Cross-lingual personalized speech generation seeks to synthesize a target speaker's voice
from only a few training samples that are in a different language. One popular technique is to …

We propose a novel training scheme to optimize voice conversion network with a speaker
identity loss function. The training scheme not only minimizes frame-level spectral loss, but …

We study a novel neural speaker encoder and its training strategies for speaker recognition
without using any identity labels. The speaker encoder is trained to extract a fixed …

This paper presents a cross-lingual voice conversion framework that adopts a modularized
neural network. The modularized neural network has a common input structure that is …

Abstract Cross-Lingual Voice Conversion (XVC) aims to modify a source speaker identity
towards a target while preserving the source linguistic content. This paper introduces a cycle …

One-shot voice conversion has received significant attention since only one utterance from
source speaker and target speaker respectively is required. Moreover, source speaker and …

We study a novel neural architecture and its training strategies of speaker encoder for
speaker recognition without using any identity labels. The speaker encoder is trained to …

Cross-lingual voice conversion (VC) is a task that aims to synthesize target voices with the
same content while source and target speakers speak in different languages. Its challenge …

Voice conversion aims to change the timber of the source speaker to that of the target
speaker without changing the speech content. The cross-lingual voice conversion requires …

In our daily life, humans can recognize the person based on their facial and voice
characteristics. Research in biology has proved that speech and face modalities can provide …