@inproceedings{kaseva-etal-2021-speaker,
title = "Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces",
author = "Kaseva, Tuomas and
Kathania, Hemant Kumar and
Rouhe, Aku and
Kurimo, Mikko",
editor = "Dobnik, Simon and
{\O}vrelid, Lilja",
booktitle = "Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may # " 31--2 " # jun,
year = "2021",
address = "Reykjavik, Iceland (Online)",
publisher = {Link{\"o}ping University Electronic Press, Sweden},
url = "https://aclanthology.org/2021.nodalida-main.9/",
pages = "86--93",
abstract = "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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaseva-etal-2021-speaker">
<titleInfo>
<title>Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tuomas</namePart>
<namePart type="family">Kaseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hemant</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Kathania</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aku</namePart>
<namePart type="family">Rouhe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Kurimo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-may 31–2 jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilja</namePart>
<namePart type="family">Øvrelid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press, Sweden</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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.</abstract>
<identifier type="citekey">kaseva-etal-2021-speaker</identifier>
<location>
<url>https://aclanthology.org/2021.nodalida-main.9/</url>
</location>
<part>
<date>2021-may 31–2 jun</date>
<extent unit="page">
<start>86</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces
%A Kaseva, Tuomas
%A Kathania, Hemant Kumar
%A Rouhe, Aku
%A Kurimo, Mikko
%Y Dobnik, Simon
%Y Øvrelid, Lilja
%S Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2021
%8 may 31–2 jun
%I Linköping University Electronic Press, Sweden
%C Reykjavik, Iceland (Online)
%F kaseva-etal-2021-speaker
%X 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.
%U https://aclanthology.org/2021.nodalida-main.9/
%P 86-93
Markdown (Informal)
[Speaker Verification Experiments for Adults and Children Using Shared Embedding Spaces](https://aclanthology.org/2021.nodalida-main.9/) (Kaseva et al., NoDaLiDa 2021)
ACL