zhenye234/xcodec

AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model

42
/ 100
Emerging

This project offers a way to enhance existing audio codecs by integrating both acoustic and semantic information. It takes raw audio inputs and processes them to produce higher-quality audio suitable for large audio language models. It would be used by researchers and developers working on advanced audio processing, speech synthesis, and general audio understanding applications.

294 stars. No commits in the last 6 months.

Use this if you are building or improving audio language models and need to ensure your audio encoding effectively captures both the sound quality and the meaning of the audio.

Not ideal if you are looking for a simple audio compression tool for general media consumption or basic audio file conversion.

audio-language-models speech-synthesis audio-processing voice-AI sound-engineering
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

294

Forks

23

Language

Python

License

MIT

Last pushed

Oct 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zhenye234/xcodec"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.