Speaker identity is one of the important characteristics of human speech. In voice
conversion, we change the speaker identity from one to another, while keeping the linguistic …

Existing objective evaluation metrics for voice conversion (VC) are not always correlated
with human perception. Therefore, training VC models with such criteria may not effectively …

Evaluating synthetic speech generated by machines is a complicated process, as it involves
judging along multiple dimensions including naturalness, intelligibility, and whether the …

The release of WaveNet and Tacotron has forever transformed the speech synthesis
landscape. Thanks to these game-changing innovations, the quality of synthetic speech has …

In this paper, we explore the possibility of using the WaveNet architecture as a statistical
vocoder. In that case, the generation of speech waveforms is locally conditioned only by …

Many audio processing tasks require perceptual assessment. However, the time and
expense of obtaining``gold standard''human judgments limit the availability of such data …

The quality of speech synthesis systems can be significantly deteriorated by the presence of
background noise in the recordings. Despite the existence of speech enhancement …

A problem when developing and tuning speech synthesis systems is that there is no well-
established method of automatically rating the quality of the synthetic speech. This research …

The quality of current commercial speech synthesis systems is now so high that system
improvements are being made at subtle sub-and supra-segmental levels. Human perceptual …

In communication systems, it is crucial to estimate the perceived quality of audio and
speech. The industrial standards for many years have been PESQ, 3QUEST, and POLQA …