A-SHOJAEI/cross-lingual-phoneme-aware-speech-enhancement-with-adaptive-masking

Multi-stage speech enhancement system that leverages cross-lingual phoneme embeddings to guide adaptive time-frequency masking for noise reduction in low-resource languages. The model uses phoneme-conditioned attention to learn language-agnostic acoustic patterns from high-resource languages (English, Spanish) and transfers them to low-resource lan

19
/ 100
Experimental
No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

MIT

Last pushed

Feb 21, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/A-SHOJAEI/cross-lingual-phoneme-aware-speech-enhancement-with-adaptive-masking"

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