Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural
speech given text, is a hot research topic in speech, language, and machine learning …

Adaptive text to speech (TTS) can synthesize new voices in zero-shot scenarios efficiently,
by using a well-trained source TTS model without adapting it on the speech data of new …

Abstract Recent Text-to-Speech (TTS) systems trained on reading or acted corpora have
achieved near human-level naturalness. The diversity of human speech, however, often …

The majority of current Text-to-Speech (TTS) datasets, which are collections of individual
utterances, contain few conversational aspects. In this paper, we introduce DailyTalk, a high …

The rise of audio deepfakes presents a significant security threat that undermines trust in
digital communications and media. These synthetic audio technologies can convincingly …

Zero-shot speaker adaptation aims to clone an unseen speaker's voice without any
adaptation time and parameters. Previous researches usually use a speaker encoder to …

Speaking is one of the most important language capabilities (the others being listening,
reading, and writing) of human beings. Text-to-speech synthesis (TTS for short), which aims …

Spontaneous style speech synthesis, which aims to generate human-like speech, often
encounters challenges due to the scarcity of high-quality data and limitations in model …

Publishing open-source academic video recordings is an emergent and prevalent approach
to sharing knowledge online. Such videos carry rich multimodal information including …

Spontaneous speaking style exhibits notable differences from other speaking styles due to
various spontaneous phenomena (eg, filled pauses, prolongation) and substantial prosody …