Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training
By Sameer Khurana, Niko Moritz, Takaaki Hori, Jonathan Le Roux. 2020
74 citations recorded by the source corpus.
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 DUST, a dropout-based uncertainty-driven self-training 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.
Subfields: Artificial Intelligence, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training (2021, neutral): “This includes data augmentation [13, 14], self-training on target domain [15], domain adversarial training [16], and joint training [8].”
- Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives (2022, background): “, 2021a, 2022), speech recognition (Wang et al., 2018; Manohar et al., 2018; Khurana et al., 2021; Anoop et al., 2021), and imagined speech recognition (Jimenez-Guarneros and Gomez-Gil, 2021) also brings the concept of UDA.”