Publication result detail

Description and Analysis of ABC Submission to NIST LRE 2022

MATĚJKA, P.; SILNOVA, A.; SLAVÍČEK, J.; MOŠNER, L.; PLCHOT, O.; KLČO, M.; PENG, J.; STAFYLAKIS, T.; BURGET, L.

Original Title

Description and Analysis of ABC Submission to NIST LRE 2022

English Title

Description and Analysis of ABC Submission to NIST LRE 2022

Type

Paper in proceedings (conference paper)

Original Abstract

This paper summarizes our efforts in the NIST Language Recognition Evaluations 2022 resulting in systems providing competitive performance. We provide both the description and analysis of the systems. We describe what data we have used to train our models, and we follow with embedding extractors and back-end classifiers. After covering the architecture, we concentrate on post-evaluation analysis. We compare different topologies of DNN, different backend classifiers, and the impact of the data used to train them. We also report results with XLS-R pre-trained models. We present the performance of the systems in the Fixed condition, where participants are required to use only predefined data sets, and also in the Open condition allowing to use any data to train the systems.

English abstract

This paper summarizes our efforts in the NIST Language Recognition Evaluations 2022 resulting in systems providing competitive performance. We provide both the description and analysis of the systems. We describe what data we have used to train our models, and we follow with embedding extractors and back-end classifiers. After covering the architecture, we concentrate on post-evaluation analysis. We compare different topologies of DNN, different backend classifiers, and the impact of the data used to train them. We also report results with XLS-R pre-trained models. We present the performance of the systems in the Fixed condition, where participants are required to use only predefined data sets, and also in the Open condition allowing to use any data to train the systems.

Keywords

nguage detection, language recognition, embedding extractor, LRE, NIST

Key words in English

nguage detection, language recognition, embedding extractor, LRE, NIST

Authors

MATĚJKA, P.; SILNOVA, A.; SLAVÍČEK, J.; MOŠNER, L.; PLCHOT, O.; KLČO, M.; PENG, J.; STAFYLAKIS, T.; BURGET, L.

RIV year

2024

Released

20.08.2023

Publisher

International Speech Communication Association

Location

Dublin

Book

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ISBN

1990-9772

Periodical

Proceedings of Interspeech

Volume

2023

Number

08

State

French Republic

Pages from

511

Pages to

515

Pages count

5

URL

https://www.isca-speech.org/archive/pdfs/interspeech_2023/matejka23_interspeech.pdf

Full text in the Digital Library

http://hdl.handle.net/

BibTex

@inproceedings{BUT185574,
  author="MATĚJKA, P. and SILNOVA, A. and SLAVÍČEK, J. and MOŠNER, L. and PLCHOT, O. and KLČO, M. and PENG, J. and STAFYLAKIS, T. and BURGET, L.",
  title="Description and Analysis of ABC Submission to NIST LRE 2022",
  booktitle="Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
  year="2023",
  journal="Proceedings of Interspeech",
  volume="2023",
  number="08",
  pages="511--515",
  publisher="International Speech Communication Association",
  address="Dublin",
  doi="10.21437/Interspeech.2023-1529",
  issn="1990-9772",
  url="https://www.isca-speech.org/archive/pdfs/interspeech_2023/matejka23_interspeech.pdf"
}

Documents

matejka23_interspeech2023_description