Beyond the Transcript: Measuring and Improving the Use of Acoustic Information in Audio Language Models
cs.CL
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/rany2/edge-tts
Terminology
Sources
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems
- When Audio-LLMs Don't Listen: A Cross-Linguistic Study of Modality Arbitration
- Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance
- Qwen2-Audio Technical Report
- Closing the Gap Between Text and Speech Understanding in LLMs
- MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
- LLM can Read Spectrogram: Encoder-free Speech-Language Modeling
- All That Glitters Is Not Audio: Rethinking Text Priors and Audio Reliance in Audio-Language Evaluation
- Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models
- Gemma 4 Technical Report
- Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
- Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
- Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models
- MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models
- Distilling an End-to-End Voice Assistant Without Instruction Training Data
- Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding
- LoRA: Low-Rank Adaptation of Large Language Models
- Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
- Kimi-Audio Technical Report
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data