# Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs

arXiv: https://arxiv.org/abs/2508.17914 · HTML: https://mlsanity.com/paper/2508.17914/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 25 Aug 2025.

## Builds on (most cited first, 7 of 7)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Simple and Effective Zero-shot Cross-lingual Phoneme Recognition](https://mlsanity.com/paper/2109.11680/) (2021)
- [Analyzing Hidden Representations in End-to-End Automatic Speech Recognition Systems](https://mlsanity.com/paper/1709.04482/) (2017)
- [Probing Acoustic Representations for Phonetic Properties](https://mlsanity.com/paper/2010.13007/) (2020)
- [Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/1907.04224/) (2019)
- [Comparative Analysis of the wav2vec 2.0 Feature Extractor](https://mlsanity.com/paper/2308.04286/) (2023)

## Abstract (arXiv)

Automatic Speech Recognition has advanced with self-supervised learning, enabling feature extraction directly from raw audio. In Wav2Vec, a CNN first transforms audio into feature vectors before the transformer processes them. This study examines CNN-extracted information for monophthong vowels using the TIMIT corpus. We compare MFCCs, MFCCs with formants, and CNN activations by training SVM classifiers for front-back vowel identification, assessing their classification accuracy to evaluate phonetic representation.