@inproceedings{kim-etal-2019-audiocaps,
title = "{A}udio{C}aps: Generating Captions for Audios in The Wild",
author = "Kim, Chris Dongjoo and
Kim, Byeongchang and
Lee, Hyunmin and
Kim, Gunhee",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1011",
doi = "10.18653/v1/N19-1011",
pages = "119--132",
abstract = "We explore the problem of Audio Captioning: generating natural language description for any kind of audio in the wild, which has been surprisingly unexplored in previous research. We contribute a large-scale dataset of 46K audio clips with human-written text pairs collected via crowdsourcing on the AudioSet dataset. Our thorough empirical studies not only show that our collected captions are indeed faithful to audio inputs but also discover what forms of audio representation and captioning models are effective for the audio captioning. From extensive experiments, we also propose two novel components that help improve audio captioning performance: the top-down multi-scale encoder and aligned semantic attention.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2019-audiocaps">
<titleInfo>
<title>AudioCaps: Generating Captions for Audios in The Wild</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="given">Dongjoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byeongchang</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunmin</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gunhee</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We explore the problem of Audio Captioning: generating natural language description for any kind of audio in the wild, which has been surprisingly unexplored in previous research. We contribute a large-scale dataset of 46K audio clips with human-written text pairs collected via crowdsourcing on the AudioSet dataset. Our thorough empirical studies not only show that our collected captions are indeed faithful to audio inputs but also discover what forms of audio representation and captioning models are effective for the audio captioning. From extensive experiments, we also propose two novel components that help improve audio captioning performance: the top-down multi-scale encoder and aligned semantic attention.</abstract>
<identifier type="citekey">kim-etal-2019-audiocaps</identifier>
<identifier type="doi">10.18653/v1/N19-1011</identifier>
<location>
<url>https://aclanthology.org/N19-1011</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>119</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AudioCaps: Generating Captions for Audios in The Wild
%A Kim, Chris Dongjoo
%A Kim, Byeongchang
%A Lee, Hyunmin
%A Kim, Gunhee
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F kim-etal-2019-audiocaps
%X We explore the problem of Audio Captioning: generating natural language description for any kind of audio in the wild, which has been surprisingly unexplored in previous research. We contribute a large-scale dataset of 46K audio clips with human-written text pairs collected via crowdsourcing on the AudioSet dataset. Our thorough empirical studies not only show that our collected captions are indeed faithful to audio inputs but also discover what forms of audio representation and captioning models are effective for the audio captioning. From extensive experiments, we also propose two novel components that help improve audio captioning performance: the top-down multi-scale encoder and aligned semantic attention.
%R 10.18653/v1/N19-1011
%U https://aclanthology.org/N19-1011
%U https://doi.org/10.18653/v1/N19-1011
%P 119-132
Markdown (Informal)
[AudioCaps: Generating Captions for Audios in The Wild](https://aclanthology.org/N19-1011) (Kim et al., NAACL 2019)
ACL
- Chris Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim. 2019. AudioCaps: Generating Captions for Audios in The Wild. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 119–132, Minneapolis, Minnesota. Association for Computational Linguistics.