13 papers
Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: A Case Study on Accent Information
Shih-Heng Wang, Tiantian Feng, Aditya Kommineni +4
Neural Audio Codecs (NACs) are widely adopted in modern speech systems, yet how they encode linguistic and paralinguistic information remains unclear. Improving the interpretabilit…
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…
Trade-offs Between Capacity and Robustness in Neural Audio Codecs for Adversarially Robust Speech Recognition
Jordan Prescott, Thanathai Lertpetchpun, Shrikanth Narayanan
Adversarial perturbations exploit vulnerabilities in automatic speech recognition (ASR) systems while preserving human perceived linguistic content. Neural audio codecs impose a di…
Learning-free L2-Accented Speech Generation using Phonological Rules
Thanathai Lertpetchpun, Yoonjeong Lee, Jihwan Lee +3
Accent plays a crucial role in speaker identity and inclusivity in speech technologies. Existing accented text-to-speech (TTS) systems either require large-scale accented datasets…
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…