Speakerly: A Voice-based Writing Assistant for Text Composition

Dhruv Kumar, Vipul Raheja, Alice Kaiser-Schatzlein, Robyn Perry, Apurva Joshi, Justin Hugues-Nuger, Samuel Lou, Navid Chowdhury


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.
Anthology ID:
2023.emnlp-industry.38
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
December
Year:
2023
Address:
Singapore
Editors:
Mingxuan Wang, Imed Zitouni
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
396–407
Language:
URL:
https://aclanthology.org/2023.emnlp-industry.38
DOI:
10.18653/v1/2023.emnlp-industry.38
Bibkey:
Cite (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.
Cite (Informal):
Speakerly: A Voice-based Writing Assistant for Text Composition (Kumar et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-industry.38.pdf
Video:
 https://aclanthology.org/2023.emnlp-industry.38.mp4