Many-to-Many Voice Conversion based on Bottleneck Features with Variational Autoencoder for Non-parallel Training Data

Yanping Li, Kong Aik Lee, Yougen Yuan, Haizhou Li, Zhen Yang

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

6 Citations (Scopus)

Abstract

This paper proposes a novel approach to many-to-many (M2M) voice conversion for non-parallel training data. In the proposed approach, we first obtain bottleneck features (BNFs) as speaker representations from a deep neural network (DNN). Then, a variational autoencoder (VAE) implements the mapping function (i.e., a reconstruction process) using both the latent semantic information and the speaker representations. Furthermore, we propose an adaptive scheme by intervening the training process of the DNN, which can enrich the target speaker's personality feature space in the case of limited training data. Our approach has three advantages: 1) neither parallel training data nor explicit frame alignment process is required; 2) consolidates multiple pair-wise systems into a single M2M model (many-source speakers to many-target speakers); 3) expands M2M conversion task from closed set to open set when the training data of target speaker is very limited. The objective and subjective evaluations show that our proposed approach outperforms the baseline system.

Original languageEnglish
Title of host publication2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages829-833
Number of pages5
ISBN (Electronic)9789881476852
DOIs
Publication statusPublished - 2 Jul 2018
Externally publishedYes
Event10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Honolulu, United States
Duration: 12 Nov 201815 Nov 2018

Publication series

Name2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018 - Proceedings

Conference

Conference10th Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2018
Country/TerritoryUnited States
CityHonolulu
Period12/11/1815/11/18

ASJC Scopus subject areas

  • Information Systems

Fingerprint

Dive into the research topics of 'Many-to-Many Voice Conversion based on Bottleneck Features with Variational Autoencoder for Non-parallel Training Data'. Together they form a unique fingerprint.

Cite this