Abstract | ||
---|---|---|
Even as progress in speech technologies and task and dialog modeling has allowed the development of advanced spoken dialog systems, the low-level interaction behavior of those systems often remains rigid and inefficient. Based on an analysis of human-human and human-computer turn-taking in naturally occurring task-oriented dialogs, we define a set of features that can be automatically extracted and show that they can be used to inform efficient end-of-turn detection. We then frame turn-taking as decision making under uncertainty and describe the Finite-State Turn-Taking Machine (FSTTM), a decision-theoretic model that combines data-driven machine learning methods and a cost structure derived from Conversation Analysis to control the turn-taking behavior of dialog systems. Evaluation results on CMU Let's Go, a publicly deployed bus information system, confirm that the FSTTM significantly improves the responsiveness of the system compared to a standard threshold-based approach, as well as previous data-driven methods. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2168748.2168749 | TSLP |
Keywords | Field | DocType |
bus information system,dialog system,task-oriented dialog,dialog modeling,previous data-driven method,data-driven machine,conversation analysis,turn-taking behavior,human-computer turn-taking,low-level interaction behavior,information system,machine learning | Information system,Dialog box,Spoken dialog systems,Turn-taking,Computer science,Speech recognition,Conversation analysis,Artificial intelligence,Dialog system,Natural language processing,Task oriented | Journal |
Volume | Issue | ISSN |
9 | 1 | 1550-4875 |
Citations | PageRank | References |
17 | 0.79 | 31 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Antoine Raux | 1 | 423 | 33.54 |
Maxine Eskenazi | 2 | 979 | 127.53 |