Publication Details

How Does Pre-Trained Wav2Vec 2.0 Perform on Domain-Shifted ASR? an Extensive Benchmark on Air Traffic Control Communications

ZULUAGA-GOMEZ, J.; PRASAD, A.; NIGMATULINA, I.; SARFJOO, S.; MOTLÍČEK, P.; KLEINERT, M.; HELMKE, H.; OHNEISER, O.; ZHAN, Q. How Does Pre-Trained Wav2Vec 2.0 Perform on Domain-Shifted ASR? an Extensive Benchmark on Air Traffic Control Communications. In IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings. Doha: IEEE Signal Processing Society, 2023. p. 205-212. ISBN: 978-1-6654-7189-3.
Czech title
Jak si vede předtrénovaný Wav2Vec 2.0 v ASR s posunem domény? Rozsáhlé testování na komunikaci v řízení letového provozu
Type
conference paper
Language
English
Authors
ZULUAGA-GOMEZ, J.
Prasad Amrutha (DCGM)
NIGMATULINA, I.
Sarfjoo Seyyed Saeed
Motlíček Petr, doc. Ing., Ph.D. (DCGM)
KLEINERT, M.
HELMKE, H.
OHNEISER, O.
ZHAN, Q.
URL
Keywords

Automatic speech recognition, Wav2Vec 2.0, self-supervised pre-training, air traffic control communications.

Abstract

Recent work on self-supervised pre-training focus on leveraging large-scale unlabeled speech data to build robust end-to-end (E2E) acoustic models (AM) that can be later fine-tuned on downstream tasks e.g., automatic speech recognition (ASR). Yet, few works investigated the impact on performance when the data properties substantially differ between the pre-training and fine-tuning phases, termed domain shift. We target this scenario by analyzing the robustness of Wav2Vec 2.0 and XLS-R models on downstream ASR for a completely unseen domain, air traffic control (ATC) communications. We benchmark these two models on several open-source and challenging ATC databases with signal-to-noise ratio between 5 to 20 dB. Relative word error rate (WER) reductions between 20% to 40% are obtained in comparison to hybrid-based ASR baselines by only fine-tuning E2E acoustic models with a smaller fraction of labeled data. We analyze WERs on the low-resource scenario and gender bias carried by one ATC dataset.

Published
2023
Pages
205–212
Proceedings
IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings
Conference
Spoken Language Technology Workshop 2022, Doha, QA
ISBN
978-1-6654-7189-3
Publisher
IEEE Signal Processing Society
Place
Doha
DOI
10.1109/SLT54892.2023.10022724
UT WoS
000968851900028
EID Scopus
2-s2.0-85141659819
BibTeX 
@inproceedings{BUT185194,
  author="ZULUAGA-GOMEZ, J. and PRASAD, A. and NIGMATULINA, I. and SARFJOO, S. and MOTLÍČEK, P. and KLEINERT, M. and HELMKE, H. and OHNEISER, O. and ZHAN, Q.",
  title="How Does Pre-Trained Wav2Vec 2.0 Perform on Domain-Shifted ASR? an Extensive Benchmark on Air Traffic Control Communications",
  booktitle="IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings",
  year="2023",
  pages="205--212",
  publisher="IEEE Signal Processing Society",
  address="Doha",
  doi="10.1109/SLT54892.2023.10022724",
  isbn="978-1-6654-7189-3",
  url="https://ieeexplore.ieee.org/document/10022724"
}
Back to top