← Back to Publications List

SSChNet: Self Supervised Learning based pre-trained network for Child Speech Recognition

Students & Supervisors

Student Authors
Mahamodul Hasan Mahadi
Souhardo Rahman
Md. Nasif Safwan
Supervisors
Firoz Ahmed
Professor, Faculty, FST

Abstract

Automatic Speech Recognition (ASR) is a key part of human-computer interaction, playing a major role in educa tion, accessibility, and personal assistant technologies. However, recognizing child speech remains a significant challenge due to the scarcity of large labeled datasets and the distinctive traits of children’s voices, such as higher pitch, greater tonal variation, and frequent mispronunciations. ASR models predom inantly trained on adult speech often struggle to process child speech accurately. To address these challenges, we propose a modified framework based on the Wav2Vec2 architecture, which leverages self-supervised learning to pre-train on a large set of unlabeled child speech data, followed by fine-tuning on a smaller labeled dataset. This approach incorporates targeted enhancements, including pitch normalization, phoneme-aware masking, and a child-specific speech dataset, to better capture the unique characteristics of child speech. Our investigation show significant performance improvements, with the large model achieving a WER of 8.13% on MyST test and 14.87% on PFS test, demonstrating its ability to handle diverse and chal lenging datasets effectively. This framework offers a promising solution for developing ASR systems tailored for children, with potential applications in education, child-computer interaction, and accessibility tools.

Keywords

child speech recognition Wav2Vec2 MyST dataset speech recognition

Publication Details

  • Type of Publication: Conference 
  • Conference Name: 2nd International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM-2025)
  • Date of Conference: 27/06/2025 - 27/06/2025
  • Venue: Department of Computer Science and Engineering, Dhaka University of Engineering & Technology (DUET), Gazipur, Bangladesh
  • Organizer: Department of Computer Science and Engineering, Dhaka University of Engineering & Technology (DUET)
View on Publisher