# Extracting Domain Invariant Features by Unsupervised Learning for Robust Automatic Speech Recognition

arXiv: https://arxiv.org/abs/1803.02551 · HTML: https://mlsanity.com/paper/1803.02551/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2018.

## Built on by (most cited first, 5 of 5)

- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training](https://mlsanity.com/paper/2104.01027/) (2021)
- [BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2109.13226/) (2021)
- [Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses](https://mlsanity.com/paper/2407.21061/) (2024)
- [Improved far-field speech recognition using Joint Variational Autoencoder](https://mlsanity.com/paper/2204.11286/) (2022)

## Abstract (arXiv)

The performance of automatic speech recognition (ASR) systems can be significantly compromised by previously unseen conditions, which is typically due to a mismatch between training and testing distributions. In this paper, we address robustness by studying domain invariant features, such that domain information becomes transparent to ASR systems, resolving the mismatch problem. Specifically, we investigate a recent model, called the Factorized Hierarchical Variational Autoencoder (FHVAE). FHVAEs learn to factorize sequence-level and segment-level attributes into different latent variables without supervision. We argue that the set of latent variables that contain segment-level information is our desired domain invariant feature for ASR. Experiments are conducted on Aurora-4 and CHiME-4, which demonstrate 41% and 27% absolute word error rate reductions respectively on mismatched domains.