6 papers · 1 filter
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…
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…
Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe
Tiantian Feng, Kevin Huang, Anfeng Xu +6
We present Voxlect, a novel benchmark for modeling dialects and regional languages worldwide using speech foundation models. Specifically, we report comprehensive benchmark evaluat…
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…
Developing a Top-tier Framework in Naturalistic Conditions Challenge for Categorized Emotion Prediction: From Speech Foundation Models and Learning Objective to Data Augmentation and Engineering Choices
Tiantian Feng, Thanathai Lertpetchpun, Dani Byrd +1
Speech emotion recognition (SER), particularly for naturally expressed emotions, remains a challenging computational task. Key challenges include the inherent subjectivity in emoti…
Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker Traits and Speech Properties
Tiantian Feng, Jihwan Lee, Anfeng Xu +9
We introduce Vox-Profile, a comprehensive benchmark to characterize rich speaker traits and speech properties using speech foundation models. Unlike prior work that targets a singl…