%Aigaion2 BibTeX export from Idiap Publications %Monday 07 October 2024 07:04:56 PM @INPROCEEDINGS{Juan_SLT2023-2_2023, author = {Juan, Zuluaga-Gomez. and Prasad, Amrutha and Iuliia, Nigmatulina and Sarfjoo, Seyyed Saeed and Motlicek, Petr and Kleinert, Matthias and Helmke, Hartmut and Ohneiser, Oliver and Zhan, Qingran}, keywords = {air traffic control communications, Automatic Speech Recognition, self-supervised pre-training, wav2vec 2.0}, projects = {Idiap, HAAWAII, EC H2020- ATCO2}, month = jan, title = {How Does Pre-trained Wav2Vec 2.0 Perform on Domain-Shifted ASR? An Extensive Benchmark on Air Traffic Control Communications}, booktitle = {2023 IEEE Spoken Language Technology Workshop (SLT)}, series = {1}, volume = {1}, number = {1}, year = {2023}, organization = {IEEE}, url = {https://arxiv.org/abs/2203.16822}, 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.}, pdf = {https://publications.idiap.ch/attachments/papers/2022/Juan_SLT2023-2_2023.pdf} }