pyannote.audio: neural building blocks for speaker diarization

Hervé Bredin, Ruiqing Yin, Juan Manuel Coria, Gregory Gelly, Pavel Korshunov +5 more
11/4/2019
eess.AScs.SD

Official code: pyannote/pyannote-audio (10,674 stars, MIT, PyTorch, last commit 2026-10-20).

Abstract

We introduce pyannote.audio, an open-source toolkit written in Python for speaker diarization. Based on PyTorch machine learning framework, it provides a set of trainable end-to-end neural building blocks that can be combined and jointly optimized to build speaker diarization pipelines. pyannote.audio also comes with pre-trained models covering a wide range of domains for voice activity detection, speaker change detection, overlapped speech detection, and speaker embedding -- reaching state-of-the-art performance for most of them.

View on arXivView PDF

Code Implementations(1)

pyannote/pyannote-audioOfficial100%
PyTorchMIT

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

10,6741,123Python, Jupyter NotebookMar 7, 20165 days agoMIT
overlapped-speech-detectionpretrained-modelspytorchspeaker-change-detectionspeaker-diarization+6 more

Similar Papers

Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network

82% match2023

From Modular to End-to-End Speaker Diarization

81% match2024

AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark

81% match1 repo3752018

Exploring Speaker Diarization with Mixture of Experts

80% match2025

SpeechBrain: A General-Purpose Speech Toolkit

80% match1 repo11.8k2021

Joint Audio and Speech Understanding

80% match1 repo4782023

Cite this paper

@article{bredin2019pyannoteaudio,
  title  = {pyannote.audio: neural building blocks for speaker diarization},
  author = {Hervé Bredin and Ruiqing Yin and Juan Manuel Coria and Gregory Gelly and Pavel Korshunov and Marvin Lavechin and Diego Fustes and Hadrien Titeux and Wassim Bouaziz and Marie-Philippe Gill},
  year   = {2019},
  eprint = {1911.01255},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1911.01255}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1911.01255.svg)](https://codeofpaper.com/paper/1911.01255)

Discussion