mlsanityData to 7 Oct 2026

FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition

arXiv 2206.15056 ↗First posted 30 Jun 2022cs.SD cs.LG eess.AScited by 5

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning representations (SSLR) have resulted in robust features for downstream tasks in many fields. Recently, several SSLRs have shown promising results on automatic speech recognition (ASR) benchmark corpora. However, previous studies have only shown performance for solitary SSLRs as an input feature for ASR models. In this study, we propose to investigate the effectiveness of diverse SSLR combinations using various fusion methods within end-to-end (E2E) ASR models. In addition, we will show there are correlations between these extracted SSLRs. As such, we further propose a feature refinement loss for decorrelation to efficiently combine the set of input features. For evaluation, we show that the proposed 'FeaRLESS learning features' perform better than systems without the proposed feature refinement loss for both the WSJ and Fearless Steps Challenge (FSC) corpora.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 15 of its 26 references that are in the map. First posted on arXiv 30 Jun 2022.

Builds on

15 of 26 references.

References · 15

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  5. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 589
  6. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  7. 2020TERA: Self-Supervised Learning of Transformer Encoder Representation for Speechcited by 186
  8. 2019An Unsupervised Autoregressive Model for Speech Representation Learningcited by 185
  9. 2015Reducing Overfitting in Deep Networks by Decorrelating Representationscited by 94
  10. 2017Self-supervised learning of visual features through embedding images into text topic spacescited by 43
  11. 2021An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognitioncited by 39
  12. 2017Face Detection using Deep Learning: An Improved Faster RCNN Approachcited by 16
3 more
  1. 2021On Architectures and Training for Raw Waveform Feature Extraction in ASRcited by 8
  2. 2020FEARLESS STEPS Challenge (FS-2): Supervised Learning with Massive Naturalistic Apollo Datacited by 4
  3. 2021Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corporacited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 0; 2026: 1.

5 papers.

  1. 2023Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyondcited by 10
  2. 2023High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Unitscited by 4
  3. 2026Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASRcited by 3
  4. 2024Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple Modalitiescited by 2
  5. 2024Converting Anyone's Voice: End-to-End Expressive Voice Conversion with a Conditional Diffusion Modelcited by 1