Improving End-to-End Models for Children’s Speech Recognition

Research output: Contribution to journalArticleScientificpeer-review

96 Downloads (Pure)

Abstract

Children’s Speech Recognition (CSR) is a challenging task due to the high variability in children’s speech patterns and limited amount of available annotated children’s speech data. We aim to improve CSR in the often-occurring scenario that no children’s speech data is available for training the Automatic Speech Recognition (ASR) systems. Traditionally, Vocal Tract Length Normalization (VTLN) has been widely used in hybrid ASR systems to address acoustic mismatch and variability in children’s speech when training models on adults’ speech. Meanwhile, End-to-End (E2E) systems often use data augmentation methods to create child-like speech from adults’ speech. For adult speech-trained ASRs, we investigate the effectiveness of augmentation methods; speed perturbations and spectral augmentation, along with VTLN, in an E2E framework for the CSR task, comparing these across Dutch, German, and Mandarin. We applied VTLN at different stages (training/test) of the ASR and conducted age and gender analyses. Our experiments showed highly similar patterns across the languages: Speed Perturbations and Spectral Augmentation yield significant performance improvements, while VTLN provided further improvements while maintaining recognition performance on adults’ speech (depending on when it is applied). Additionally, VTLN showed performance improvement for both male and female speakers and was particularly effective for younger children.
Original languageEnglish
Article number2353
Number of pages28
JournalApplied Sciences
Volume14
Issue number6
DOIs
Publication statusPublished - 2024

Keywords

  • children’s speech recognition
  • speed perturbations
  • spectral augmentation
  • vocal tract length normalization
  • end-to-end automatic speech recognition

Fingerprint

Dive into the research topics of 'Improving End-to-End Models for Children’s Speech Recognition'. Together they form a unique fingerprint.

Cite this