The EURECOM Submission to the First DIHARD Challenge

Jose Patino, Héctor Delgado and Nicholas Evans

Abstract:

The first DIHARD challenge aims to promote speaker diarization research and to foster progress in domain robustness. This paper reports EURECOM's submission to the DIHARD challenge. It is based upon a low-resource, domain-robust binary key approach to speaker modelling. New contributions include the use of an infinite impulse response - constant Q Mel-frequency cepstral coefficient (ICMC) front-end, a clustering selection / stopping criterion algorithm based on spectral clustering and a mechanism to detect single-speaker trials. Experimental results obtained using the standard DIHARD database show that the contributions reported in this paper deliver relative improvements of 39% in terms of the diarization error rate over the baseline algorithm. An absolute DER of 29% on the evaluation set compares favourably with those of competing systems, especially given that the binary key system is highly efficient, running 63 times faster than real-time.

---

Cite as: Patino, J., Delgado, H., Evans, N. (2018) The EURECOM Submission to the First DIHARD Challenge. Proc. Interspeech 2018, 2813-2817, DOI: 10.21437/Interspeech.2018-2172.

---

BiBTeX Entry:

@inproceedings{Patino2018,
author={Jose Patino and Héctor Delgado and Nicholas Evans},
title={The EURECOM Submission to the First DIHARD Challenge},
year=2018,
booktitle={Proc. Interspeech 2018},
pages={2813--2817},
doi={10.21437/Interspeech.2018-2172},
url={http://dx.doi.org/10.21437/Interspeech.2018-2172} }