@inproceedings{shon-etal-2023-slue,
title = "{SLUE} Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks",
author = "Shon, Suwon and
Arora, Siddhant and
Lin, Chyi-Jiunn and
Pasad, Ankita and
Wu, Felix and
Sharma, Roshan S and
Wu, Wei-Lun and
Lee, Hung-yi and
Livescu, Karen and
Watanabe, Shinji",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.496",
doi = "10.18653/v1/2023.acl-long.496",
pages = "8906--8937",
abstract = "Spoken language understanding (SLU) tasks have been studied for many decades in the speech research community, but have not received as much attention as lower-level tasks like speech and speaker recognition. In this work, we introduce several new annotated SLU benchmark tasks based on freely available speech data, which complement existing benchmarks and address gaps in the SLU evaluation landscape. We contribute four tasks: question answering and summarization involve inference over longer speech sequences; named entity localization addresses the speech-specific task of locating the targeted content in the signal; dialog act classification identifies the function of a given speech utterance. In order to facilitate the development of SLU models that leverage the success of pre-trained speech representations, we will release a new benchmark suite, including for each task (i) curated annotations for a relatively small fine-tuning set, (ii) reproducible pipeline (speech recognizer + text model) and end-to-end baseline models and evaluation metrics, (iii) baseline model performance in various types of systems for easy comparisons. We present the details of data collection and annotation and the performance of the baseline models. We also analyze the sensitivity of pipeline models{'} performance to the speech recognition accuracy, using more than 20 publicly availablespeech recognition models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shon-etal-2023-slue">
<titleInfo>
<title>SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suwon</namePart>
<namePart type="family">Shon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddhant</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chyi-Jiunn</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankita</namePart>
<namePart type="family">Pasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roshan</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei-Lun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Livescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinji</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Spoken language understanding (SLU) tasks have been studied for many decades in the speech research community, but have not received as much attention as lower-level tasks like speech and speaker recognition. In this work, we introduce several new annotated SLU benchmark tasks based on freely available speech data, which complement existing benchmarks and address gaps in the SLU evaluation landscape. We contribute four tasks: question answering and summarization involve inference over longer speech sequences; named entity localization addresses the speech-specific task of locating the targeted content in the signal; dialog act classification identifies the function of a given speech utterance. In order to facilitate the development of SLU models that leverage the success of pre-trained speech representations, we will release a new benchmark suite, including for each task (i) curated annotations for a relatively small fine-tuning set, (ii) reproducible pipeline (speech recognizer + text model) and end-to-end baseline models and evaluation metrics, (iii) baseline model performance in various types of systems for easy comparisons. We present the details of data collection and annotation and the performance of the baseline models. We also analyze the sensitivity of pipeline models’ performance to the speech recognition accuracy, using more than 20 publicly availablespeech recognition models.</abstract>
<identifier type="citekey">shon-etal-2023-slue</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.496</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.496</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>8906</start>
<end>8937</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks
%A Shon, Suwon
%A Arora, Siddhant
%A Lin, Chyi-Jiunn
%A Pasad, Ankita
%A Wu, Felix
%A Sharma, Roshan S.
%A Wu, Wei-Lun
%A Lee, Hung-yi
%A Livescu, Karen
%A Watanabe, Shinji
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F shon-etal-2023-slue
%X Spoken language understanding (SLU) tasks have been studied for many decades in the speech research community, but have not received as much attention as lower-level tasks like speech and speaker recognition. In this work, we introduce several new annotated SLU benchmark tasks based on freely available speech data, which complement existing benchmarks and address gaps in the SLU evaluation landscape. We contribute four tasks: question answering and summarization involve inference over longer speech sequences; named entity localization addresses the speech-specific task of locating the targeted content in the signal; dialog act classification identifies the function of a given speech utterance. In order to facilitate the development of SLU models that leverage the success of pre-trained speech representations, we will release a new benchmark suite, including for each task (i) curated annotations for a relatively small fine-tuning set, (ii) reproducible pipeline (speech recognizer + text model) and end-to-end baseline models and evaluation metrics, (iii) baseline model performance in various types of systems for easy comparisons. We present the details of data collection and annotation and the performance of the baseline models. We also analyze the sensitivity of pipeline models’ performance to the speech recognition accuracy, using more than 20 publicly availablespeech recognition models.
%R 10.18653/v1/2023.acl-long.496
%U https://aclanthology.org/2023.acl-long.496
%U https://doi.org/10.18653/v1/2023.acl-long.496
%P 8906-8937
Markdown (Informal)
[SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks](https://aclanthology.org/2023.acl-long.496) (Shon et al., ACL 2023)
ACL
- Suwon Shon, Siddhant Arora, Chyi-Jiunn Lin, Ankita Pasad, Felix Wu, Roshan S Sharma, Wei-Lun Wu, Hung-yi Lee, Karen Livescu, and Shinji Watanabe. 2023. SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8906–8937, Toronto, Canada. Association for Computational Linguistics.