# Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children's Speech

arXiv: https://arxiv.org/abs/2508.10332 · HTML: https://mlsanity.com/paper/2508.10332/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 34 references that are in the map.
- First posted on arXiv 14 Aug 2025.

## Builds on (most cited first, 8 of 8)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings](https://mlsanity.com/paper/2104.03502/) (2021)
- [Exploring wav2vec 2.0 on speaker verification and language identification](https://mlsanity.com/paper/2012.06185/) (2020)
- [Speech Emotion Recognition using Self-Supervised Features](https://mlsanity.com/paper/2202.03896/) (2022)
- [A Noise-Robust Self-supervised Pre-training Model Based Speech Representation Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2201.08930/) (2022)
- [Speaker Recognition for Children's Speech](https://mlsanity.com/paper/1609.07498/) (2016)
- [SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning](https://mlsanity.com/paper/2210.09524/) (2022)

## Built on by (most cited first, 1 of 1)

- [How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures](https://mlsanity.com/paper/2606.22177/) (2026)

## Abstract (arXiv)

Children's speech presents challenges for age and gender classification due to high variability in pitch, articulation, and developmental traits. While self-supervised learning (SSL) models perform well on adult speech tasks, their ability to encode speaker traits in children remains underexplored. This paper presents a detailed layer-wise analysis of four Wav2Vec2 variants using the PFSTAR and CMU Kids datasets. Results show that early layers (1-7) capture speaker-specific cues more effectively than deeper layers, which increasingly focus on linguistic information. Applying PCA further improves classification, reducing redundancy and highlighting the most informative components. The Wav2Vec2-large-lv60 model achieves 97.14% (age) and 98.20% (gender) on CMU Kids; base-100h and large-lv60 models reach 86.05% and 95.00% on PFSTAR. These results reveal how speaker traits are structured across SSL model depth and support more targeted, adaptive strategies for child-aware speech interfaces.