4 papers · 1 filter
Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs
Jing Peng, Zichao Nie, Zhisheng Zhang +2
Large Audio Language Models (LALMs) utilize either continuous features or discrete tokens, yet the optimal representation paradigm for general audio understanding remains debated.…
Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
Xiang Li, Yixuan Zhou, Jingran Xie +2
Neural speech codecs based on Vector-Quantized VAEs (VQ-VAEs) are core audio tokenizers for speech LLMs, yet their reconstruction fidelity is bottlenecked by quantization error. Mo…
Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
Haiyun Li, Shuhai Peng, Zhisheng Zhang +4
Audio watermarking aims to embed identifiable information into audio while remaining imperceptible. Existing methods adopt high-fidelity, low-energy designs to preserve perceptual…
VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents
Haiyun Li, Zhiyong Wu, Xiaofeng Xie +3
Voice cloning (VC)-resistant watermarking is an emerging technique for tracing and preventing unauthorized cloning. Existing methods effectively trace traditional VC models by trai…