# Comparative Analysis of the wav2vec 2.0 Feature Extractor

arXiv: https://arxiv.org/abs/2308.04286 · HTML: https://mlsanity.com/paper/2308.04286/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 8 Aug 2023.

## Builds on (most cited first, 17 of 17)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Speaker Recognition from Raw Waveform with SincNet](https://mlsanity.com/paper/1808.00158/) (2018)
- [On Using Monolingual Corpora in Neural Machine Translation](https://mlsanity.com/paper/1503.03535/) (2015)
- [Exploring wav2vec 2.0 on speaker verification and language identification](https://mlsanity.com/paper/2012.06185/) (2020)
- [LEAF: A Learnable Frontend for Audio Classification](https://mlsanity.com/paper/2101.08596/) (2021)
- [Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition](https://mlsanity.com/paper/2109.06870/) (2021)
- [Exploration of A Self-Supervised Speech Model: A Study on Emotional Corpora](https://mlsanity.com/paper/2210.02595/) (2022)
- [RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition](https://mlsanity.com/paper/1805.05225/) (2018)
- [Opening the Black Box of wav2vec Feature Encoder](https://mlsanity.com/paper/2210.15386/) (2022)
- [Conformer-based Hybrid ASR System for Switchboard Dataset](https://mlsanity.com/paper/2111.03442/) (2021)
- [Efficient Training of Neural Transducer for Speech Recognition](https://mlsanity.com/paper/2204.10586/) (2022)
- [On-demand compute reduction with stochastic wav2vec 2.0](https://mlsanity.com/paper/2204.11934/) (2022)
- [On Architectures and Training for Raw Waveform Feature Extraction in ASR](https://mlsanity.com/paper/2104.04298/) (2021)

## Built on by (most cited first, 4 of 4)

- [Regularizing Learnable Feature Extraction for Automatic Speech Recognition](https://mlsanity.com/paper/2506.09804/) (2025)
- [Multi-modal Transfer Learning for Dynamic Facial Emotion Recognition in the Wild](https://mlsanity.com/paper/2504.21248/) (2025)
- [Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs](https://mlsanity.com/paper/2508.17914/) (2025)
- [Unified Learnable 2D Convolutional Feature Extraction for ASR](https://mlsanity.com/paper/2509.10031/) (2025)

## 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.