Loading...
Please wait, while we are loading the content...
Similar Documents
Front-end Back-end ASR + VUI TTS Middle-end Device
| Content Provider | Semantic Scholar |
|---|---|
| Author | Fang, Hao Cheng, Hao Clark, Elizabeth Holtzman, Ariel Sap, Maarten Ostendorf, Mari Choi, Yejin Smith, Noah A. |
| Copyright Year | 2017 |
| Abstract | This paper introduces the University of Washington’s Alexa Prize socialbot, Sounding Board, which is designed to engage users with a wide variety of content. The system models the user utterance using a multi-dimensional representation. A hierarchical dialogue manager is employed where a master manages the overall conversation and a collection of miniskills manage different conversation segments. The system constructs responses using speech acts selected by the dialogue manager, where each speech act is instantiated with randomness to introduce variation to the conversation. Further, we analyze the impact of miniskill variety, user personality, and speech recognition performance on user interaction ratings. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://s3.amazonaws.com/alexaprize/2017/technical-article/soundingboard.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
