How Does Pre-Trained Wav2Vec 2.0 Perform on Domain-Shifted ASR? an Extensive Benchmark on Air Traffic Control Communications
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149421" target="_blank" >RIV/00216305:26230/23:PU149421 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/10022724" target="_blank" >https://ieeexplore.ieee.org/document/10022724</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/SLT54892.2023.10022724" target="_blank" >10.1109/SLT54892.2023.10022724</a>
Alternative languages
Result language
angličtina
Original language name
How Does Pre-Trained Wav2Vec 2.0 Perform on Domain-Shifted ASR? an Extensive Benchmark on Air Traffic Control Communications
Original language description
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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
R - Projekt Ramcoveho programu EK
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
IEEE Spoken Language Technology Workshop, SLT 2022 - Proceedings
ISBN
978-1-6654-7189-3
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
205-212
Publisher name
IEEE Signal Processing Society
Place of publication
Doha
Event location
Doha
Event date
Jan 9, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000968851900028