Information density and overlap in spoken dialogue
- Submitting institution
-
Heriot-Watt University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 14475435
- Type
- D - Journal article
- DOI
-
10.1016/j.csl.2015.11.001
- Title of journal
- Computer Speech and Language
- Article number
- -
- First page
- 82
- Volume
- 37
- Issue
- -
- ISSN
- 0885-2308
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper investigates the role of information density in identifying acceptable points of speaker overlap in dialogs with a spoken dialog system. This work is impactful it its contribution to more natural dialogue systems with polite and appropriate turn-taking, important for human-robot interaction and intelligent assistants such as Amazon Alexa and Google home. This work has influenced 9 studies and systems including ones that investigates what constitutes a ‘rude’ spoken dialogue systems (for example, ones that always barge-in). Such studies will ensure that systems in the future will be easy to use and non-offensive.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -