Filters








440 Hits in 3.0 sec

Continuous asr for flexible incremental dialogue

C. Breslin, M. Gasic, M. Henderson, D. Kim, M. Szummer, B. Thomson, P. Tsiakoulis, S. Young
2013 2013 IEEE International Conference on Acoustics, Speech and Signal Processing  
In this way, a flexible framework for incremental dialogue management is possible.  ...  Spoken dialogue systems provide a convenient way for users to interact with a machine using only speech.  ...  This paper lays the framework for a flexible incremental dialogue system that has no explicit VAD module.  ... 
doi:10.1109/icassp.2013.6639296 dblp:conf/icassp/BreslinGHKSTTY13 fatcat:oybgkw7hgjdvved6s2663dgnxm

Demonstration of the PARLANCE system: a data-driven incremental, spoken dialogue system for interactive search

Helen F. Hastie, Marie-Aude Aufaure, Panos Alexopoulos, Heriberto Cuayáhuitl, Nina Dethlefs, Milica Gasic, James Henderson, Oliver Lemon, Xingkun Liu, Peter Mika, Nesrine Ben Mustapha, Verena Rieser (+3 others)
2013 SIGDIAL Conferences  
The Parlance system for interactive search processes dialogue at a microturn level, displaying dialogue phenomena that play a vital role in human spoken conversation.  ...  The Parlance demonstration system differentiates from other incremental systems in that it is data-driven with an infrastructure that scales well.  ...  For the first pass of the ASR 2 , a fast bigram decoder performs continuous traceback generating word by word output.  ... 
dblp:conf/sigdial/HastieAACDGHLLM13 fatcat:fe35l6fvznenbouoqex2gypmjq

Towards Incremental Speech Generation in Dialogue Systems

Gabriel Skantze, Anna Hjalmarsson
2010 SIGDIAL Conferences  
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.  ...  But, as we will see, the output in an incremental system must also be flexible, as speech plans are incrementally produced and amended.  ... 
dblp:conf/sigdial/SkantzeH10 fatcat:br3lgfk46rcjlngzfbpqsdkcdu

Role Play Dialogue Aware Language Models Based on Conditional Hierarchical Recurrent Encoder-Decoder

Ryo Masumura, Tomohiro Tanaka, Atsushi Ando, Hirokazu Masataki, Yushi Aono
2018 Interspeech 2018  
Our motivation is to improve automatic speech recognition (ASR) performance in role play dialogues such as contact center dialogues and service center dialogues.  ...  We propose role play dialogue-aware language models (RPDA-LMs) that can leverage interactive contexts in role play multiturn dialogues for estimating the generative probability of words.  ...  In real ASR applications, more flexible LMs are required because two speaker's utterances rarely alternate.  ... 
doi:10.21437/interspeech.2018-2185 dblp:conf/interspeech/MasumuraTAMA18 fatcat:weuxxsutcrbhveygfhbwinhwxi

Audiovisual interface for Czech spoken dialogue system

Pavel Ircing, Jan Romportl, Zdenek Loose
2010 IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS  
The interface was originally designed for the dialogue system that allows elderly users to reminiscence about their photographs.  ...  However, the modular architecture of the whole system and the flexibility of messages that are used for communication between the modules facilitate seamless transition of the application to any domain  ...  It is basically a system comprising a central messaging hub and flexible mechanisms for information flow control.  ... 
doi:10.1109/icosp.2010.5656088 fatcat:o3wpsym3creb5ds5a2quora3lu

Information density and overlap in spoken dialogue

Nina Dethlefs, Helen Hastie, Heriberto Cuayáhuitl, Yanchao Yu, Verena Rieser, Oliver Lemon
2016 Computer Speech and Language  
modules in spoken and incremental dialogue systems.  ...  Incremental dialogue systems are often perceived as more responsive and natural because they are able to address phenomena of turn-taking and overlapping speech, such as backchannels or barge-ins.  ...  Thanks to Michael White for making the initial suggestion to explore information density in dialogue and to Chika Ugwuanyi for her help in setting up the website for experimentation. 28  ... 
doi:10.1016/j.csl.2015.11.001 fatcat:fvdh6nzucbbnznfxczwookcxrm

