8 papers
Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR
Yuan Xie, Jiaqi Song, Xianliang Wang +3
Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross-lingual knowledge to achiev…
TI-StegoAlign: Channel-Guided Post-Training for Generative Text Steganography under Tokenization Inconsistency
Jiuan Zhou, Yuhao Xue, Yu Cheng +2
Generative text steganography enables LLM agents to exchange secret information through task-relevant messages. Yet most methods evaluate recovery on sender-side tokens, whereas th…
AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan
Yuankun Xie, Haonan Cheng, Jiayi Zhou +10
The rapid advancement of Audio Large Language Models (ALLMs) has enabled cost-effective, high-fidelity generation and manipulation of both speech and non-speech audio, including so…
A Full-Stack Performance Evaluation Infrastructure for 3D-DRAM-based LLM Accelerators
Cong Li, Chenhao Xue, Yi Ren +11
Large language models (LLMs) exhibit memory-intensive behavior during decoding, making it a key bottleneck in LLM inference. To accelerate decoding execution, hybrid-bonding-based…
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
Yuan Xie, Jiaqi Song, Guang Qiu +4
Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a dominant paradigm. Although recent LLM-based ASR models have shown promising performan…
Face-D(^2)CL: Multi-Domain Synergistic Representation with Dual Continual Learning for Facial DeepFake Detection
Yushuo Zhang, Yu Cheng, Yongkang Hu +3
Facial forgery techniques are advancing rapidly, posing severe threats to public trust and information security while imposing higher demands on the continual adaptation of DeepFak…
Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detection
Xiaoxuan Guo, Yuankun Xie, Haonan Cheng +5
Speech deepfake detection (SDD) focuses on identifying whether a given speech signal is genuine or has been synthetically generated. Existing audio large language model (LLM)-based…
Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs
Jun Xue, Yi Chai, Yanzhen Ren +6
Existing speech editing detection (SED) datasets are predominantly constructed using manual splicing or limited editing operations, resulting in restricted diversity and poor cover…