A Holistic Evaluation Methodology for Multi-Party Spoken Conversational Agents
While research in multi-party spoken conversation with intelligent embodied agents has made significant progress in sub-tasks like speaker identification and non-verbal cues, there’s a gap in fully autonomous applications users can directly interact with. This lack translates to the absence of a standard methodology for evaluating multi-party conversational speech agents that considers both task-based system performance and user experience.
Authors
- Nancie Gunson (ORCID: https://orcid.org/0000-0001-5561-5174)
- Christian Dondrup (ORCID: https://orcid.org/0000-0003-4821-5871)
- Angus Addlesee (ORCID: https://orcid.org/0000-0001-9059-1104)
- Oliver Lemon (ORCID: https://orcid.org/0000-0001-9497-4743)
- Marta Romeo (ORCID: https://orcid.org/0000-0003-4438-0255)
- Daniel Hernández García (ORCID: https://orcid.org/0000-0001-9296-9692)
Institutions
- Heriot-Watt University (GB)
Publication Details
- Published
- 2024-09-16
- DOI
- https://doi.org/10.1145/3652988.3673966
- Primary Topic
- Speech and dialogue systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00