%Aigaion2 BibTeX export from Idiap Publications %Tuesday 03 December 2024 06:35:12 PM @INPROCEEDINGS{Bredin_ICASSP_2020, author = {Bredin, Herve and Yin, Ruiqing and Coria, Juan Manuel and Korshunov, Pavel and Lavechin, Marvin and Fustes, Diego and Titeux, Hadrien and Bouaziz, Wassim and Gill, Marie-Philippe}, projects = {Idiap, SWAN}, month = may, title = {pyannote.audio: neural building blocks for speaker diarization}, booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing}, year = {2020}, url = {https://arxiv.org/pdf/1911.01255.pdf}, 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.} }