Text Scores Do Not Establish Performance on Lexically Non-Diagnostic Speech Tasks: A Qwen2-Audio Quantization Case Study
cs.SD, cs.CL, eess.AS
Submitted: 2026-09-20
Updated: 2026-10-06
Code: https://github.com/MENGZHEGENG/speechllm-quantization
Terminology
Sources
- Qwen2-Audio Technical Report
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- From Semantics to Readout: Mechanistic Understanding of Audio Tokens after Fine-Tuning for Temporal Audio Grounding
- Efficient Speech Translation through Model Compression and Knowledge Distillation
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
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