Audio Language Model

Papers

State-Space Large Audio Language Models, arXiv, 2411.15685, arxiv, pdf, cication: -1

Saurabhchand Bhati, Yuan Gong, Leonid Karlinsky, ..., Rogerio Feris, James Glass
🌟 Scaling Speech-Text Pre-training with Synthetic Interleaved Data, arXiv, 2411.17607, arxiv, pdf, cication: -1

Aohan Zeng, Zhengxiao Du, Mingdao Liu, ..., Yuxiao Dong, Jie Tang
🌟 A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models, arXiv, 2411.08742, arxiv, pdf, cication: -1

Dingdong Wang, Mingyu Cui, Dongchao Yang, ..., Xueyuan Chen, Helen Meng
Roadmap towards Superhuman Speech Understanding using Large Language Models, arXiv, 2410.13268, arxiv, pdf, cication: -1

Fan Bu, Yuhao Zhang, Xidong Wang, ..., Qun Liu, Haizhou Li

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks, arXiv, 2411.05361, arxiv, pdf, cication: -1

Chien-yu Huang, Wei-Chih Chen, Shu-wen Yang, ..., Shinji Watanabe, Hung-yi Lee

What Do Speech Foundation Models Not Learn About Speech?, arXiv, 2410.12948, arxiv, pdf, cication: -1

Abdul Waheed, Hanin Atwany, Bhiksha Raj, ..., Rita Singh
Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Models, arXiv, 2410.23861, arxiv, pdf, cication: -1

Hao Yang, Lizhen Qu, Ehsan Shareghi, ..., Gholamreza Haffari
MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark, arXiv, 2410.19168, arxiv, pdf, cication: -1

S Sakshi, Utkarsh Tyagi, Sonal Kumar, ..., Sreyan Ghosh, Dinesh Manocha · (sakshi113.github)

Qwen2-Audio is a SOTA small-scale multimodal model (AudioLM) that handles audio and text inputs, allowing you to have voice interactions without ASR modules 🤗