An artificial neural network is one of the most important models for training features of voice conversion (VC) tasks. Typically, neural networks (NNs) are very effective in processing nonlinear features, such as mel cepstral coefficients (MCC) which represent the spectrum features. However, a simple representation for fundamental frequency (F0) is not enough for neural networks to deal with an...

So far, cross-language voice conversion requires at least one bilingual speaker and parallel speech data to perform the training. This paper shows how these obstacles can be overcome by means of a recently presented text-independent training method based on unit selection. The new method is evaluated in the framework of the European speech-to-speech translation project TC-Star and achieves a pe...

Voice conversion method is applied to synthesizing emotional speech from standard reading (neutral) speech. Pairs of neutral speech and emotional speech are used for conversion rule training. The conversion adopts GMM (Gaussian Mixture Model) with DFW (Dynamic Frequency Warping). We also adopt STRAIGHT, the high-quality speech analysis-synthesis algorithm. As conversion target emotions, (Hot) a...

This paper studies the inclusion of glottal source characteristics in voice conversion (VC) systems. We use source/filter decomposition to parametrize the vocal tract using LSF, the glottal source using the LF model, and the aspiration noise using amplitude-modulated high-pass filtered AWGN noise. To evaluate the impact of this new parametrization in VC, we use a reference conversion system tha...

In this paper, we propose a hybrid system based on a modified statistical GMM voice conversion algorithm for improving the recognition of esophageal speech. This hybrid system aims to compensate for the distorted information present in the esophageal acoustic features by using a voice conversion method. The esophageal speech is converted into a "target" laryngeal speech using an iterative stati...

Voice conversion is a technique for modifying a source speaker’s speech to sound as if it was spoken by a target speaker. A popular approach to voice conversion is to apply a linear transformation to the spectral envelope. However, conventional parameter estimation based on least square error optimization does not necessarily lead to the best perceptual result. In this paper, a perceptually wei...

The Voice Conversion Challenge (VCC) 2016, one of the special sessions at Interspeech 2016, deals with the well-known task of speaker identity conversion, referred as Voice Conversion (VC). The objective of the VCC is to compare various VC techniques on identical training and evaluation speech data. The full description of VCC 2016, the motivation, the database, the rules, the participants and ...

In this paper, we propose modeling a noisy-channel for the task of voice conversion (VC). We have used the artificial neural networks (ANN) to capture speaker-specific characteristics of a target speaker which avoid the need for any training utterance from a source speaker. We use articulatory features (AFs) as a canonical form or speaker-independent representation of a speech signal. Our studi...

In this paper, we propose modeling a noisy-channel for the task of voice conversion (VC). We have used the artificial neural networks (ANN) to capture speaker-specific characteristics of a target speaker which avoid the need for any training utterance from a source speaker. We use articulatory features (AFs) as a canonical form or speaker-independent representation of a speech signal. Our studi...

Voice changing has many applications in the industry and commercial filed. This paper emphasizes voice conversion using a pitch shifting method which depends on detecting the pitch of the signal (fundamental frequency) using Simplified Inverse Filter Tracking (SIFT) and changing it according to the target pitch period using time stretching with Pitch Synchronous Over Lap Add Algorithm (PSOLA), ...