VoxWatch: An open-set speaker recognition benchmark on VoxCeleb

no code implementations • 30 Jun 2023 • Raghuveer Peri, Seyed Omid Sadjadi, Daniel Garcia-Romero

Prior studies on this problem are sparse, and lack a common benchmark for systematic evaluations.

Speaker Identification Speaker Recognition +1

VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge

1 code implementation • 20 Feb 2023 • Jaesung Huh, Andrew Brown, Jee-weon Jung, Joon Son Chung, Arsha Nagrani, Daniel Garcia-Romero, Andrew Zisserman

This paper summarises the findings from the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22), which was held in conjunction with INTERSPEECH 2022.

Speaker Diarization Speaker Recognition +1

Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speech

no code implementations • 10 Dec 2021 • Rohit Paturi, Sundararajan Srinivasan, Katrin Kirchhoff, Daniel Garcia-Romero

Also, most of these models are trained with synthetic mixtures and do not generalize to real conversational data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors

1 code implementation • 24 Mar 2018 • Anna Silnova, Niko Brummer, Daniel Garcia-Romero, David Snyder, Lukas Burget

We have recently introduced a fast scoring algorithm for a discriminatively trained HT-PLDA backend.

Topic Identification and Discovery on Text and Speech

no code implementations • EMNLP 2015 • Ch May, ler, Francis Ferraro, Alan McCree, Jonathan Wintrode, Daniel Garcia-Romero, Benjamin Van Durme

Dimensionality Reduction Speech Recognition +1

Generative Modelling for Unsupervised Score Calibration

no code implementations • 4 Nov 2013 • Niko Brümmer, Daniel Garcia-Romero

Score calibration enables automatic speaker recognizers to make cost-effective accept / reject decisions.