# Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation

arXiv: https://arxiv.org/abs/1707.06265 · HTML: https://mlsanity.com/paper/1707.06265/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2017.

## Built on by (most cited first, 27 of 27)

- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [Data Augmentation techniques in time series domain: A survey and taxonomy](https://mlsanity.com/paper/2206.13508/) (2022)
- [Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder](https://mlsanity.com/paper/2105.00026/) (2021)
- [Towards Lifelong Learning of End-to-end ASR](https://mlsanity.com/paper/2104.01616/) (2021)
- [Hallucination Improves the Performance of Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2307.12168/) (2023)
- [TreeMix: Compositional Constituency-based Data Augmentation for Natural Language Understanding](https://mlsanity.com/paper/2205.06153/) (2022)
- [CB-Conformer: Contextual biasing Conformer for biased word recognition](https://mlsanity.com/paper/2304.09607/) (2023)
- [Boosting Cross-Domain Speech Recognition with Self-Supervision](https://mlsanity.com/paper/2206.09783/) (2022)
- [An Investigation of End-to-End Models for Robust Speech Recognition](https://mlsanity.com/paper/2102.06237/) (2021)
- [Data Augmentation for Time-Series Classification: An Extensive Empirical Study and Comprehensive Survey](https://mlsanity.com/paper/2310.10060/) (2023)
- [Interpretable CNN-Multilevel Attention Transformer for Rapid Recognition of Pneumonia from Chest X-Ray Images](https://mlsanity.com/paper/2210.16584/) (2022)
- [Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2405.14161/) (2024)
- [Advancing Test-Time Adaptation in Wild Acoustic Test Settings](https://mlsanity.com/paper/2310.09505/) (2023)
- [Unsupervised domain adaptation for speech recognition with unsupervised error correction](https://mlsanity.com/paper/2209.12043/) (2022)
- [Making Invisible Visible: Data-Driven Seismic Inversion with Spatio-temporally Constrained Data Augmentation](https://mlsanity.com/paper/2106.11892/) (2021)
- [Personalized One-Shot Lipreading for an ALS Patient](https://mlsanity.com/paper/2111.01740/) (2021)
- [Towards certification: A complete statistical validation pipeline for supervised learning in industry](https://mlsanity.com/paper/2411.02075/) (2024)
- [Context-aware Multi-task Learning for Pedestrian Intent and Trajectory Prediction](https://mlsanity.com/paper/2407.17162/) (2024)
- [LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition](https://mlsanity.com/paper/2408.05769/) (2024)
- [String-based Molecule Generation via Multi-decoder VAE](https://mlsanity.com/paper/2208.10718/) (2022)
- [Improved far-field speech recognition using Joint Variational Autoencoder](https://mlsanity.com/paper/2204.11286/) (2022)
- [Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes](https://mlsanity.com/paper/2506.10653/) (2025)
- [Hybrid Adversarial Spectral Loss Conditional Generative Adversarial Networks for Signal Data Augmentation in Ultra-precision Machining Surface Roughness Prediction](https://mlsanity.com/paper/2507.04665/) (2025)
- [Unsupervised domain transfer: Overcoming signal degradation in sleep monitoring by increasing scoring realism](https://mlsanity.com/paper/2604.13988/) (2026)
- [Variational Autoencoder Domain Adaptation for Cross-System Generalization in ML-Based SOP Monitoring](https://mlsanity.com/paper/2604.18035/) (2026)
- [Frequency Selective Neural Networks as a Foundation Architecture for Time Series Learning](https://mlsanity.com/paper/2608.29012/) (2026)

## Abstract (arXiv)

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 presented, 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.