VITA-Group/Audio-Lottery

[ICLR 2022] "Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable", by Shaojin Ding, Tianlong Chen, Zhangyang Wang

39
/ 100
Emerging

This helps speech application developers make their voice features run efficiently on mobile devices. It takes an existing, large speech recognition model and finds a much smaller, equally powerful version. This is for engineers and developers building speech-interactive apps who need to optimize for device performance and varied user environments.

No commits in the last 6 months.

Use this if you are developing mobile applications with speech recognition features and need to reduce the model size without sacrificing accuracy, even in noisy conditions.

Not ideal if you are looking for an off-the-shelf, ready-to-use speech recognition system without needing to optimize or customize the underlying models.

mobile-speech-apps voice-user-interfaces edge-ai speech-model-optimization noise-robustness
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

32

Forks

7

Language

Python

License

MIT

Last pushed

Apr 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/VITA-Group/Audio-Lottery"

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