Abstract | ||
---|---|---|
This paper presents a model of incremental speech generation in practical conversational systems. The model allows a conversational system to incrementally interpret spoken input, while simultaneously planning, realising and self-monitoring the system response. If these processes are time consuming and result in a response delay, the system can automatically produce hesitations to retain the floor. While speaking, the system utilises hidden and overt self-corrections to accommodate revisions in the system. The model has been implemented in a general dialogue system framework. Using this framework, we have implemented a conversational game application. A Wizard-of-Oz experiment is presented, where the automatic speech recognizer is replaced by a Wizard who transcribes the spoken input. In this setting, the incremental model allows the system to start speaking while the user's utterance is being transcribed. In comparison to a non-incremental version of the same system, the incremental version has a shorter response time and is perceived as more efficient by the users. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1016/j.csl.2012.05.004 | Computer Speech & Language |
Keywords | Field | DocType |
shorter response time,system response,towards incremental speech generation,incremental speech generation,conversational system,conversational game application,incremental model,response delay,practical conversational system,general dialogue system framework,incremental version,computer science | Automatic speech,System framework,Computer science,Utterance,Response delay,Incremental build model,Response time,Speech recognition,Artificial intelligence,Natural language processing,Wizard,Wizard of oz | Journal |
Volume | Issue | ISSN |
27 | 1 | 0885-2308 |
Citations | PageRank | References |
4 | 0.44 | 17 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gabriel Skantze | 1 | 485 | 46.16 |
Anna Hjalmarsson | 2 | 157 | 13.86 |