mlsanityData to 7 Oct 2026

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

arXiv 2203.16104 ↗First posted 30 Mar 2022cs.SD cs.LG eess.AScited by 16

Not on the map. Why?

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.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

20 of 34 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  4. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  5. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
  6. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 400
  7. 2020FSD50K: An Open Dataset of Human-Labeled Sound Eventscited by 339
  8. 2019Speech Model Pre-training for End-to-End Spoken Language Understandingcited by 191
  9. 2021Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Trainingcited by 148
  10. 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 127
  11. 2018The fifth 'CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselinescited by 90
  12. 2018Domain Adversarial Training for Accented Speech Recognitioncited by 40
8 more
  1. 2020Augmentation adversarial training for self-supervised speaker recognitioncited by 24
  2. 2022A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognitioncited by 20
  3. 2020REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabelingcited by 18
  4. 2021Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learningcited by 17
  5. 2018Noise Adaptive Speech Enhancement using Domain Adversarial Trainingcited by 15
  6. 2021Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstructioncited by 12
  7. 2019Unsupervised Adversarial Domain Adaptation for Cross-Lingual Speech Emotion Recognitioncited by 10
  8. 2021Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verificationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 7; 2024: 4; 2025: 0; 2026: 1.

16 papers.

Sort:

  1. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 258
  2. 2022SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learningcited by 26
  3. 2023Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clusteringcited by 21
  4. 2023Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languagescited by 12
  5. 2023Ensemble knowledge distillation of self-supervised speech modelscited by 10
  6. 2023R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Piecescited by 7
  7. 2022Improving generalizability of distilled self-supervised speech processing models under distorted settingscited by 5
  8. 2023On the Transferability of Whisper-based Representations for "In-the-Wild" Cross-Task Downstream Speech Applicationscited by 4
  9. 2024SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representationscited by 3
  10. 2024LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Taskscited by 2
  11. 2026Dimensionality-Aware Anomaly Detection in Learned Representations of Self-Supervised Speech Modelscited by 2
  12. 2022Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancementcited by 1
4 more
  1. 2023MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognitioncited by 1
  2. 2024Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Trainingcited by 1
  3. 2024Describe Where You Are: Improving Noise-Robustness for Speech Emotion Recognition with Text Description of the Environmentcited by 1
  4. 2023Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representationscited by 0