;DR: A through study of emotional speech in Spanish, and its application to TTS, and a prototype system that simulates emotional speech using a commercial synthesiser are presented.
Analysis and modelling of emotional speech in spanish
TL;DR: In this article, the authors present the prosodic analysis, modelling and evaluation of the Spanish Emotional Speech Database including four emotions: happiness, sadness, cold anger, and surprise.
Journal ArticleDOI
Characterization of Dysphonic Voices by Means of a Filterbank-Based Spectral Analysis: Sustained Vowels and Running Speech
Rubén Fraile,Juan Ignacio Godino-Llorente,Nicolás Sáenz-Lechón,Víctor Osma-Ruiz,Juana M. Gutiérrez-Arriola +4 more
TL;DR: The reported results indicate that only minor differences exist in the shape of the power spectrum of normal and dysphonic voices when performing sustained vowel phonation tasks, however, the calculated band power decorrelation times indicate that power in bands between 2000 and 6400Hz is significantly less stable in dysphonia.
Proceedings Article
Development of an emotional speech synthesiser in Spanish.
Juan Manuel Montero,Juana M. Gutiérrez-Arriola,José Colás,Javier Macías Guarasa,Emilia Enríquez,José Manuel Pardo +5 more
TL;DR: Two experiments are performed aimed at developing a concatenative emotional synthesiser, a synthesiser that can copy the quality of an emotional voice without an explicit mathematical model.
Proceedings Article
Automatic modeling of duration in a Spanish text-to-speech system using neural networks.
Ricardo de Córdoba,José A. Vallejo,Juan Manuel Montero,Juana M. Gutiérrez-Arriola,M. A. López,José Manuel Pardo +5 more
TL;DR: This work presents a complete environment in which to decide which parameters are more relevant in different situations and the best way to code them, based in a neural network absolutely configurable, including the contextual effects using windows of variable length.