Towards Incremental Speech Generation in Dialogue Systems
G. Skantze, and A. Hjalmarsson. Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGdial 2010), Tokyo, Japan, page 1-8. (2010)
Abstract
We present a first step towards a model of speech generation for incremental dialogue systems. The model allows a dialogue system to incrementally interpret spoken input, while simultaneously planning, realising and selfmonitoring the system response. The model has been implemented in a general dialogue system framework. Using this framework, we have implemented a specific application and tested it in a Wizard-of-Oz setting, comparing it with a non-incremental version of the same system. The results show that the incremental version, while producing longer utterances, has a shorter response time and is perceived as more efficient by the users.
%0 Conference Paper
%1 SkantzeHjalmarsson10SIGDIAL
%A Skantze, Gabriel
%A Hjalmarsson, Anna
%B Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGdial 2010), Tokyo, Japan
%D 2010
%K v1205 paper ai user interface dialog interaction language speech processing zzz.th.c4
%P 1-8
%T Towards Incremental Speech Generation in Dialogue Systems
%U http://www.sigdial.org/workshops/workshop11/proc/pdf/SIGDIAL01.pdf
%X We present a first step towards a model of speech generation for incremental dialogue systems. The model allows a dialogue system to incrementally interpret spoken input, while simultaneously planning, realising and selfmonitoring the system response. The model has been implemented in a general dialogue system framework. Using this framework, we have implemented a specific application and tested it in a Wizard-of-Oz setting, comparing it with a non-incremental version of the same system. The results show that the incremental version, while producing longer utterances, has a shorter response time and is perceived as more efficient by the users.
@inproceedings{SkantzeHjalmarsson10SIGDIAL,
abstract = {We present a first step towards a model of speech generation for incremental dialogue systems. The model allows a dialogue system to incrementally interpret spoken input, while simultaneously planning, realising and selfmonitoring the system response. The model has been implemented in a general dialogue system framework. Using this framework, we have implemented a specific application and tested it in a Wizard-of-Oz setting, comparing it with a non-incremental version of the same system. The results show that the incremental version, while producing longer utterances, has a shorter response time and is perceived as more efficient by the users.},
added-at = {2012-05-30T10:54:13.000+0200},
author = {Skantze, Gabriel and Hjalmarsson, Anna},
biburl = {https://www.bibsonomy.org/bibtex/2621a6053cdc836c70566040951a58858/flint63},
booktitle = {Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGdial 2010), Tokyo, Japan},
file = {SIGdial Archive:2010/SkantzeHjalmarsson10SIGDIAL.pdf:PDF;Related Site:http\://www.speech.kth.se/jindigo/:URL},
groups = {public},
interhash = {9377dc536cbcbcc72510e1d12f208ece},
intrahash = {621a6053cdc836c70566040951a58858},
keywords = {v1205 paper ai user interface dialog interaction language speech processing zzz.th.c4},
pages = {1-8},
timestamp = {2018-04-16T12:02:41.000+0200},
title = {Towards Incremental Speech Generation in Dialogue Systems},
url = {http://www.sigdial.org/workshops/workshop11/proc/pdf/SIGDIAL01.pdf},
username = {flint63},
year = 2010
}