4 papers
ClariCodec: Optimising Neural Speech Codes for 200bps Communication using Reinforcement Learning
Junyi Wang, Chi Zhang, Jing Qian +4
In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary object…
Augmenting Open-Vocabulary Dysarthric Speech Assessment with Human Perceptual Supervision
Kaimeng Jia, Minzhu Tu, Zengrui Jin +2
Dysarthria is a speech disorder characterized by impaired intelligibility and reduced communicative effectiveness. Automatic dysarthria assessment provides a scalable, cost-effecti…
Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard
Yudong Yang, Xuezhen Zhang, Zhifeng Han +6
Recent progress in LLMs has enabled understanding of audio signals, but has also exposed new safety risks arising from complex audio inputs that are inadequately handled by current…
Multiplexing Neural Audio Watermarks
Zheqi Yuan, Yucheng Huang, Guangzhi Sun +2
Audio watermarking is essential for verifying speech authenticity, yet single-watermark schemes often struggle against sophisticated distortions such as neural reconstruction and a…