# Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation

arXiv: https://arxiv.org/abs/2203.16104 · HTML: https://mlsanity.com/paper/2203.16104/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 30 Mar 2022.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [Speech Model Pre-training for End-to-End Spoken Language Understanding](https://mlsanity.com/paper/1904.03670/) (2019)
- [Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training](https://mlsanity.com/paper/2104.01027/) (2021)
- [Multi-task self-supervised learning for Robust Speech Recognition](https://mlsanity.com/paper/2001.09239/) (2020)
- [The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines](https://mlsanity.com/paper/1803.10609/) (2018)
- [Domain Adversarial Training for Accented Speech Recognition](https://mlsanity.com/paper/1806.02786/) (2018)
- [Augmentation adversarial training for self-supervised speaker recognition](https://mlsanity.com/paper/2007.12085/) (2020)
- [A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2201.08930/) (2022)
- [REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling](https://mlsanity.com/paper/2012.07353/) (2020)
- [Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning](https://mlsanity.com/paper/2103.05834/) (2021)
- [Noise Adaptive Speech Enhancement using Domain Adversarial Training](https://mlsanity.com/paper/1807.07501/) (2018)
- [Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction](https://mlsanity.com/paper/2110.15430/) (2021)
- [Unsupervised Adversarial Domain Adaptation for Cross-Lingual Speech Emotion Recognition](https://mlsanity.com/paper/1907.06083/) (2019)
- [Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification](https://mlsanity.com/paper/2108.13843/) (2021)

## Built on by (most cited first, 17 of 17)

- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2210.08634/) (2022)
- [Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering](https://mlsanity.com/paper/2305.11072/) (2023)
- [Ensemble knowledge distillation of self-supervised speech models](https://mlsanity.com/paper/2302.12757/) (2023)
- [Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages](https://mlsanity.com/paper/2310.03018/) (2023)
- [Improving generalizability of distilled self-supervised speech processing models under distorted settings](https://mlsanity.com/paper/2210.07978/) (2022)
- [R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces](https://mlsanity.com/paper/2311.09117/) (2023)
- [On the Transferability of Whisper-based Representations for "In-the-Wild" Cross-Task Downstream Speech Applications](https://mlsanity.com/paper/2305.14546/) (2023)
- [SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations](https://mlsanity.com/paper/2403.06260/) (2024)
- [LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks](https://mlsanity.com/paper/2406.09153/) (2024)
- [Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Models](https://mlsanity.com/paper/2605.02715/) (2026)
- [Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement](https://mlsanity.com/paper/2211.06562/) (2022)
- [MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition](https://mlsanity.com/paper/2302.11224/) (2023)
- [Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training](https://mlsanity.com/paper/2401.15323/) (2024)
- [Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition with Text Description of the Environment](https://mlsanity.com/paper/2407.17716/) (2024)
- [Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations](https://mlsanity.com/paper/2306.00481/) (2023)
- [Noise robust distillation of self-supervised speech models via correlation metrics](https://mlsanity.com/paper/2312.12153/) (2023)

## Abstract (arXiv)

Speech distortions are a long-standing problem that degrades the performance of supervisely trained speech processing models. It is high time that we enhance the robustness of speech processing models to obtain good performance when encountering speech distortions while not hurting the original performance on clean speech. In this work, we propose to improve the robustness of speech processing models by domain adversarial training (DAT). We conducted experiments based on the SUPERB framework on five different speech processing tasks. In case we do not always have knowledge of the distortion types for speech data, we analyzed the binary-domain and multi-domain settings, where the former treats all distorted speech as one domain, and the latter views different distortions as different domains. In contrast to supervised training methods, we obtained promising results in target domains where speech data is distorted with different distortions including new unseen distortions introduced during testing.