Long-Term Memory-Guided Enhancement for Target Perception in Audio-Language Models
cs.SD, cs.AI, cs.CL
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/aynlp/ltm-audio-code
Terminology
Sources
- Qwen2-Audio Technical Report
- Kimi-Audio Technical Report
- Noise Adaptive Streaming Audio-Visual Speech Token Enhancement for Robust Full-Duplex Spoken Dialogue Models
- Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset
- DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement
- Text-Driven Separation of Arbitrary Sounds
- EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillation
- Separate What You Describe: Language-Queried Audio Source Separation
- SEGAN: Speech Enhancement Generative Adversarial Network
- GAPS: A Large and Diverse Classical Guitar Dataset and Benchmark Transcription Model
- Self-Improvement for Audio Large Language Model using Unlabeled Speech
- Step-Audio 2 Technical Report
- Memorizing Transformers
- Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language Models
- Focus Then Listen: An Empirical Study of Plug-and-Play Audio Enhancer for Noise-Robust Large Audio 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