Un algorithme temporel permettant de modifier la prosodie de la parole tout en conservant le naturel du timbre a été proposé récemment dans le contexte de la synthèse par diphones [1]. Cet algorithme est fondé sur le méthode de l'addition-recouvrement synchrone de la fréquence fondamentale (PSOLA) de formes d'onde temporelle. Nous étudions dans cet article les raisons pour lesquelles cet algorithme conceptuellement simple permet d'obtenir des modifications de haute qualité. Nous montrons notamment que deux types de distortion sont possibles, selon la longueur de la fenêtre de synthèse: (1) élargissement de la bande passante des formants pour des fenêtres de synthèse courtes (2) effet de réverbération pour des fenêtres longues. Un compromis ...
Generally defined, speech modification is the process of changing certain perceptual properties of s...
This paper presents some preliminary methods to apply the Time- Frequency Interpolation technique - ...
Coexistence of different formats for cinema (24 frames/s) andvideo (25 frames/s) involves speeding u...
The duration of a speech passage can be altered using audio time-scale modification techniques. Time...
The duration of a speech passage can be altered using audio time-scale modification techniques. Time...
The development of algorithms for synthesizing audio and speech has been a topic of interest for sev...
Le domaine de recherche de la modification de durée d'un signal audio est actif depuis plus d'une qu...
The duration of a speech passage can be altered using audio time-scale modification techniques. Time...
Concatenative synthesis becomes more and more popular nowadays because of its high naturalness and ...
International audienceA new light is thrown on the Portnoff [1] speech signal timescale modification...
A new light is thrown on the Portnoff [1] speech signal time-scale modification algorithm. It is sho...
La parole produite en plongée profonde, et que nous qualifierons d'hyperbare, présente une variété d...
In this paper, an algorithm for the concatenation of speech signal segments taken from disjoint utte...
SIGLEINIST T 77137 / INIST-CNRS - Institut de l'Information Scientifique et TechniqueFRFranc
In this work, we look for methods providing a local variation of the time-frequency resolution for s...
Generally defined, speech modification is the process of changing certain perceptual properties of s...
This paper presents some preliminary methods to apply the Time- Frequency Interpolation technique - ...
Coexistence of different formats for cinema (24 frames/s) andvideo (25 frames/s) involves speeding u...
The duration of a speech passage can be altered using audio time-scale modification techniques. Time...
The duration of a speech passage can be altered using audio time-scale modification techniques. Time...
The development of algorithms for synthesizing audio and speech has been a topic of interest for sev...
Le domaine de recherche de la modification de durée d'un signal audio est actif depuis plus d'une qu...
The duration of a speech passage can be altered using audio time-scale modification techniques. Time...
Concatenative synthesis becomes more and more popular nowadays because of its high naturalness and ...
International audienceA new light is thrown on the Portnoff [1] speech signal timescale modification...
A new light is thrown on the Portnoff [1] speech signal time-scale modification algorithm. It is sho...
La parole produite en plongée profonde, et que nous qualifierons d'hyperbare, présente une variété d...
In this paper, an algorithm for the concatenation of speech signal segments taken from disjoint utte...
SIGLEINIST T 77137 / INIST-CNRS - Institut de l'Information Scientifique et TechniqueFRFranc
In this work, we look for methods providing a local variation of the time-frequency resolution for s...
Generally defined, speech modification is the process of changing certain perceptual properties of s...
This paper presents some preliminary methods to apply the Time- Frequency Interpolation technique - ...
Coexistence of different formats for cinema (24 frames/s) andvideo (25 frames/s) involves speeding u...