@inproceedings{jiang-etal-2026-controlaudio,
title = "{C}ontrol{A}udio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling",
author = "Jiang, Yuxuan and
Chen, Zehua and
Ju, Zeqian and
Dai, Yusheng and
Dou, Weibei and
Zhu, Jun",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.62/",
pages = "1394--1413",
ISBN = "979-8-89176-390-6",
abstract = "Recent efforts on text-to-audio (TTA) generation are starting to explore fine-grained controllability, e.g., precise timing control, with innovations on conditioning techniques or training-free latent manipulations. However, constrained by data scarcity, their generation performance at scale is still limited. In this study, we recast high-controllability TTA generation as a multi-task learning problem, and introduce a progressive diffusion modeling approach, ControlAudio. Our method adeptly fits distributions conditioned on fine-grained information, including text, timing, and phoneme features, through a step-by-step strategy. First, we propose a data construction method spanning both annotation and simulation, augmenting condition information in the sequence of text, timing, and phoneme. Second, at the model training stage, we pretrain a scalable diffusion transformer (DiT) on large-scale text-audio pairs, achieving high-fidelity TTA generation, and then incrementally integrate the timing and phoneme features, expanding controllability. Finally, at the inference stage, we propose progressively guided generation, which sequentially emphasizes more fine-grained information, aligning inherently with the coarse-to-fine sampling nature of DiT. Extensive experiments show that ControlAudio achieves state-of-the-art performance in terms of temporal accuracy and speech clarity, significantly outperforming existing methods on both objective and subjective evaluations. Demo samples are available at: https://control-audio.github.io/Control-Audio."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2026-controlaudio">
<titleInfo>
<title>ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuxuan</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zehua</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeqian</namePart>
<namePart type="family">Ju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusheng</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weibei</namePart>
<namePart type="family">Dou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Recent efforts on text-to-audio (TTA) generation are starting to explore fine-grained controllability, e.g., precise timing control, with innovations on conditioning techniques or training-free latent manipulations. However, constrained by data scarcity, their generation performance at scale is still limited. In this study, we recast high-controllability TTA generation as a multi-task learning problem, and introduce a progressive diffusion modeling approach, ControlAudio. Our method adeptly fits distributions conditioned on fine-grained information, including text, timing, and phoneme features, through a step-by-step strategy. First, we propose a data construction method spanning both annotation and simulation, augmenting condition information in the sequence of text, timing, and phoneme. Second, at the model training stage, we pretrain a scalable diffusion transformer (DiT) on large-scale text-audio pairs, achieving high-fidelity TTA generation, and then incrementally integrate the timing and phoneme features, expanding controllability. Finally, at the inference stage, we propose progressively guided generation, which sequentially emphasizes more fine-grained information, aligning inherently with the coarse-to-fine sampling nature of DiT. Extensive experiments show that ControlAudio achieves state-of-the-art performance in terms of temporal accuracy and speech clarity, significantly outperforming existing methods on both objective and subjective evaluations. Demo samples are available at: https://control-audio.github.io/Control-Audio.</abstract>
<identifier type="citekey">jiang-etal-2026-controlaudio</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.62/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1394</start>
<end>1413</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling
%A Jiang, Yuxuan
%A Chen, Zehua
%A Ju, Zeqian
%A Dai, Yusheng
%A Dou, Weibei
%A Zhu, Jun
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F jiang-etal-2026-controlaudio
%X Recent efforts on text-to-audio (TTA) generation are starting to explore fine-grained controllability, e.g., precise timing control, with innovations on conditioning techniques or training-free latent manipulations. However, constrained by data scarcity, their generation performance at scale is still limited. In this study, we recast high-controllability TTA generation as a multi-task learning problem, and introduce a progressive diffusion modeling approach, ControlAudio. Our method adeptly fits distributions conditioned on fine-grained information, including text, timing, and phoneme features, through a step-by-step strategy. First, we propose a data construction method spanning both annotation and simulation, augmenting condition information in the sequence of text, timing, and phoneme. Second, at the model training stage, we pretrain a scalable diffusion transformer (DiT) on large-scale text-audio pairs, achieving high-fidelity TTA generation, and then incrementally integrate the timing and phoneme features, expanding controllability. Finally, at the inference stage, we propose progressively guided generation, which sequentially emphasizes more fine-grained information, aligning inherently with the coarse-to-fine sampling nature of DiT. Extensive experiments show that ControlAudio achieves state-of-the-art performance in terms of temporal accuracy and speech clarity, significantly outperforming existing methods on both objective and subjective evaluations. Demo samples are available at: https://control-audio.github.io/Control-Audio.
%U https://aclanthology.org/2026.acl-long.62/
%P 1394-1413
Markdown (Informal)
[ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling](https://aclanthology.org/2026.acl-long.62/) (Jiang et al., ACL 2026)
ACL
- Yuxuan Jiang, Zehua Chen, Zeqian Ju, Yusheng Dai, Weibei Dou, and Jun Zhu. 2026. ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1394–1413, San Diego, California, United States. Association for Computational Linguistics.