5 papers
Targeted Speaker Poisoning Framework in Zero-Shot Text-to-Speech
Thanapat Trachu, Thanathai Lertpetchpun, Sai Praneeth Karimireddy +1
Zero-shot Text-to-Speech (TTS) voice cloning poses severe privacy risks, demanding the removal of specific speaker identities from trained TTS models. Conventional machine unlearni…
Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data
Thanathai Lertpetchpun, Thanapat Trachu, Jihwan Lee +3
Accent is an integral part of society, reflecting multiculturalism and shaping how individuals express identity. The majority of English speakers are non-native (L2) speakers, yet…
Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis
Thanathai Lertpetchpun, Yoonjeong Lee, Thanapat Trachu +4
Many spoken languages, including English, exhibit wide variation in dialects and accents, making accent control an important capability for flexible text-to-speech (TTS) models. Cu…
Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking
Yuatyong Chaichana, Thanapat Trachu, Peerat Limkonchotiwat +3
In the era of large-scale training, model merging has evolved into a tool for creating multitasking models efficiently. It enables the knowledge of models to be fused, without the…
Amplifying Artifacts with Speech Enhancement in Voice Anti-spoofing
Thanapat Trachu, Thanathai Lertpetchpun, Ekapol Chuangsuwanich
Spoofed utterances always contain artifacts introduced by generative models. While several countermeasures have been proposed to detect spoofed utterances, most primarily focus on…