Robustness of Voice Conversion Techniques Under Mismatched Conditions

Most of the existing studies on voice conversion (VC) are conducted in acoustically matched conditions between source and target signal. However, the robustness of VC methods in presence of mismatch remains unknown. In this paper, we report a comparative analysis of different VC techniques under mismatched conditions. The extensive experiments with five different VC techniques on CMU ARCTIC corpus suggest that performance of VC methods substantially degrades in noisy conditions. We have found that bilinear frequency warping with amplitude scaling (BLFWAS) outperforms other methods in most of t...

Voice Conversion using Convolutional Neural Networks

The human auditory system is able to distinguish the vocal source of thousands of speakers, yet not much is known about what features the auditory system uses to do this. Fourier Transforms are capable of capturing the pitch and harmonic structure of the speaker but this alone proves insufficient at identifying speakers uniquely. The remaining structure, often referred to as timbre, is critical to identifying speakers but we understood little about it. In this paper we use recent advances in neural networks in order to manipulate the voice of one speaker into another by transforming not only t...

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

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 sma...

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

We propose a flexible framework for spectral conversion (SC) that facilitates training with unaligned corpora. Many SC frameworks require parallel corpora, phonetic alignments, or explicit frame-wise correspondence for learning conversion functions or for synthesizing a target spectrum with the aid of alignments. However, these requirements gravely limit the scope of practical applications of SC due to scarcity or even unavailability of parallel corpora. We propose an SC framework based on variational auto-encoder which enables us to exploit non-parallel corpora. The framework comprises an enc...

Voice Conversion Using Coefficient Mapping and Neural Network

The research presents a voice conversion model using coefficient mapping and neural network. Most previous works on parametric speech synthesis did not account for losses in spectral details causing over smoothing and invariably, an appreciable deviation of the converted speech from the targeted speaker. An improved model that uses both linear predictive coding (LPC) and line spectral frequency (LSF) coefficients to parametrize the source speech signal was developed in this work to reveal the effect of over-smoothing. Non-linear mapping ability of neural network was employed in mapping the sou...

High quality voice conversion using prosodic and high-resolution spectral features

Voice conversion methods have advanced rapidly over the last decade. Studies have shown that speaker characteristics are captured by spectral feature as well as various prosodic features. Most existing conversion methods focus on the spectral feature as it directly represents the timbre characteristics, while some conversion methods have focused only on the prosodic feature represented by the fundamental frequency. In this paper, a comprehensive framework using deep neural networks to convert both timbre and prosodic features is proposed. The timbre feature is represented by a high-resolution ...

Reducing one-to-many problem in Voice Conversion by equalizing the formant locations using dynamic frequency warping

In this study, we investigate a solution to reduce the effect of one-to-many problem in voice conversion. One-to-many problem in VC happens when two very similar speech segments in source speaker have corresponding speech segments in target speaker that are not similar to each other. As a result, the mapper function usually over-smoothes the generated features in order to be similar to both target speech segments. In this study, we propose to equalize the formant location of source-target frame pairs using dynamic frequency warping in order to reduce the complexity. After the conversion, anoth...