Download
This de-esser uses a novel approach called Temporal Sibilance Processing. The idea is to distinguish between fricatives and voiced sections of the speech signal by the number of zero crossings in time. Most of the speech file is left untouched (the samples are directly copied from source to destination). Only fricatives that are long enough and loud enough are filtered. The advantage of this approach over traditional approaches is that the clarity of the remaining speech is completely unaffected.
Features
- Reduce sibilance in speech without affecting the quality of the rest of the audio.
- Sibilance can be classified according to harshness (RMS amplitude) and duration and custom filters can be applied to each class.
Project Samples
License
GNU General Public License version 3.0 (GPLv3)Follow de-ess
Other Useful Business Software
Retool your internal operations
Build internal software that meets enterprise security standards without waiting on engineering resources. Retool connects to your databases, APIs, and data sources while maintaining the permissions and controls you need. Create custom dashboards, admin tools, and workflows from natural language prompts—all deployed in your cloud with security baked in. Stop duct-taping operations together, start building in Retool.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of de-ess!
