@inproceedings{chaudhuri-etal-2025-speechee,
title = "{S}peech{EE}@{XLLM}25: End-to-End Structured Event Extraction from Speech",
author = "Chaudhuri, Soham and
Biswas, Diganta and
Saha, Dipanjan and
Das, Dipankar and
Bandyopadhyay, Sivaji",
editor = "Fei, Hao and
Tu, Kewei and
Zhang, Yuhui and
Hu, Xiang and
Han, Wenjuan and
Jia, Zixia and
Zheng, Zilong and
Cao, Yixin and
Zhang, Meishan and
Lu, Wei and
Siddharth, N. and
{\O}vrelid, Lilja and
Xue, Nianwen and
Zhang, Yue",
booktitle = "Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.xllm-1.24/",
doi = "10.18653/v1/2025.xllm-1.24",
pages = "283--287",
ISBN = "979-8-89176-286-2",
abstract = "Event extraction from text is a complex taskthat involves the identification of event triggersand their supporting arguments. Whenapplied to speech, this task becomes evenmore challenging due to the continuous natureof audio signals and the need for robustAutomatic Speech Recognition (ASR). Thispaper proposes an approach that integratesASR with event extraction by utilizing theWhisper model for speech recognition and aText2Event2 Transformer for extracting eventsfrom English audio samples. The Whispermodel is used to generate transcripts from audio,which are then fed into the Text2Event2Transformer to identify event triggers and theirarguments. This approach combines two difficulttasks into one, streamlining the processof extracting structured event information directlyfrom audio. Our approach leverages arobust ASR system (Whisper) followed by aparameter-efficient transformer (Text2Event2fine-tuned via LoRA) to extract structuredevents from raw speech. Unlike prior worktrained on gold textual input, our pipeline istrained end-to-end on noisy ASR outputs. Despitesignificant resource constraints and datanoise, our system ranked first in the ACL 2025XLLM Shared Task II."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaudhuri-etal-2025-speechee">
<titleInfo>
<title>SpeechEE@XLLM25: End-to-End Structured Event Extraction from Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soham</namePart>
<namePart type="family">Chaudhuri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diganta</namePart>
<namePart type="family">Biswas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipanjan</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipankar</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sivaji</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kewei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjuan</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixia</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zilong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixin</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meishan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">N</namePart>
<namePart type="family">Siddharth</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>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-286-2</identifier>
</relatedItem>
<abstract>Event extraction from text is a complex taskthat involves the identification of event triggersand their supporting arguments. Whenapplied to speech, this task becomes evenmore challenging due to the continuous natureof audio signals and the need for robustAutomatic Speech Recognition (ASR). Thispaper proposes an approach that integratesASR with event extraction by utilizing theWhisper model for speech recognition and aText2Event2 Transformer for extracting eventsfrom English audio samples. The Whispermodel is used to generate transcripts from audio,which are then fed into the Text2Event2Transformer to identify event triggers and theirarguments. This approach combines two difficulttasks into one, streamlining the processof extracting structured event information directlyfrom audio. Our approach leverages arobust ASR system (Whisper) followed by aparameter-efficient transformer (Text2Event2fine-tuned via LoRA) to extract structuredevents from raw speech. Unlike prior worktrained on gold textual input, our pipeline istrained end-to-end on noisy ASR outputs. Despitesignificant resource constraints and datanoise, our system ranked first in the ACL 2025XLLM Shared Task II.</abstract>
<identifier type="citekey">chaudhuri-etal-2025-speechee</identifier>
<identifier type="doi">10.18653/v1/2025.xllm-1.24</identifier>
<location>
<url>https://aclanthology.org/2025.xllm-1.24/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>283</start>
<end>287</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SpeechEE@XLLM25: End-to-End Structured Event Extraction from Speech
%A Chaudhuri, Soham
%A Biswas, Diganta
%A Saha, Dipanjan
%A Das, Dipankar
%A Bandyopadhyay, Sivaji
%Y Fei, Hao
%Y Tu, Kewei
%Y Zhang, Yuhui
%Y Hu, Xiang
%Y Han, Wenjuan
%Y Jia, Zixia
%Y Zheng, Zilong
%Y Cao, Yixin
%Y Zhang, Meishan
%Y Lu, Wei
%Y Siddharth, N.
%Y Øvrelid, Lilja
%Y Xue, Nianwen
%Y Zhang, Yue
%S Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-286-2
%F chaudhuri-etal-2025-speechee
%X Event extraction from text is a complex taskthat involves the identification of event triggersand their supporting arguments. Whenapplied to speech, this task becomes evenmore challenging due to the continuous natureof audio signals and the need for robustAutomatic Speech Recognition (ASR). Thispaper proposes an approach that integratesASR with event extraction by utilizing theWhisper model for speech recognition and aText2Event2 Transformer for extracting eventsfrom English audio samples. The Whispermodel is used to generate transcripts from audio,which are then fed into the Text2Event2Transformer to identify event triggers and theirarguments. This approach combines two difficulttasks into one, streamlining the processof extracting structured event information directlyfrom audio. Our approach leverages arobust ASR system (Whisper) followed by aparameter-efficient transformer (Text2Event2fine-tuned via LoRA) to extract structuredevents from raw speech. Unlike prior worktrained on gold textual input, our pipeline istrained end-to-end on noisy ASR outputs. Despitesignificant resource constraints and datanoise, our system ranked first in the ACL 2025XLLM Shared Task II.
%R 10.18653/v1/2025.xllm-1.24
%U https://aclanthology.org/2025.xllm-1.24/
%U https://doi.org/10.18653/v1/2025.xllm-1.24
%P 283-287
Markdown (Informal)
[SpeechEE@XLLM25: End-to-End Structured Event Extraction from Speech](https://aclanthology.org/2025.xllm-1.24/) (Chaudhuri et al., XLLM 2025)
ACL
- Soham Chaudhuri, Diganta Biswas, Dipanjan Saha, Dipankar Das, and Sivaji Bandyopadhyay. 2025. SpeechEE@XLLM25: End-to-End Structured Event Extraction from Speech. In Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025), pages 283–287, Vienna, Austria. Association for Computational Linguistics.