Year: 2019
Type: preprint
Abstract: End-to-end models for raw audio generation are a challenge, specially if they have to work with non-parallel data, which is a desirable setup in many situations. Voice conversion, in which a model has to impersonate a speaker in a recording, is one of those situations. In this paper, we propose Blow, a single-scale normalizing flow using hypernetwork conditioning to perform many-to-many voice conversion between raw audio. Blow is trained end-to-end, with non-parallel data, on a frame-by-frame basis using a single speaker identifier. We show that Blow compares favorably to existing flow-based architectures and other competitive baselines, obtaining equal or better performance in both objective and subjective evaluations. We further assess the impact of its main components with an ablation study, and quantify a number of properties such as the necessary amount of training data or the preference for source or target speakers.
Source: arXiv (Cornell University)
Authors: Serrà, Joan, Pascual, Santiago, Segura, Carlos
Institutions: Telefónica (Spain), Universitat Politècnica de Catalunya
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2947196194