The main goal of a voice conversion system is to modify the voice of a source speaker, in order to be perceived as if it had been uttered by another specific speaker. Many approaches found in the literature convert only the features related to the vocal tract of the speaker. Our proposal is to convert those characteristics, and to process the signal passing through the vocal chords. Thus, the g...

This paper describes the Voice Conversion Challenge 2016 devised by the authors to better understand different voice conversion (VC) techniques by comparing their performance on a common dataset. The task of the challenge was speaker conversion, i.e., to transform the voice identity of a source speaker into that of a target speaker while preserving the linguistic content. Using a common dataset...

This paper presents a novel method for modeling the one-way quality prediction of VoIP, non-intrusively. Intrusive measures of voice quality suffer from common deficiency that is the need of reference signal for evaluating the quality of voice. Owing to this lack, a great deal of effort has been recently devoted for modeling voice quality prediction non-intrusively according to quality degradat...

Voice conversion is a technique for modifying a source speaker’s speech to sound as if it was spoken by a target speaker. The conventional solutions to this problem are based on training and applying conversion functions which require a substantial amount of training data from both the source and the target speaker. In this paper, we present a voice conversion technique that requires no preexis...

Learners of a second language practice their pronunciation by listening to and imitating utterances from native speakers. Recent research has shown that choosing a well-matched native speaker to imitate can have a positive impact on pronunciation training. Here we propose a voice-transformation technique that can be used to generate the (arguably) ideal voice to imitate: the own voice of the le...

There is a need to improve the synthesis quality of HiFi-GAN-based real-time neural speech waveform generative models on CPUs while preserving controllability fundamental frequency ( $f_{\mathrm{o}}$ ) and rate (SR). For this purpose, w...

Voice over Internet Protocol (VoIP) is being widely deployed to offer users low-cost alternatives for long-distance and international telephone calls. However, for users who are accustomed to the high-quality sound offered by traditional Public Switched Telephone Network (PSTN) service, VoIP voice quality often pales in comparison. Voice quality in VoIP networks widely varies as a result of sev...

The current practice in virtual human dialogue systems is to use professional human recordings or limited-domain speech synthesis. Both approaches lead to good performance but at a high cost. To determine the best trade-off between performance and cost, we perform a systematic evaluation of human and synthesized voices with regard to naturalness, conversational aspect, and likability. We also v...