| Paper ID | SPE-32.5 |
| Paper Title |
Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training |
| Authors |
Sameer Khurana, Massachusetts Institute of Technology, United States; Niko Moritz, Takaaki Hori, Jonathan Le Roux, Mitsubishi Electric Research Laboratories (MERL), United States |
| Session | SPE-32: Speech Recognition 12: Self-supervised, Semi-supervised, Unsupervised Training |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 13:00 - 13:45 |
| Presentation Time: | Thursday, 10 June, 13:00 - 13:45 |
| Presentation |
Poster
|
| Topic |
Speech Processing: [SPE-GASR] General Topics in Speech Recognition |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based pseudo-label filtering approach can be effectively used for domain adaptation. We propose a dropout-based uncertainty-driven self-training (DUST) technique, which uses agreement between multiple predictions of an ASR system obtained for different dropout settings to measure the model's uncertainty about its prediction. DUST excludes pseudo-labeled data with high uncertainties from the training, which leads to substantially improved ASR results compared to ST without filtering, and accelerates the training time due to a reduced training data set. Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD as the target domains show that up to 80% of the performance of a system trained on ground-truth data can be recovered. |
