Exploració per altres contribucions "Bonafonte Cávez, Antonio"
Ara es mostren els items 21-31 de 31
-
Síntesis de voz mediante Modelos Ocultos de Markov
(Universitat Politècnica de Catalunya, 2008-11-27)
Projecte/Treball Final de Carrera
Accés obert -
Speech activity detection: Application-specific tuning and context-based neural approaches
(Universitat Politècnica de Catalunya, 2016-06)
Treball Final de Grau
Accés restringit per acord de confidencialitat -
Speech enhancement using deep learning
(Universitat Politècnica de Catalunya, 2017)
Treball Final de Grau
Accés obertThis thesis explores the possibility to achieve enhancement on noisy speech signals using Deep Neural Networks. Signal enhancement is a classic problem in speech processing. In the last years, researches using deep learning ... -
Study of the signal properties of music genres
(Universitat Politècnica de Catalunya, 2018-06)
Treball Final de Grau
Accés obertIn this project different features of the music signals are studied and evaluated, for a better understanding of its behaviour from the technical point of view, to attribute similar patrons to the different genres studied, ... -
Trombone Synthesis using Deep Learning
(Universitat Politècnica de Catalunya, 2017-10-18)
Treball Final de Grau
Accés obertIn this project we present a possible expansion of the sampleRNN project for trombone synthesis. The project is divided in three main blocks: the database creation, the sampleRNN analysis and the sampleRNN modification. ... -
Ultrasound based Silent Speech Interface using Deep Learning
(Universitat Politècnica de Catalunya, 2018-05-18)
Treball Final de Grau
Accés obert
Realitzat a/amb: Budapesti Műszaki és Gazdaságtudományi EgyetemSilent Speech Interface (SSI) is a technology able to synthesize speech in the absence of any acoustic signal. It can be useful in cases like laryngectomy patients, noisy environments or silent calls. This thesis explores ... -
Unsupervised learning for expressive speech synthesis
(Universitat Politècnica de Catalunya, 2017-09-12)
Tesi
Accés obertNowadays, especially with the upswing of neural networks, speech synthesis is almost totally data driven. The goal of this thesis is to provide methods for automatic and unsupervised learning from data for expressive speech ... -
Voice conversion using Deep Learning
(Universitat Politècnica de Catalunya, 2017-05-15)
Treball Final de Grau
Accés obertIn this project we present a first attempt at a Voice Conversion system based on Deep Learning in which the alignment between the training data is intrinsic to the model. Our system is structured in three main blocks. The ... -
Voice generation using deep learning
(Universitat Politècnica de Catalunya, 2016-09-28)
Treball Final de Grau
Accés obertVoice generation, also known as Speech Synthesis, is the artificial production of human speech. In the last decade, the Speech Synthesis research has been focused on a technique called Statistical Parametric Speech Synthesis. ... -
Voice source characterization for prosodic and spectral manipulation
(Universitat Politècnica de Catalunya, 2012-07-03)
Tesi
Accés obertThe objective of this dissertation is to study and develop techniques to decompose the speech signal into its two main components: voice source and vocal tract. Our main efforts are on the glottal pulse analysis and ... -
Word and paragraph embeddings for expresive speech synthesis
(Universitat Politècnica de Catalunya, 2017)
Treball Final de Grau
Accés obertSpeech synthesis is the task of generating speech using computers. Due to the limitations of classical techniques, these systems are normally not suitable for applications that would benefit from expressiveness in the ...