MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition
Not on the map. Why?
Abstract (arXiv)
End-to-end automatic speech recognition (ASR) usually suffers from performance degradation when applied to a new domain due to domain shift. Unsupervised domain adaptation (UDA) aims to improve the performance on the unlabeled target domain by transferring knowledge from the source to the target domain. To improve transferability, existing UDA approaches mainly focus on matching the distributions of the source and target domains globally and/or locally, while ignoring the model discriminability. In this paper, we propose a novel UDA approach for ASR via inter-domain MAtching and intra-domain DIscrimination (MADI), which improves the model transferability by fine-grained inter-domain matching and discriminability by intra-domain contrastive discrimination simultaneously. Evaluations on the Libri-Adapt dataset demonstrate the effectiveness of our approach. MADI reduces the relative word error rate (WER) on cross-device and cross-environment ASR by 17.7% and 22.8%, respectively.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 26 references that are in the map. First posted on arXiv 22 Feb 2023.
Builds on
17 of 26 references.
References · 17
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
- 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 138
- 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
- 2021Category Contrast for Unsupervised Domain Adaptation in Visual Taskscited by 65
- 2020Data Augmenting Contrastive Learning of Speech Representations in the Time Domaincited by 63
- 2021CLDA: Contrastive Learning for Semi-Supervised Domain Adaptationcited by 52
- 2018Domain Adversarial Training for Accented Speech Recognitioncited by 40
- 2020Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learningcited by 33
- 2020REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabelingcited by 18
- 2021Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learningcited by 17
- 2022Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptationcited by 16
5 more
- 2019AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognitioncited by 11
- 2020Mic2Mic: Using Cycle-Consistent Generative Adversarial Networks to Overcome Microphone Variability in Speech Systemscited by 11
- 2021Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matchingcited by 9
- 2020Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptationcited by 7
- 2020Domain Adversarial Neural Networks for Dysarthric Speech Recognitioncited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.