wq2012/awesome-diarization
A curated list of papers, libraries, datasets, and tools for speaker diarization using deep learning and machine learning techniques.
★1.9k stars Learning
Not currently ranked — collecting fresh signals.
star history
This repository organizes the world’s resources for speaker diarization, a speech processing task that identifies who spoke when in audio recordings. The curated list covers publications including review and survey papers on deep learning approaches, software frameworks for clustering and speaker embedding, evaluation tools, datasets for training and augmentation, and other learning materials such as courses, books, and tutorials. It serves as a centralized reference for practitioners and researchers in the speech and audio processing community.
Frequently asked
- What is wq2012/awesome-diarization?
- A curated list of papers, libraries, datasets, and tools for speaker diarization using deep learning and machine learning techniques.
- Is awesome-diarization open source?
- Yes — wq2012/awesome-diarization is open source, released under the Apache-2.0 license.
- How popular is awesome-diarization?
- wq2012/awesome-diarization has 1.9k stars on GitHub.
- Where can I find awesome-diarization?
- wq2012/awesome-diarization is on GitHub at https://github.com/wq2012/awesome-diarization.