Audio-AGI

Audio-AGI is an open-source research community. The community members are working on audio x AI research, including but not limited to:

• Computational auditory scene analysis (e.g., source separation, audio classification, acoustic event detection)
• Generative AI for audio (e.g., text-to-audio/music/speech synthesis, audio super-resolution)
• Large language models (LLMs) for audio/speech/music signals

We are actively seeking research and commercial cooperation in advancing AI-assisted multimedia storytelling. If you are interested, please email xubo.liu@surrey.ac.uk for more details! 👐