Rambler in the Wild: A Diary Study of LLM-Assisted Writing With Speech
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Speech-to-text technologies have been shown to improve text input efficiency and potentially lower the barriers to writing. Recent LLM-assisted dictation tools aim to support writing with speech by bridging the gaps between speaking and traditional writing. This case study reports on the real-world writing experiences of twelve academic or creative writers using one such tool, Rambler, to write various pieces such as blog posts, diaries, screenplays, notes, or fictional stories, etc. Through a ten-day diary study, we identified the participants' in-context writing strategies using Rambler, such as how they expanded from an outline or organized their loose thoughts for different writing goals. The interviews uncovered the psychological and productivity affordances of writing with speech, pointing to future directions of designing for this writing modality and the utilization of AI support.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This design preserved the authenticity of the creative process and enabled richer accounts of thought trajectories and decision-making [71].”
From How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters (2026) · cites this paper as [71]
Citations
Cites
Fereday, J., & Muir-Cochrane, E. (2006) · International Journal of Qualitative Methods · doi:10.1177/160940690600500107 · Cited by 11,829 · cited 1×
“Inductive thematic analysis was used to identify patterns and themes within data [5].”
Manner, J., Haarmann, S., Kolb, S., Herzberg, N., & Kopp, O. (2021) · Cited by 732
Patterns of entry and correction in large vocabulary continuous speech recognition systems
Karat, C.-M., Halverson, C., Horn, D., & Karat, J. (1999) · Proceedings of the SIGCHI conference on Human factors in computing systems the CHI is the limit - CHI '99 · doi:10.1145/302979.303160 · Cited by 275 · cited 1×
“However, challenges such as ambient noise interference, dialectal variations, and inaccuracies in speech recognition systems can hinder the accuracy and dependability of transcriptions, necessitating additional efforts to refine the converted speech text [6].”
Comparing Speech and Keyboard Text Entry for Short Messages in Two Languages on Touchscreen Phones
Ruan, S., Wobbrock, J. O., Liou, K., Ng, A., & Landay, J. A. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3161187 · Cited by 187
Beyond Text Generation: Supporting Writers with Continuous Automatic Text Summaries
Dang, H., Benharrak, K., Lehmann, F., & Buschek, D. (2022) · Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3526113.3545672 · Cited by 84
Improving Readability for Automatic Speech Recognition Transcription
Liao, J., Eskimez, Ş. E., Lu, L., Shi, Y., Gong, M., Shou, L., Qu, H., & Zeng, M. (2022) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3557894 · Cited by 79
Hierarchical Summarization for Longform Spoken Dialog
Li, D., Chen, T., Tung, A., & Chilton, L. B. (2021) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3472749.3474771 · Cited by 41 · cited 1×
“Previous research has explored the use of natural language processing (NLP) and large language models (LLMs) to assist in writing [4] and reviewing spoken dialogue [7, 8], especially in cleaning disfluency and speech recognition errors [2, 9, 13].”
Rambler: Supporting Writing With Speech via LLM-Assisted Gist Manipulation
Lin, S., Warner, J., Zamfirescu-Pereira, J. D., Lee, M. G., Jain, S., Cai, S., Lertvittayakumjorn, P., Huang, M. X., Zhai, S., Hartmann, B., et al. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642217 · Cited by 39
Self-citationNeural Error Corrective Language Models for Automatic Speech Recognition
Tanaka, T., Masumura, R., Masataki, H., & Aono, Y. (2018) · Interspeech (USB) · doi:10.21437/interspeech.2018-1430 · Cited by 31 · cited 1×
“Previous research has explored the use of natural language processing (NLP) and large language models (LLMs) to assist in writing [4] and reviewing spoken dialogue [7, 8], especially in cleaning disfluency and speech recognition errors [2, 9, 13].”
Improving Automatic Summarization for Browsing Longform Spoken Dialog
Li, D., Chen, T., Zadikian, A., Tung, A., & Chilton, L. B. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581339 · Cited by 18
Gist and Verbatim: Understanding Speech to Inform New Interfaces for Verbal Text Composition
Mehra, B., Shen, K., Yen, R., & Liu, C. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3597134 · Cited by 8
Self-citation
Research works printed but not linked: 3
- Kenneth C Arnold, April M Volzer, and Noah G Madrid. 2021. Generative Models can Help Writers without Writing for Them. In Joint Proceedings of the IUI 2021 Workshops. CEUR-WS Team, College Station, TX, USA, 8 pages. http://ceur-ws.org/Vol-2903/
- Saksham Bassi Giulio Duregon Siddhartha Jalagam and David Roth. 2023. End-to-End Speech Recognition and Disfluency Removal with Acoustic Language Model Pretraining. arxiv:https://arXiv.org/abs/2309.04516 [eess.AS] https://arxiv.org/abs/2309.04516 · arXiv
- David Crystal. 1995. Speaking of writing and writing of speaking. Longman Language Review 1 (1995) 5–8.
Cited by
How Do Human Creators Embrace Human-AI Co-Creation? A Perspective on Human Agency of Screenwriters
Tang, Y., Zhou, J., Li, H., Xie, X., Ma, X., & Qu, H. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790300 · Cited by 5
“This design preserved the authenticity of the creative process and enabled richer accounts of thought trajectories and decision-making [71].”
Zhang, R., Pan, Z., Yi, H., Qu, H., & Ma, X. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3798483 · Cited by 1
A Comparison of Speech and Typing Input for Creative Generative AI Tasks
RATHORE, N., Billakanti, T., Ceha, J., & Henderson, J. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816224 · Cited by 1
“Similarly, Rambler uses an LLM to extract the main ideas from spoken input (e.g., summaries and keywords) and provide tools that help users review and reorganize their dictated text [21, 37].”
Development of a Voice Assistant for Automated Creation of a Draft Version of a Scientific ArticlePreprint
Isaev, R., & Mukashova, A. (2025) · Preprints.org · doi:10.20944/preprints202505.1430.v1
Liang, Z., Chen, Y., Madi, N. A., & Liu, C. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791209
“This helps explain the low percentage of Sustained Reading found in Section 6.1.”
InfluentialSelf-citation
Metadata
- Authors
- Yang, X., Li, W., Lee, M. G., Li, Z., Zamfirescu-Pereira, J. D., & Liu, C.
- Affiliations
- City University of Hong Kong (HK)
- Stanford University (US)
- University of California, Berkeley (US)
- Venue
- Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2025-04-25
- Pages
- 1-9
- OpenAlex
- W4409720024
- Cited by
- 1
- References
- 11
- Citations by year
- 2026: 1
- FWCI
- 2.86
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Google Faculty Research Award (9229068)
- Topics
- Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
- Social Sciences › Education › Writing and Handwriting Education
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- large language models, speech synthesis, text-to-speech, diary study, user experience
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.