@inproceedings{he-etal-2025-ritta,
title = "{R}i{TTA}: Modeling Event Relations in Text-to-Audio Generation",
author = "He, Yuhang and
Jain, Yash and
Liu, Xubo and
Markham, Andrew and
Vineet, Vibhav",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.173/",
doi = "10.18653/v1/2025.emnlp-main.173",
pages = "3497--3511",
ISBN = "979-8-89176-332-6",
abstract = "Existing text-to-audio (TTA) generation methods have neither systematically explored audio event relation modeling, nor proposed any new framework to enhance this capability. In this work, we systematically study audio event relation modeling in TTA generation models. We first establish a benchmark for this task by: (1) proposing a comprehensive relation corpus covering all potential relations in real-world scenarios; (2) introducing a new audio event corpus encompassing commonly heard audios; and (3) proposing new evaluation metrics to assess audio event relation modeling from various perspectives. Furthermore, we propose a gated prompt tuning strategy that improves existing TTA models' relation modeling capability with negligible extra parameters. Specifically, we introduce learnable relation and event prompt that append to the text prompt before feeding to existing TTA models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2025-ritta">
<titleInfo>
<title>RiTTA: Modeling Event Relations in Text-to-Audio Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuhang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xubo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Markham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vibhav</namePart>
<namePart type="family">Vineet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Existing text-to-audio (TTA) generation methods have neither systematically explored audio event relation modeling, nor proposed any new framework to enhance this capability. In this work, we systematically study audio event relation modeling in TTA generation models. We first establish a benchmark for this task by: (1) proposing a comprehensive relation corpus covering all potential relations in real-world scenarios; (2) introducing a new audio event corpus encompassing commonly heard audios; and (3) proposing new evaluation metrics to assess audio event relation modeling from various perspectives. Furthermore, we propose a gated prompt tuning strategy that improves existing TTA models’ relation modeling capability with negligible extra parameters. Specifically, we introduce learnable relation and event prompt that append to the text prompt before feeding to existing TTA models.</abstract>
<identifier type="citekey">he-etal-2025-ritta</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.173</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.173/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>3497</start>
<end>3511</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RiTTA: Modeling Event Relations in Text-to-Audio Generation
%A He, Yuhang
%A Jain, Yash
%A Liu, Xubo
%A Markham, Andrew
%A Vineet, Vibhav
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F he-etal-2025-ritta
%X Existing text-to-audio (TTA) generation methods have neither systematically explored audio event relation modeling, nor proposed any new framework to enhance this capability. In this work, we systematically study audio event relation modeling in TTA generation models. We first establish a benchmark for this task by: (1) proposing a comprehensive relation corpus covering all potential relations in real-world scenarios; (2) introducing a new audio event corpus encompassing commonly heard audios; and (3) proposing new evaluation metrics to assess audio event relation modeling from various perspectives. Furthermore, we propose a gated prompt tuning strategy that improves existing TTA models’ relation modeling capability with negligible extra parameters. Specifically, we introduce learnable relation and event prompt that append to the text prompt before feeding to existing TTA models.
%R 10.18653/v1/2025.emnlp-main.173
%U https://aclanthology.org/2025.emnlp-main.173/
%U https://doi.org/10.18653/v1/2025.emnlp-main.173
%P 3497-3511
Markdown (Informal)
[RiTTA: Modeling Event Relations in Text-to-Audio Generation](https://aclanthology.org/2025.emnlp-main.173/) (He et al., EMNLP 2025)
ACL
- Yuhang He, Yash Jain, Xubo Liu, Andrew Markham, and Vibhav Vineet. 2025. RiTTA: Modeling Event Relations in Text-to-Audio Generation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 3497–3511, Suzhou, China. Association for Computational Linguistics.