logo Idiap Research Institute        
 [BibTeX] [Marc21]
How Does Pre-trained Wav2Vec 2.0 Perform on Domain-Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications
Type of publication: Conference paper
Citation: Juan_SLT2023-2_2023
Publication status: Accepted
Booktitle: 2023 IEEE Spoken Language Technology Workshop (SLT)
Series: 1
Volume: 1
Number: 1
Year: 2023
Month: January
Organization: IEEE
URL: https://arxiv.org/abs/2203.168...
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 and 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.
Keywords: air traffic control communications, Automatic Speech Recognition, self-supervised pre-training, wav2vec 2.0
Projects Idiap
EC H2020- ATCO2
Authors Juan, Zuluaga-Gomez.
Prasad, Amrutha
Iuliia, Nigmatulina
Sarfjoo, Seyyed Saeed
Motlicek, Petr
Kleinert, Matthias
Helmke, Hartmut
Ohneiser, Oliver
Zhan, Qingran
Added by: [UNK]
Total mark: 0
  • Juan_SLT2023-2_2023.pdf