activity
20242026
collaborators

15 papers

cs.SD2026

Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System

Thomas Thebaud, Sonal Joshi, Henry Li +4

Poisoning attacks entail attackers intentionally tampering with training data. In this paper, we consider a dirty-label poisoning attack scenario on a speech commands classificatio…

cs.SD2026

Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation

Thomas Thebaud, Yuzhe Wang, Laureano Moro-Velazquez +2

Speech-aware large language models (LLMs) can accept speech inputs, yet their training objectives largely emphasize linguistic content or specific fields such as emotions or the sp…

cs.CL2026

Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models

Alexandrine Fortier, Thomas Thebaud, Jesús Villalba +3

Speech language models (SLMs) are systems of systems: independent components that unite to achieve a common goal. Despite their heterogeneous nature, SLMs are often studied end-to-…

eess.AS2026

DiT-Flow: Speech Enhancement Robust to Multiple Distortions based on Flow Matching in Latent Space and Diffusion Transformers

Tianyu Cao, Helin Wang, Ari Frummer +7

Recent advances in generative models, such as diffusion and flow matching, have shown strong performance in audio tasks. However, speech enhancement (SE) models are typically train…

eess.AS2026

Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec

Junhyeok Lee, Xiluo He, Jihwan Lee +6

Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation improves encoded representations, it do…

eess.AS2026

MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances

Junhyeok Lee, Helin Wang, Yaohan Guan +4

We introduce MaskVCT, a zero-shot voice conversion (VC) model that offers multi-factor controllability through multiple classifier-free guidances (CFGs). While previous VC models r…