Pyannote.audio 2.1 Speaker Diarization Pipeline: Principle, Benchmark, and Recipe

By Hervé Bredin. 2023

317 citations recorded by the source corpus.

pyannote.audio is an open-source toolkit written in Python for speaker diarization. Version 2.1 introduces a major overhaul of pyannote.audio default speaker diarization pipeline, made of three main stages: speaker segmentation applied to a short sliding window, neural speaker embedding of each (local) speakers, and (global) ag-glomerative clustering. One of the main objective of the toolkit is to democratize speaker diarization. Therefore, on top of a pretrained speaker diarization pipeline that gives good results out of the box, we also provide a recipe that practitioners can follow to improve its performance on their own (manually annotated) dataset.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Alexis Plaquet
2. Matt Le
3. Bowen Shi
4. Joshua Lane
5. Rashel Moritz
6. Hervé Bredin
7. Andros Tjandra
8. Apoorv Vyas

Citations in the corpus

• Audiobox: Unified Audio Generation with Natural Language Prompts (2023, methodology): “We create the transcribed subset with the following pre-processing methods: For unsegmented multi-speaker conversational datasets information, we first segment our dataset using PyAnnote diarization toolkit (Plaquet and Bredin, 2023; Bredin, 2023) to create single speaker speech segments.”
• Powerset multi-class cross entropy loss for neural speaker diarization (2023, methodology): “More details on the pipeline internals are available in [10] but we describe the gist of it in the following section.”