How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures

• URL: http://arxiv.org/abs/2606.22177v1
• Date: Sat, 20 Jun 2026 18:16:37 GMT
• Title: How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures
• Abstract summary: We present a comprehensive analysis of how age and gender information is encoded across layers of four widely used SSL models.<n>Results show that age- and gender-related information is unevenly distributed across SSL layers.<n>We show that reliable age and gender classification is achievable even from short speech segments of 1--3 seconds.
• Score: 38.10327438835634
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Self-supervised learning (SSL) models have become a central component of modern speech processing systems, as they enable the learning of rich acoustic representations without reliance on labeled data. Despite their success on adult speech, it remains unclear how effectively these models capture speaker-related attributes such as age and gender in children's speech, which differs substantially from adult speech due to ongoing physiological and cognitive development. Higher pitch, increased articulatory variability, and age-dependent acoustic changes make children's speech a particularly challenging domain. In this work, we present a comprehensive analysis of how age and gender information is encoded across layers of four widely used SSL models: Wav2Vec2, HuBERT, Data2Vec, and WavLM. Layer-wise features are extracted and evaluated using a lightweight CNN on two benchmark children's speech corpora, PFSTAR and CMU Kids. To analyze feature compactness and redundancy, PCA is applied to identify redundancy and highlight the dimensions that contribute most to classification performance. Experimental results show that age- and gender-related information is unevenly distributed across SSL layers, with early to mid-level layers encoding the strongest paralinguistic cues. HuBERT achieves the best overall performance for age classification, while Wav2Vec2 and HuBERT lead gender classification on PFSTAR and CMU Kids, respectively. Beyond single-split evaluation, we further demonstrate that these findings remain stable under speaker-wise cross-validation, layer aggregation, and cross-database evaluation, indicating robustness to data imbalance and domain mismatch. Finally, we show that reliable age and gender classification is achievable even from short speech segments of 1--3 seconds.

Related papers

• Abjad-Kids: An Arabic Speech Classification Dataset for Primary Education [0.0]
  This paper presents Abjad-Kids, an Arabic speech dataset designed for kindergarten and primary education.<n>The dataset consists of 46397 audio samples collected from children aged 3 - 12 years, covering 141 classes.<n>We propose a hierarchical audio classification based on CNN-LSTM architectures to address high intra-class similarity among Arabic phonemes.
  arXiv  Detail & Related papers  (2026-03-11T08:03:52Z)
• Can Layer-wise SSL Features Improve Zero-Shot ASR Performance for Children's Speech? [43.31597557333867]
  This study investigates the effectiveness of layer-wise features extracted from state-of-the-art SSL pre-trained models in improving the performance of ASR for children's speech in zero-shot scenarios.<n>The analysis identified the most effective layers for enhancing ASR performance on children's speech in a zero-shot scenario.
  arXiv  Detail & Related papers  (2025-08-28T21:32:36Z)
• Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs [59.230858581944425]
  Two dominant approaches have emerged for speech processing: discrete tokens and continuous features.<n>We compare self-supervised learning (SSL)-based discrete and continuous features under the same experimental settings.<n>Our findings reveal that continuous features generally outperform discrete tokens in various tasks.
  arXiv  Detail & Related papers  (2025-08-25T10:16:07Z)
• Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet [72.53502346791814]
  We compare flat-start training across datasets, SSL representations (WavLM, XEUS), and decoder architectures.<n> SSL representations are biased toward adult speech, with flat-start training on child speech mitigating these biases.<n>Age-related ASR and speaker verification analysis highlights the limitations of proprietary models.
  arXiv  Detail & Related papers  (2025-08-22T17:59:35Z)
• Layer-Wise Analysis of Self-Supervised Representations for Age and Gender Classification in Children's Speech [27.60599947546406]
  This paper presents a detailed analysis of four Wav2Vec2 variants using the PFSTAR and CMU Kids datasets.<n>Results show that early layers capture speaker-specific cues more effectively than deeper layers.<n>Applying PCA further improves classification, reducing redundancy and highlighting the most informative components.
  arXiv  Detail & Related papers  (2025-08-14T04:11:44Z)
• Age-Dependent Analysis and Stochastic Generation of Child-Directed Speech [10.369750912567714]
  We present an approach to model age-dependent linguistic properties of child-directed speech (CDS) using a language model (LM) trained on CDS transcripts and ages of the recipient children. We compare characteristics of the generated CDS against the real speech addressed at children of different ages, showing that the LM manages to capture age-dependent changes in CDS.
  arXiv  Detail & Related papers  (2024-05-13T12:35:10Z)
• Analysing the Impact of Audio Quality on the Use of Naturalistic Long-Form Recordings for Infant-Directed Speech Research [62.997667081978825]
  Modelling of early language acquisition aims to understand how infants bootstrap their language skills. Recent developments have enabled the use of more naturalistic training data for computational models. It is currently unclear how the sound quality could affect analyses and modelling experiments conducted on such data.
  arXiv  Detail & Related papers  (2023-05-03T08:25:37Z)
• Self-supervised models of audio effectively explain human cortical responses to speech [71.57870452667369]
  We capitalize on the progress of self-supervised speech representation learning to create new state-of-the-art models of the human auditory system. We show that these results show that self-supervised models effectively capture the hierarchy of information relevant to different stages of speech processing in human cortex.
  arXiv  Detail & Related papers  (2022-05-27T22:04:02Z)
• Self-Supervised Learning for speech recognition with Intermediate layer supervision [52.93758711230248]
  We propose Intermediate Layer Supervision for Self-Supervised Learning (ILS-SSL) ILS-SSL forces the model to concentrate on content information as much as possible by adding an additional SSL loss on the intermediate layers. Experiments on LibriSpeech test-other set show that our method outperforms HuBERT significantly.
  arXiv  Detail & Related papers  (2021-12-16T10:45:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.