Speaker Anonymization for Children's Oral Reading Assessment
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 40814-40821
DOI: 10.1609/aaai.v40i48.42113 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Sandipan Dhar und 2 weiteren Autor:innen.
Themen: Kinderkrankenpflege
Abstract (Originalsprache)
Speaker anonymization aims to modify the speech signal in order to protect the identity of a speaker while preserving the linguistic content. Despite the increasing use of children's voices in educational applications, such as oral reading fluency (ORF) assessment, there is little work on the anonymization aspects. In this work, we investigate the effectiveness of available speaker anonymization methods drawing from traditional speech-production based approaches and a neural codec based method. We investigate the trade-off between privacy protection, measured as the degree of anonymity, and utility preservation, which in the current context of ORF assessment, includes the segmental and suprasegmental features of children’s read speech utterances. We report objective and subjective evaluations using two child-speaker datasets: MPS and SpeechOcean. Our objective evaluation results indicate that the speech-production based method of vocal tract length normalization coupled with pitch-transposition achieves the best balance between privacy and utility. Subjective listening results indicate that naturalness is achievable across methods while the neural method fails to preserve age characteristics, which are more easily controlled by the speech-production driven methods.
Zitieren
APA
Dhar, S., Chetupalli, S. R., & Rao, P. (2026). Speaker Anonymization for Children's Oral Reading Assessment. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 40814-40821. https://doi.org/10.1609/aaai.v40i48.42113
Vancouver
Dhar S, Chetupalli SR, Rao P. Speaker Anonymization for Children's Oral Reading Assessment. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):40814-40821. doi:10.1609/aaai.v40i48.42113
BibTeX
@article{Dhar2026,
author = {Dhar, Sandipan and Chetupalli, Srikanth Raj and Rao, Preeti},
title = {Speaker Anonymization for Children's Oral Reading Assessment},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {40814--40821},
doi = {10.1609/aaai.v40i48.42113}
}
EUVIMED