The Phonexia VoxCeleb Speaker Recognition Challenge 2021 System Description

Autor:	Slavíček, Josef, Swart, Albert, Klčo, Michal, Brümmer, Niko
Rok vydání:	2021
Předmět:	Computer Science - Sound Computer Science - Machine Learning Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	We describe the Phonexia submission for the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21) in the unsupervised speaker verification track. Our solution was very similar to IDLab's winning submission for VoxSRC-20. An embedding extractor was bootstrapped using momentum contrastive learning, with input augmentations as the only source of supervision. This was followed by several iterations of clustering to assign pseudo-speaker labels that were then used for supervised embedding extractor training. Finally, a score fusion was done, by averaging the zt-normalized cosine scores of five different embedding extractors. We briefly also describe unsuccessful solutions involving i-vectors instead of DNN embeddings and PLDA instead of cosine scoring. Comment: Second place in the self-supervised track of VoxSRC-21: VoxCeleb Speaker Recognition Challenge
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2109.02052 Zobrazit plný text záznamu View this record from Arxiv