Analysis and modification of excitation source characteristics for singing voice synthesis
Autor: | Gilles Degottex, Stefan Huber, Xavier Rodet, Axel Roebel |
---|---|
Přispěvatelé: | Analyse et synthèse sonores [Paris], Sciences et Technologies de la Musique et du Son (STMS), Institut de Recherche et Coordination Acoustique/Musique (IRCAM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche et Coordination Acoustique/Musique (IRCAM)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), ircam, ircam |
Jazyk: | francouzština |
Rok vydání: | 2012 |
Předmět: |
Computer science
Speech recognition Speech synthesis Glottal pulse parameter estimation computer.software_genre 01 natural sciences Vibrato Singing voice synthesis Harmonic analysis 030507 speech-language pathology & audiology 03 medical and health sciences 0103 physical sciences Glottal pulse speech transformation 010301 acoustics [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing [SPI.ACOU]Engineering Sciences [physics]/Acoustics [physics.class-ph] [SPI.ACOU] Engineering Sciences [physics]/Acoustics [physics.class-ph] [SCCO.NEUR]Cognitive science/Neuroscience [SCCO.NEUR] Cognitive science/Neuroscience Estimator Speech processing singing synthesis Singing 0305 other medical science computer [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing |
Zdroj: | International Conference on Audio, Speech and Signal Processing (ICASSP) International Conference on Audio, Speech and Signal Processing (ICASSP), Mar 2012, Kyoto, France. pp.5381-5384 ICASSP |
Popis: | cote interne IRCAM: Roebel12a; None / None; National audience; The present article investigates into the use of the LF glottal pulse model for singing synthesis and transformation. A recent estima- tor of the LF-glottal pulse shape parameter (rd) is used to analyze a small collection of professional singing examples and the results are discussed in the context of recent findings relating the rd shape parameter to other speech signal parameters (intensity and vibrato). We propose a rd shape parameter model for vibrato rendering and present an algorithm that allows modifying the glottal pulse shape parameter of a given speech signal and is used to enhance the vibrato generation in a speech to singing transformation system. |
Databáze: | OpenAIRE |
Externí odkaz: |