Detail publikace

BUT System Description for The Third DIHARD Speech Diarization Challenge

LANDINI, F. LOZANO DÍEZ, A. BURGET, L. DIEZ SÁNCHEZ, M. SILNOVA, A. ŽMOLÍKOVÁ, K. GLEMBEK, O. MATĚJKA, P. STAFYLAKIS, T. BRUMMER, J.

Originální název

BUT System Description for The Third DIHARD Speech Diarization Challenge

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

This is the system description corresponding to the systems developed by the BUT team for The Third DIHARD Speech Diarization Challenge. The systems for both tracks consist of a DOVERlap fusion of an end-to-end NN system with xvector based clustering systems in the form of spectral clustering and VBx. Given that the x-vector clustering systems do not provide overlapping speakers, overlapped speech is detected by a TasNet-based detector before the final fusion with the end-to-end approach.

Klíčová slova

Speaker Diarization, DIHARD, VBx diarization, end-to-end diarization, overlapped speech detection

Autoři

LANDINI, F.; LOZANO DÍEZ, A.; BURGET, L.; DIEZ SÁNCHEZ, M.; SILNOVA, A.; ŽMOLÍKOVÁ, K.; GLEMBEK, O.; MATĚJKA, P.; STAFYLAKIS, T.; BRUMMER, J.

Vydáno

23. 1. 2021

Místo

on-line by LDC and University of Pennsylvania

Strany od

1

Strany do

5

Strany počet

5

URL

https://dihardchallenge.github.io/dihard3/system_descriptions/dihard3_system_description_team55.pdf

BibTex

@inproceedings{BUT170909,
  author="Federico Nicolás {Landini} and Alicia {Lozano Díez} and Lukáš {Burget} and Mireia {Diez Sánchez} and Anna {Silnova} and Kateřina {Žmolíková} and Ondřej {Glembek} and Pavel {Matějka} and Themos {Stafylakis} and Johan Nikolaas Langenhoven {Brummer}",
  title="BUT System Description for The Third DIHARD Speech Diarization Challenge",
  booktitle="Proceedings available at Dihard Challenge Github",
  year="2021",
  pages="1--5",
  address="on-line by LDC and University of Pennsylvania",
  url="https://dihardchallenge.github.io/dihard3/system_descriptions/dihard3_system_description_team55.pdf"
}