Speaker detection in the wild: Lessons learned from JSALT 2019
Abstract
This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios. The main focus was to tackle a wide range of conditions that go from meetings to wild speech. We describe the research threads we explored and a set of modules that was successful for these scenarios. The ultimate goal was to explore speaker detection; but our first finding was that an effective diarization improves detection, and not having a diarization stage impoverishes the performance. All the different configurations of our research agree on this fact and follow a main backbone that includes diarization as a previous stage. With this backbone, we analyzed the following problems: voice activity detection, how to deal with noisy signals, domain mismatch, how to improve the clustering; and the overall impact of previous stages in the final speaker detection. In this paper, we show partial results for speaker diarizarion to have a better understanding of the problem and we present the final results for speaker detection.
Cite
@article{arxiv.1912.00938,
title = {Speaker detection in the wild: Lessons learned from JSALT 2019},
author = {Paola Garcia and Jesus Villalba and Herve Bredin and Jun Du and Diego Castan and Alejandrina Cristia and Latane Bullock and Ling Guo and Koji Okabe and Phani Sankar Nidadavolu and Saurabh Kataria and Sizhu Chen and Leo Galmant and Marvin Lavechin and Lei Sun and Marie-Philippe Gill and Bar Ben-Yair and Sajjad Abdoli and Xin Wang and Wassim Bouaziz and Hadrien Titeux and Emmanuel Dupoux and Kong Aik Lee and Najim Dehak},
journal= {arXiv preprint arXiv:1912.00938},
year = {2019}
}
Comments
Submitted to ICASSP 2020