Same-class controls isolate local audio evidence in model answers
Different-class edits change answers 49.7 to 60.9 points more often than matched same-class replacements.
Stories per day · 30 days
1 RSS
Relatedacoustic-perception1benchmark1evaluation1linear-probing1local-edits1music1persona1reinforcement-learning1soundscapes1supervised-fine-tuning1vocalgrad1
5 stories, newest first · one card per story
Stories tagged #audio-language-models
MusicTwins post-trains Audio Flamingo Next to match a listener persona
On ten held-out personas, fine-tuning and reinforcement learning improved personality, style, and music responses.
VocalGrad finds audio language models near chance on acoustic change
Human annotators score high on binary temporal-change classification while models stay near chance.
Do Audio Language Models Hear and Read Distinctive Features Alike?
Study finds most audio language models do not align heard and read features, except voicing in Qwen2.5-Omni.
FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection
FRAUDSkill adapts frozen audio-language models for telecom fraud detection via external skill programs, reaching 73.50% Macro-F1.