Speech is the fundamental mode of human communication, and its synthesis has long been
a core priority in human–computer interaction research. In recent years, machines have …

Speech-driven 3D face animation aims to generate realistic facial expressions that match
the speech content and emotion. However, existing methods often neglect emotional facial …

Style transfer TTS has shown impressive performance in recent years. However, style
control is often restricted to systems built on expressive speech recordings with discrete style …

While the performance of cross-lingual TTS based on monolingual corpora has been
significantly improved recently, generating cross-lingual speech still suffers from the foreign …

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a
variant of the standard version (L1), which is challenging as L2 is different from L1 in terms …

Previous multilingual text-to-speech (TTS) approaches have considered leveraging
monolingual speaker data to enable cross-lingual speech synthesis. However, such data …

Emotional Text-to-Speech (E-TTS) synthesis has gained significant attention in recent years
due to its potential to enhance human-computer interaction. However, current E-TTS …

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a
variant of the standard version (L1). Accented TTS synthesis is challenging as L2 is different …

Zero-shot emotion transfer in cross-lingual speech synthesis aims to transfer emotion from
an arbitrary speech reference in the source language to the synthetic speech in the target …

Neural text-to-speech systems are often optimized on L1/L2 losses, which make strong
assumptions about the distributions of the target data space. Aiming to improve those …