mlsanityData to 7 Oct 2026

Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation

arXiv 2210.08182 ↗First posted 15 Oct 2022cs.SD cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Unsupervised representation learning for speech audios attained impressive performances for speech recognition tasks, particularly when annotated speech is limited. However, the unsupervised paradigm needs to be carefully designed and little is known about what properties these representations acquire. There is no guarantee that the model learns meaningful representations for valuable information for recognition. Moreover, the adaptation ability of the learned representations to other domains still needs to be estimated. In this work, we explore learning domain-invariant representations via a direct mapping of speech representations to their corresponding high-level linguistic informations. Results prove that the learned latents not only capture the articulatory feature of each phoneme but also enhance the adaptation ability, outperforming the baseline largely on accented benchmarks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 15 Oct 2022.

Builds on

20 of 37 references.

References · 20

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  2. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  3. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  4. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  5. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 335
  6. 2019Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoderscited by 196
  7. 2021Unsupervised Speech Recognitioncited by 147
  8. 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 127
  9. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  10. 2017Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Datacited by 92
  11. 2021UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Datacited by 76
  12. 2018wav2letter++: The Fastest Open-source Speech Recognition Systemcited by 42
8 more
  1. 2020Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Trainingcited by 38
  2. 2020Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretrainingcited by 35
  3. 2017Learning Latent Representations for Speech Generation and Transformationcited by 27
  4. 2020A Convolutional Deep Markov Model for Unsupervised Speech Representation Learningcited by 18
  5. 2021Federated Learning with Dynamic Transformer for Text to Speechcited by 11
  6. 2020A Comparison of Discrete Latent Variable Models for Speech Representation Learningcited by 8
  7. 2022r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled noise introducing and Contextual information incorporationcited by 7
  8. 2022Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognitioncited by 2

Built on by

Not cited yet.