7 papers
LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs
Thanapat Trachu, Samuele Cornell, William Chen +1
Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing computational costs. Dynamic frame ra…
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…
Speech Generation Speaker Poisoning: Capability Erasure in Zero-Shot Text-to-Speech
Thanapat Trachu, Thanathai Lertpetchpun, Sai Praneeth Karimireddy +1
Recent zero-shot Text-to-Speech (TTS) systems can clone previously unseen voices from only a few seconds of audio. We formulate Speech Generation Speaker Poisoning (SGSP), a task t…
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…
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…
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…
Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridge
Thanapat Trachu, Chawan Piansaddhayanon, Ekapol Chuangsuwanich
Diffusion-based speech enhancement has shown promising results, but can suffer from a slower inference time. Initializing the diffusion process with the enhanced audio generated by…