LiangXu123/Robust-One-step-Speech-Enhancement-via-Consistency-Distillation-ROSE-CD-

Robust One-step Speech Enhancement via Consistency Distillation (ROSE-CD)(IEEE WASPAA ORAL)

22
/ 100
Experimental

This helps clear up noisy speech recordings, making voices much easier to understand. You input an audio file containing speech with background noise, and it outputs a significantly cleaner version of that speech. This is ideal for anyone working with audio that needs improved clarity, such as transcriptionists, podcasters, or customer service analysts.

Use this if you need to quickly and effectively remove background noise from speech recordings for better intelligibility and analysis.

Not ideal if your primary need is complex audio mastering or if you require fine-grained control over specific audio frequencies beyond basic noise reduction.

audio-post-production voice-recording speech-analysis call-center-analytics podcast-editing
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

License

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/LiangXu123/Robust-One-step-Speech-Enhancement-via-Consistency-Distillation-ROSE-CD-"

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