Text-informed speech inpainting via voice conversion - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Text-informed speech inpainting via voice conversion


The problem of speech inpainting consists in recovering some parts in a speech signal that are missing for some reasons. To our best knowledge none of the existing methods allows satisfactory inpainting of missing parts of large size such as one second and longer. In this work we address this challenging scenario. Since in the case of such long missing parts entire words can be lost, we assume that the full text uttered in the speech signal is known. This leads to a new concept of text-informed speech inpainting. To solve this problem we propose a method that is based on synthesizing the missing speech by a speech synthesizer, on modifying its vocal characteristics via a voice conversion method, and on filling in the missing part with the resulting converted speech sample. We carried subjective listening tests to compare the proposed approach with two baseline methods.
Fichier principal
Vignette du fichier
eusipco16a.pdf (268.87 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01271257 , version 1 (08-02-2016)
hal-01271257 , version 2 (22-11-2016)


  • HAL Id : hal-01271257 , version 2


Pierre Prablanc, Alexey Ozerov, Ngoc Q. K. Duong, Patrick Pérez. Text-informed speech inpainting via voice conversion. 24th European Signal Processing Conference (EUSIPCO 2016), Aug 2016, Budapest, Hungary. ⟨hal-01271257v2⟩


235 View
405 Download


Gmail Facebook X LinkedIn More