arXiv:2603. 04219v2 Announce Type: replace-cross Abstract: We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis.
arXiv:2606. 26534v1 Announce Type: cross Abstract: Recently, zero-shot text-to-speech (TTS) has enabled high-fidelity and expressive speech synthesis, but it often fails to imitate unseen speaking styles from uncommon scenarios (e.
arXiv:2606. 14922v1 Announce Type: cross Abstract: For the last couple of years, the field of speech synthesis has improved dramatically thanks to deep learning.
arXiv:2609.25411v1 Announce Type: cross Abstract: Classifier-free Guidance (CFG) is widely adopted in text-to-speech (TTS) systems to enhance generation quality and conditioning fidelity by interpola...
arXiv:2610.07647v1 Announce Type: cross Abstract: Speech becomes less intelligible in noisy environments, and humans naturally adapt their voice to compensate. Inspired by this behavior, we investiga...
arXiv:2607. 26742v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) clones a voice from a short audio prompt, but this reliance on reference audio is a barrier when only visual information is available, e.
arXiv:2606. 14750v1 Announce Type: cross Abstract: Recent advances in pixel-based text modeling show that representing text as images enables models to exploit visual cues for language understanding.
arXiv:2607. 03134v1 Announce Type: cross Abstract: Recent research expands beyond binary anti-spoofing with the emergence of Source Tracing, the task of identifying the specific generative origins of synthetic speech.
arXiv:2608. 11590v1 Announce Type: cross Abstract: Human voice generation has made rapid progress in speech generation, singing voice generation, voice cloning, and voice editing.
The paper investigates how different speech content representations—such as SSL features, supervised tokens, posteriorgrams, and neural audio codecs—perform when used to train a generative model that produces audio conditioned only on each representation. By evaluating the generated audio on content, speaker identity, and prosody, the study identifies two regimes: some representations almost fully reconstruct the original audio, while others effectively separate speaker identity. The findings reveal that disentanglement of speaker identity depends on both the training objective and the representation’s information capacity, rather than supervision alone.
We propose GLASS, a framework for composable acoustic style control in zero-shot autoregressive text-to-speech (TTS) that learns controls from post-generation rewards rather than style labels. In zero-shot TTS, a speaker prompt often entangles speaker identity with prosodic attributes such as speaking rate and pitch, making it difficult to change style without changing the prompt itself.
arXiv:2608. 08638v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) now supports interactive assistants, personalized media, and accessibility tools.