Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces

Tuomas Kaseva, Hemant Kathania, Aku Rouhe, Mikko Kurimo

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

18 Downloads (Pure)


For children, the system trained on a large corpus of adult speakers performed worse than a system trained on a much smaller corpus of children’s speech. This is due to the acoustic mismatch between training and testing data. To capture more acoustic variability we trained a shared system with mixed data from adults and children. The shared system yields the best EER for children with no degradation for adults. Thus, the single system trained with mixed data is applicable for speaker verification for both adults and children.
Original languageEnglish
Title of host publicationProceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa), May 31-June 2, 2021
Place of PublicationSweden
PublisherLinköping University Electronic Press
Number of pages8
ISBN (Electronic)978-91-7929-614-8
Publication statusPublished - 2021
MoE publication typeA4 Conference publication
EventNordic Conference on Computational Linguistics - Reykjavik, Iceland
Duration: 31 May 20212 Jun 2021

Publication series

NameLinköping Electronic Conference Proceedings
ISSN (Print)1650-3686
ISSN (Electronic)1650-3740


ConferenceNordic Conference on Computational Linguistics
Abbreviated titleNoDaLiDa


Dive into the research topics of 'Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces'. Together they form a unique fingerprint.

Cite this