# Adversarial Learning of Raw Speech Features for Domain Invariant Speech Recognition

arXiv: https://arxiv.org/abs/1805.08615 · HTML: https://mlsanity.com/paper/1805.08615/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2018.

## Built on by (most cited first, 4 of 4)

- [A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness](https://mlsanity.com/paper/2212.09006/) (2022)
- [Unsupervised Domain Adaptation Schemes for Building ASR in Low-resource Languages](https://mlsanity.com/paper/2109.05494/) (2021)
- [Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek](https://mlsanity.com/paper/2301.00304/) (2022)
- [Enhancing and Adversarial: Improve ASR with Speaker Labels](https://mlsanity.com/paper/2211.06369/) (2022)

## Abstract (arXiv)

Recent advances in neural network based acoustic modelling have shown significant improvements in automatic speech recognition (ASR) performance. In order for acoustic models to be able to handle large acoustic variability, large amounts of labeled data is necessary, which are often expensive to obtain. This paper explores the application of adversarial training to learn features from raw speech that are invariant to acoustic variability. This acoustic variability is referred to as a domain shift in this paper. The experimental study presented in this paper leverages the architecture of Domain Adversarial Neural Networks (DANNs) [1] which uses data from two different domains. The DANN is a Y-shaped network that consists of a multi-layer CNN feature extractor module that is common to a label (senone) classifier and a so-called domain classifier. The utility of DANNs is evaluated on multiple datasets with domain shifts caused due to differences in gender and speaker accents. Promising empirical results indicate the strength of adversarial training for unsupervised domain adaptation in ASR, thereby emphasizing the ability of DANNs to learn domain invariant features from raw speech.