Dictionary Update for NMF-based Voice Conversion Using an Encoder-Decoder Network

10/13/2016
by   Chin-Cheng Hsu, et al.
0

In this paper, we propose a dictionary update method for Nonnegative Matrix Factorization (NMF) with high dimensional data in a spectral conversion (SC) task. Voice conversion has been widely studied due to its potential applications such as personalized speech synthesis and speech enhancement. Exemplar-based NMF (ENMF) emerges as an effective and probably the simplest choice among all techniques for SC, as long as a source-target parallel speech corpus is given. ENMF-based SC systems usually need a large amount of bases (exemplars) to ensure the quality of the converted speech. However, a small and effective dictionary is desirable but hard to obtain via dictionary update, in particular when high-dimensional features such as STRAIGHT spectra are used. Therefore, we propose a dictionary update framework for NMF by means of an encoder-decoder reformulation. Regarding NMF as an encoder-decoder network makes it possible to exploit the whole parallel corpus more effectively and efficiently when applied to SC. Our experiments demonstrate significant gains of the proposed system with small dictionaries over conventional ENMF-based systems with dictionaries of same or much larger size.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/13/2016

Voice Conversion from Non-parallel Corpora Using Variational Auto-encoder

We propose a flexible framework for spectral conversion (SC) that facili...
research
07/13/2022

Subband-based Generative Adversarial Network for Non-parallel Many-to-many Voice Conversion

Voice conversion is to generate a new speech with the source content and...
research
01/18/2023

A variational autoencoder-based nonnegative matrix factorisation model for deep dictionary learning

Construction of dictionaries using nonnegative matrix factorisation (NMF...
research
08/13/2018

ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder

This paper proposes a non-parallel many-to-many voice conversion (VC) me...
research
06/30/2020

A Speech Enhancement Algorithm based on Non-negative Hidden Markov Model and Kullback-Leibler Divergence

In this paper, we propose a novel supervised single-channel speech enhan...
research
09/16/2017

Speech Dereverberation Using Nonnegative Convolutive Transfer Function and Spectro temporal Modeling

This paper presents two single channel speech dereverberation methods to...
research
10/19/2022

Two-stage training method for Japanese electrolaryngeal speech enhancement based on sequence-to-sequence voice conversion

Sequence-to-sequence (seq2seq) voice conversion (VC) models have greater...

Please sign up or login with your details

Forgot password? Click here to reset