mlsanityData to 7 Oct 2026

Comparative Analysis of the wav2vec 2.0 Feature Extractor

arXiv 2308.04286 ↗First posted 8 Aug 2023eess.AS cs.CL cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Automatic speech recognition (ASR) systems typically use handcrafted feature extraction pipelines. To avoid their inherent information loss and to achieve more consistent modeling from speech to transcribed text, neural raw waveform feature extractors (FEs) are an appealing approach. Also the wav2vec 2.0 model, which has recently gained large popularity, uses a convolutional FE which operates directly on the speech waveform. However, it is not yet studied extensively in the literature. In this work, we study its capability to replace the standard feature extraction methods in a connectionist temporal classification (CTC) ASR model and compare it to an alternative neural FE. We show that both are competitive with traditional FEs on the LibriSpeech benchmark and analyze the effect of the individual components. Furthermore, we analyze the learned filters and show that the most important information for the ASR system is obtained by a set of bandpass filters.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 17 of its 27 references that are in the map. First posted on arXiv 8 Aug 2023.

Builds on

17 of 27 references.

References · 17

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  4. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 335
  5. 2021Layer-wise Analysis of a Self-supervised Speech Representation Modelcited by 293
  6. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
  7. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  8. 2020Exploring wav2vec 2.0 on speaker verification and language identificationcited by 93
  9. 2021LEAF: A Learnable Frontend for Audio Classificationcited by 69
  10. 2021Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognitioncited by 68
  11. 2022Exploration of A Self-Supervised Speech Model: A Study on Emotional Corporacited by 31
  12. 2018RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognitioncited by 30
5 more
  1. 2022Opening the Black Box of wav2vec Feature Encodercited by 18
  2. 2021Conformer-based Hybrid ASR System for Switchboard Datasetcited by 15
  3. 2022Efficient Training of Neural Transducer for Speech Recognitioncited by 14
  4. 2022On-demand compute reduction with stochastic wav2vec 2.0cited by 10
  5. 2021On Architectures and Training for Raw Waveform Feature Extraction in ASRcited by 8

Built on by

Cited by year

Citing papers per year: 2025: 4.

4 papers.

  1. 2025Regularizing Learnable Feature Extraction for Automatic Speech Recognitioncited by 1
  2. 2025Multi-modal Transfer Learning for Dynamic Facial Emotion Recognition in the Wildcited by 0
  3. 2025Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCscited by 0
  4. 2025Unified Learnable 2D Convolutional Feature Extraction for ASRcited by 0