Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models

arXiv:2609.00727 · cs.SD, cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.SD, cs.AI

Submitted: 2026-09-01

Updated: 2026-09-01

Terminology

• Accuracy — 32× in this paper · explained in 1 episode
• Linear probe — 9× in this paper · explained in 2 episodes
• Linear Probing — 5× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Benchmark — 3× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Personalization — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Activation Patching — 1× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Training — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Gradient Reversal Layer — 1× in this paper
• Grounding — 1× in this paper · explained in 3 episodes
• Hilbert-Schmidt Independence Criterion — 1× in this paper
• In International Conference on Machine Learning — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Self-Supervised Learning — 1× in this paper · explained in 7 episodes
• Steering — 1× in this paper · explained in 2 episodes

Sources

• FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning
• Qwen2-Audio Technical Report
• Mellow: a small audio language model for reasoning
• SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation
• Kosmos-G: Generating Images in Context with Multimodal Large Language Models
• Kosmos-2: Grounding Multimodal Large Language Models to the World
• Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling
• One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models
• Towards End-to-End Private Automatic Speaker Recognition
• Qwen2.5-Omni Technical Report
• Representation Engineering: A Top-Down Approach to AI Transparency

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
• WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
• Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment