@inproceedings{zhang-zhu-2026-praat,
title = "Praat++: Multimedia Annotation System for Speech and Vocalization",
author = "Zhang, Weiran and
Zhu, Kenny Q.",
editor = "Durrett, Greg and
Jian, Ping",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-demo.80/",
pages = "812--818",
ISBN = "979-8-89176-392-0",
abstract = "High-quality time-aligned annotation is fundamental to speech processing and animal vocalization research, yet precise boundary localization and consistent labeling remain challenging in collaborative settings. We present Praat++, a web-based multimedia annotation system designed for collaborative, video-informed, and AI-assisted timeline labeling of audio and video data. The system tightly synchronizes waveform, spectrogram, pitch, intensity, and time-aligned video playback with fine-grained region-based editing, enabling precise boundary refinement and improved label accuracy within a unified interface. Praat++ further incorporates role-aware workflow management and human-in-the-loop AI-assisted pre-annotation to enhance inter-annotator consistency and reduce labeling time. Through real-world multimodal speech and animal vocalization annotation scenarios, we demonstrate that Praat++ provides an integrated infrastructure for improving annotation quality and efficiency in dataset construction workflows. The demo video (https://www.youtube.com/watch?v=YboCoBRF5lg), website (https://redgiant.uta.edu/praat) and source code (https://github.com/UTA-ACL2/PraatPlusPlus) are now publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-zhu-2026-praat">
<titleInfo>
<title>Praat++: Multimedia Annotation System for Speech and Vocalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weiran</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenny</namePart>
<namePart type="given">Q</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 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Jian</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">979-8-89176-392-0</identifier>
</relatedItem>
<abstract>High-quality time-aligned annotation is fundamental to speech processing and animal vocalization research, yet precise boundary localization and consistent labeling remain challenging in collaborative settings. We present Praat++, a web-based multimedia annotation system designed for collaborative, video-informed, and AI-assisted timeline labeling of audio and video data. The system tightly synchronizes waveform, spectrogram, pitch, intensity, and time-aligned video playback with fine-grained region-based editing, enabling precise boundary refinement and improved label accuracy within a unified interface. Praat++ further incorporates role-aware workflow management and human-in-the-loop AI-assisted pre-annotation to enhance inter-annotator consistency and reduce labeling time. Through real-world multimodal speech and animal vocalization annotation scenarios, we demonstrate that Praat++ provides an integrated infrastructure for improving annotation quality and efficiency in dataset construction workflows. The demo video (https://www.youtube.com/watch?v=YboCoBRF5lg), website (https://redgiant.uta.edu/praat) and source code (https://github.com/UTA-ACL2/PraatPlusPlus) are now publicly available.</abstract>
<identifier type="citekey">zhang-zhu-2026-praat</identifier>
<location>
<url>https://aclanthology.org/2026.acl-demo.80/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>812</start>
<end>818</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Praat++: Multimedia Annotation System for Speech and Vocalization
%A Zhang, Weiran
%A Zhu, Kenny Q.
%Y Durrett, Greg
%Y Jian, Ping
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-392-0
%F zhang-zhu-2026-praat
%X High-quality time-aligned annotation is fundamental to speech processing and animal vocalization research, yet precise boundary localization and consistent labeling remain challenging in collaborative settings. We present Praat++, a web-based multimedia annotation system designed for collaborative, video-informed, and AI-assisted timeline labeling of audio and video data. The system tightly synchronizes waveform, spectrogram, pitch, intensity, and time-aligned video playback with fine-grained region-based editing, enabling precise boundary refinement and improved label accuracy within a unified interface. Praat++ further incorporates role-aware workflow management and human-in-the-loop AI-assisted pre-annotation to enhance inter-annotator consistency and reduce labeling time. Through real-world multimodal speech and animal vocalization annotation scenarios, we demonstrate that Praat++ provides an integrated infrastructure for improving annotation quality and efficiency in dataset construction workflows. The demo video (https://www.youtube.com/watch?v=YboCoBRF5lg), website (https://redgiant.uta.edu/praat) and source code (https://github.com/UTA-ACL2/PraatPlusPlus) are now publicly available.
%U https://aclanthology.org/2026.acl-demo.80/
%P 812-818
Markdown (Informal)
[Praat++: Multimedia Annotation System for Speech and Vocalization](https://aclanthology.org/2026.acl-demo.80/) (Zhang & Zhu, ACL 2026)
ACL
- Weiran Zhang and Kenny Q. Zhu. 2026. Praat++: Multimedia Annotation System for Speech and Vocalization. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 812–818, San Diego, California, United States. Association for Computational Linguistics.