• Home
  • Search
  • Unsupervised domain adaptation for robust speech recognition via variational autoencoder-based data augmentation
  • Open Access IconOpen Access
  • Cite Icon135
  • https://doi.org/10.1109/asru.2017.8268911Copy DOI Icon

Unsupervised domain adaptation for robust speech recognition via variational autoencoder-based data augmentation

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world applications. Research on robust speech recognition can be regarded as trying to overcome this domain mismatch issue. In this paper, we address the unsupervised domain adaptation problem for robust speech recognition, where both source and target domain speech are available, but word transcripts are only available for the source domain speech. We present novel augmentation-based methods that transform speech in a way that does not change the transcripts. Specifically, we first train a variational autoencoder on both source and target domain data (without supervision) to learn a latent representation of speech. We then transform nuisance attributes of speech that are irrelevant to recognition by modifying the latent representations, in order to augment labeled training data with additional data whose distribution is more similar to the target domain. The proposed method is evaluated on the CHiME-4 dataset and reduces the absolute word error rate (WER) by as much as 35% compared to the non-adapted baseline.

Similar Papers
  • PDF
  • Supplementary Content
  • Citations67

Deep Unsupervised Domain Adaptation with Time Series Sensor Data: A Survey

  • Jul 23, 2022
  • Sensors (Basel, Switzerland)
  • Yongjie Shi +2
  • Research Article
  • Citations15

Unsupervised Domain Adaptation for Segmentation with Black-box Source Model.

  • Apr 04, 2022
  • Proceedings of SPIE--the International Society for Optical Engineering
  • Xiaofeng Liu +6
  • PDF
  • Research Article

Learning Transferable Convolutional Proxy by SMI-Based Matching Technique

  • Oct 14, 2020
  • Shock and Vibration
  • Wei Jin +1
  • Supplementary Content

On Transfer Learning Techniques for Machine Learning

  • Apr 30, 2020
  • Figshare
  • Debasmit Das
  • PDF
  • Research Article
  • Citations55

The Eyes of the Gods: A Survey of Unsupervised Domain Adaptation Methods Based on Remote Sensing Data

  • Sep 03, 2022
  • Remote Sensing
  • Mengqiu Xu +4
  • Dissertation

Data-driven Fault Diagnosis for Cyber-Physical Systems

  • May 09, 2025
  • Mehdi Saman Azari
  • Research Article
  • Citations3

Dual-Space Topological Isomorphism and Maximization of Predictive Diversity for Unsupervised Domain Adaptation.

  • Jan 01, 2025
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Mengru Wang +1
  • Research Article
  • Citations1

Towards Pose Invariant Bionic Limb Control: A comparative study of two unsupervised domain adaptation methods

  • Jan 01, 2025
  • IEEE Access
  • Alexander Hannius +2
  • Research Article

Robust Unsupervised Domain Adaptation from A Corrupted Source.

  • Nov 01, 2022
  • Proceedings. IEEE International Conference on Data Mining
  • Shuyang Yu +4
  • Research Article

A Cross-Domain Milk Freshness Detection Method Based on Transfer Learning

  • May 01, 2026
  • IEEE Internet of Things Journal
  • Jie Zhang +4
  • Research Article
  • Citations12

A complex process fault diagnosis method based on manifold distribution adaptation

  • Oct 15, 2019
  • Engineering Applications of Artificial Intelligence
  • Xiaogang Wang +1
  • Research Article
  • Citations9

Adaptive Dispersal and Collaborative Clustering for Few-Shot Unsupervised Domain Adaptation.

  • Jan 01, 2025
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Yuwu Lu +5
  • Conference Article
  • Citations22

Continual Unsupervised Domain Adaptation for Semantic Segmentation by Online Frequency Domain Style Transfer

  • Sep 19, 2021
  • Jan-Aike Termohlen +4
  • Conference Article
  • Citations29

Adaptiope: A Modern Benchmark for Unsupervised Domain Adaptation

  • Jan 01, 2021
  • Tobias Ringwald +1
  • Research Article
  • Citations17

Reducing bias to source samples for unsupervised domain adaptation

  • Mar 26, 2021
  • Neural Networks
  • Yalan Ye +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.