Restricted Boltzmann Machine-Based Voice Conversion for Nonparallel Corpus
Author:
- 8 June 2017
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 24 (8) , 1103-1107
Abstract
A large amount of parallel training corpus is necessary for robust, high-quality voice conversion. However, such parallel data may not always be available. This letter presents a new voice conversion method that needs no parallel speech corpus, and adopts a restricted Boltzmann machine (RBM) to represent the distribution of the spectral features derived from a target speaker. A linear transformation was employed to convert the spectral and delta features. A conversion function was obtained by maximizing the conditional probability density function with respect to the target RBM. A feasibility test was carried out on the OGI VOICES corpus. Results from the subjective listening tests and the objective results both showed that the proposed method outperforms the conventional GMM-based method.Keywords
Funding Information
- Konkuk University in 2015
This publication has 16 references indexed in Scilit:
- Non-Parallel Training in Voice Conversion Using an Adaptive Restricted Boltzmann MachineIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016
- Whisper‐to‐speech conversion using restricted Boltzmann machine arraysElectronics Letters, 2014
- Modeling Spectral Envelopes Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech SynthesisIEEE Transactions on Audio, Speech, and Language Processing, 2013
- Voice Conversion Based on Maximum-Likelihood Estimation of Spectral Parameter TrajectoryIEEE Transactions on Audio, Speech, and Language Processing, 2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Nonparallel training for voice conversion based on a parameter adaptation approachIEEE Transactions on Audio, Speech, and Language Processing, 2006
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov modelsComputer Speech & Language, 1995
- Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphonesSpeech Communication, 1990
- An Algorithm for Vector Quantizer DesignIEEE Transactions on Communications, 1980