Skip to main content
Search

# Audio-Language Model

2 related articles

Subscribe to updates
  1. arXiv

    A frozen general-audio codec can locate sounds too: AURA beats the strongest dedicated system by 10.31 points in dual-source direction accuracy

    AURA couples X-Codec, a general-audio codec trained without spatial supervision, directly to a frozen Qwen3-8B language model through a six-slot binaural representation and scene supervision. Dedicated spatial systems instead rely on a separately trained spatial encoder, and an answer-only interface stays at chance on left/right. On dual-source SpatialSoundQA, AURA's direction accuracy exceeds the strongest dedicated system, DSpAST-BAT†, by 10.31 points with about 40% of its trainable parameters.

    Boyan Han（First author）
    AURASpatial Audio Question AnsweringResidual Vector QuantizationAudio-Language Model
  2. arXiv

    Structured Skill Optimization Under Frozen Weights: A New Path for Audio Anti-Fraud Detection

    Without changing any parameters of the audio-language model, FRAUDSkill optimizes an external layer of skill programs, routing policies, and decision rules and combines structured output control with validation-guided multi-path inference, raising Macro-F1 on the TeleAntiFraud benchmark from 41.54% for the shared frozen-model baseline to 73.50% while cutting the invalid-output rate from 36.04% to 1.94%.

    Peking UniversityNortheastern UniversityChina People's Public Security University
    Chengxian Hu（First author）
    FRAUDSkillFrozen-Weight Skill OptimizationTelecom Fraud DetectionAudio-Language Model

You’re all caught up