@inproceedings{akhtiamov-etal-2019-cross,
title = "Cross-Corpus Data Augmentation for Acoustic Addressee Detection",
author = "Akhtiamov, Oleg and
Siegert, Ingo and
Karpov, Alexey and
Minker, Wolfgang",
editor = "Nakamura, Satoshi and
Gasic, Milica and
Zukerman, Ingrid and
Skantze, Gabriel and
Nakano, Mikio and
Papangelis, Alexandros and
Ultes, Stefan and
Yoshino, Koichiro",
booktitle = "Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue",
month = sep,
year = "2019",
address = "Stockholm, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5933",
doi = "10.18653/v1/W19-5933",
pages = "274--283",
abstract = "Acoustic addressee detection (AD) is a modern paralinguistic and dialogue challenge that especially arises in voice assistants. In the present study, we distinguish addressees in two settings (a conversation between several people and a spoken dialogue system, and a conversation between several adults and a child) and introduce the first competitive baseline (unweighted average recall equals 0.891) for the Voice Assistant Conversation Corpus that models the first setting. We jointly solve both classification problems, using three models: a linear support vector machine dealing with acoustic functionals and two neural networks utilising raw waveforms alongside with acoustic low-level descriptors. We investigate how different corpora influence each other, applying the mixup approach to data augmentation. We also study the influence of various acoustic context lengths on AD. Two-second speech fragments turn out to be sufficient for reliable AD. Mixup is shown to be beneficial for merging acoustic data (extracted features but not raw waveforms) from different domains that allows us to reach a higher classification performance on human-machine AD and also for training a multipurpose neural network that is capable of solving both human-machine and adult-child AD problems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akhtiamov-etal-2019-cross">
<titleInfo>
<title>Cross-Corpus Data Augmentation for Acoustic Addressee Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Akhtiamov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingo</namePart>
<namePart type="family">Siegert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Karpov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Minker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milica</namePart>
<namePart type="family">Gasic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ingrid</namePart>
<namePart type="family">Zukerman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Skantze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikio</namePart>
<namePart type="family">Nakano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandros</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koichiro</namePart>
<namePart type="family">Yoshino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Stockholm, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Acoustic addressee detection (AD) is a modern paralinguistic and dialogue challenge that especially arises in voice assistants. In the present study, we distinguish addressees in two settings (a conversation between several people and a spoken dialogue system, and a conversation between several adults and a child) and introduce the first competitive baseline (unweighted average recall equals 0.891) for the Voice Assistant Conversation Corpus that models the first setting. We jointly solve both classification problems, using three models: a linear support vector machine dealing with acoustic functionals and two neural networks utilising raw waveforms alongside with acoustic low-level descriptors. We investigate how different corpora influence each other, applying the mixup approach to data augmentation. We also study the influence of various acoustic context lengths on AD. Two-second speech fragments turn out to be sufficient for reliable AD. Mixup is shown to be beneficial for merging acoustic data (extracted features but not raw waveforms) from different domains that allows us to reach a higher classification performance on human-machine AD and also for training a multipurpose neural network that is capable of solving both human-machine and adult-child AD problems.</abstract>
<identifier type="citekey">akhtiamov-etal-2019-cross</identifier>
<identifier type="doi">10.18653/v1/W19-5933</identifier>
<location>
<url>https://aclanthology.org/W19-5933</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>274</start>
<end>283</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Corpus Data Augmentation for Acoustic Addressee Detection
%A Akhtiamov, Oleg
%A Siegert, Ingo
%A Karpov, Alexey
%A Minker, Wolfgang
%Y Nakamura, Satoshi
%Y Gasic, Milica
%Y Zukerman, Ingrid
%Y Skantze, Gabriel
%Y Nakano, Mikio
%Y Papangelis, Alexandros
%Y Ultes, Stefan
%Y Yoshino, Koichiro
%S Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
%D 2019
%8 September
%I Association for Computational Linguistics
%C Stockholm, Sweden
%F akhtiamov-etal-2019-cross
%X Acoustic addressee detection (AD) is a modern paralinguistic and dialogue challenge that especially arises in voice assistants. In the present study, we distinguish addressees in two settings (a conversation between several people and a spoken dialogue system, and a conversation between several adults and a child) and introduce the first competitive baseline (unweighted average recall equals 0.891) for the Voice Assistant Conversation Corpus that models the first setting. We jointly solve both classification problems, using three models: a linear support vector machine dealing with acoustic functionals and two neural networks utilising raw waveforms alongside with acoustic low-level descriptors. We investigate how different corpora influence each other, applying the mixup approach to data augmentation. We also study the influence of various acoustic context lengths on AD. Two-second speech fragments turn out to be sufficient for reliable AD. Mixup is shown to be beneficial for merging acoustic data (extracted features but not raw waveforms) from different domains that allows us to reach a higher classification performance on human-machine AD and also for training a multipurpose neural network that is capable of solving both human-machine and adult-child AD problems.
%R 10.18653/v1/W19-5933
%U https://aclanthology.org/W19-5933
%U https://doi.org/10.18653/v1/W19-5933
%P 274-283
Markdown (Informal)
[Cross-Corpus Data Augmentation for Acoustic Addressee Detection](https://aclanthology.org/W19-5933) (Akhtiamov et al., SIGDIAL 2019)
ACL