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

Domenico De Cristofaro, Vincenzo Norman Vitale, Alessandro Vietti
8/25/2025
cs.CL

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Explaining Spectrograms in Machine Learning: A Study on Neural Networks for Speech Classification

80% match2024

Evaluating the Effectiveness of Transformer Layers in Wav2Vec 2.0, XLS-R, and Whisper for Speaker Identification Tasks

79% match1 repo32025

Normalization through Fine-tuning: Understanding Wav2vec 2.0 Embeddings for Phonetic Analysis

79% match2025

Unsupervised Representations Improve Supervised Learning in Speech Emotion Recognition

78% match2023

Automatic classification of stop realisation with wav2vec2.0

77% match1 repo52025

Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs

77% match2025

Cite this paper

@article{cristofaro2025evaluating,
  title  = {Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs},
  author = {Domenico De Cristofaro and Vincenzo Norman Vitale and Alessandro Vietti},
  year   = {2025},
  eprint = {2508.17914},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.17914v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.17914.svg)](https://codeofpaper.com/paper/2508.17914)

Discussion