@inproceedings{kumar-etal-2023-speakerly,
title = "Speakerly: A Voice-based Writing Assistant for Text Composition",
author = "Kumar, Dhruv and
Raheja, Vipul and
Kaiser-Schatzlein, Alice and
Perry, Robyn and
Joshi, Apurva and
Hugues-Nuger, Justin and
Lou, Samuel and
Chowdhury, Navid",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.38",
doi = "10.18653/v1/2023.emnlp-industry.38",
pages = "396--407",
abstract = "We present Speakerly, a new real-time voice-based writing assistance system that helps users with text composition across various use cases such as emails, instant messages, and notes. The user can interact with the system through instructions or dictation, and the system generates a well-formatted and coherent document. We describe the system architecture and detail how we address the various challenges while building and deploying such a system at scale. More specifically, our system uses a combination of small, task-specific models as well as pre-trained language models for fast and effective text composition while supporting a variety of input modes for better usability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2023-speakerly">
<titleInfo>
<title>Speakerly: A Voice-based Writing Assistant for Text Composition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dhruv</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vipul</namePart>
<namePart type="family">Raheja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Kaiser-Schatzlein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robyn</namePart>
<namePart type="family">Perry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apurva</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Hugues-Nuger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Navid</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present Speakerly, a new real-time voice-based writing assistance system that helps users with text composition across various use cases such as emails, instant messages, and notes. The user can interact with the system through instructions or dictation, and the system generates a well-formatted and coherent document. We describe the system architecture and detail how we address the various challenges while building and deploying such a system at scale. More specifically, our system uses a combination of small, task-specific models as well as pre-trained language models for fast and effective text composition while supporting a variety of input modes for better usability.</abstract>
<identifier type="citekey">kumar-etal-2023-speakerly</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.38</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.38</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>396</start>
<end>407</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speakerly: A Voice-based Writing Assistant for Text Composition
%A Kumar, Dhruv
%A Raheja, Vipul
%A Kaiser-Schatzlein, Alice
%A Perry, Robyn
%A Joshi, Apurva
%A Hugues-Nuger, Justin
%A Lou, Samuel
%A Chowdhury, Navid
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F kumar-etal-2023-speakerly
%X We present Speakerly, a new real-time voice-based writing assistance system that helps users with text composition across various use cases such as emails, instant messages, and notes. The user can interact with the system through instructions or dictation, and the system generates a well-formatted and coherent document. We describe the system architecture and detail how we address the various challenges while building and deploying such a system at scale. More specifically, our system uses a combination of small, task-specific models as well as pre-trained language models for fast and effective text composition while supporting a variety of input modes for better usability.
%R 10.18653/v1/2023.emnlp-industry.38
%U https://aclanthology.org/2023.emnlp-industry.38
%U https://doi.org/10.18653/v1/2023.emnlp-industry.38
%P 396-407
Markdown (Informal)
[Speakerly: A Voice-based Writing Assistant for Text Composition](https://aclanthology.org/2023.emnlp-industry.38) (Kumar et al., EMNLP 2023)
ACL
- Dhruv Kumar, Vipul Raheja, Alice Kaiser-Schatzlein, Robyn Perry, Apurva Joshi, Justin Hugues-Nuger, Samuel Lou, and Navid Chowdhury. 2023. Speakerly: A Voice-based Writing Assistant for Text Composition. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 396–407, Singapore. Association for Computational Linguistics.