Robust Processing of Situated Spoken Dialogue [chapter]

Pierre Lison, Geert-Jan M. Kruijff
2009 Lecture Notes in Computer Science  
We present an integrated approach for addressing these two issues, based on a robust incremental parser.  ...  The approach is fully implemented in a dialogue system for autonomous robots.  ...  Conclusions We presented an integrated approach to the processing of (situated) spoken dialogue, suited to the specific needs and challenges encountered in human-robot interaction.  ... 
doi:10.1007/978-3-642-04617-9_31 fatcat:x7hdjodgbnfefb3r2xvijwewqy

A Temporal Simulator for Developing Turn-Taking Methods for Spoken Dialogue Systems

Ethan Selfridge, Peter A. Heeman
2012 SIGDIAL Conferences  
Developing sophisticated turn-taking behavior is necessary for next-generation dialogue systems.  ...  As a foundation for advancing turn-taking behavior, we present a temporal simulator that models the interaction between the user and the system, including speech, voice activity detection, and incremental  ...  Acknowledgments We thank to the reviewers for their thoughtful suggestions and critique. We acknowledge funding from the NSF under grant IIS-0713698.  ... 
dblp:conf/sigdial/SelfridgeH12 fatcat:vg52kxvb55d67huqzn4kzzycee

Enabling robust and fluid spoken dialogue with cognitively impaired users

Ramin Yaghoubzadeh, Stefan Kopp
2017 Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue  
This hybrid DM architecture affords incremental processing of uncertain input, a flexible, mixed-initiative information grounding process that can be adapted to users' cognitive capacities and interactive  ...  We present the flexdiam dialogue management architecture, which was developed in a series of projects dedicated to tailoring spoken interaction to the needs of users with cognitive impairments in an everyday  ...  NLU performed heuristic extraction of best guesses for this slot from ASR hypotheses.  ... 
doi:10.18653/v1/w17-5533 dblp:conf/sigdial/YaghoubzadehK17 fatcat:5ssdvokxuvbutci2kf5xagzzam

Supporting Spoken Assistant Systems with a Graphical User Interface that Signals Incremental Understanding and Prediction State

Casey Kennington, David Schlangen
2016 Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue  
We explore the use of a graphical output modality for signalling incremental understanding and prediction state of the dialogue system.  ...  By visualising the current dialogue state and possible continuations of it as a simple tree, and allowing interaction with that visualisation (e.g., for confirmations or corrections), the system provides  ...  Thanks also to Julian Hough for helping with experiments.  ... 
doi:10.18653/v1/w16-3631 dblp:conf/sigdial/KenningtonS16 fatcat:zypvqwmhbndplczy2omcqhtvr4

Evaluation and Optimisation of Incremental Processors

Timo Baumann, David Schlangen
2011 Dialogue and Discourse  
We believe that this work will help enable principled comparison of components for incremental dialogue systems and portability of results.  ...  Incremental spoken dialogue systems, which process user input as it unfolds, pose additional engineering challenges compared to more standard non-incremental systems: Their processing components must be  ...  We wish to thank the anonymous reviewers for their very helpful comments.  ... 
doi:10.5087/dad.2011.106 fatcat:7i4yhn64sbbzhbysszasajboku

It's About Time: Turn-Entry Timing For Situated Human-Robot Dialogue

Felix Gervits, Ravenna Thielstrom, Antonio Roque, Matthias Scheutz
2020 SIGDIAL Conferences  
Turn-entry timing is an important requirement for conversation, and one that few spoken dialogue systems consider.  ...  Our approach involves incremental processing and lexical prediction of the turn in progress, which allows a situated dialogue agent to start its turn and initiate actions earlier than would otherwise be  ...  We are especially grateful to Brad Oosterveld, Evan Krause, and Zach Munro for their technical assistance.  ... 
dblp:conf/sigdial/GervitsTRS20 fatcat:ubbdgxd4jfdljl5cmq3xddspea

Optimising Incremental Dialogue Decisions Using Information Density for Interactive Systems

Nina Dethlefs, Helen Wright Hastie, Verena Rieser, Oliver Lemon
2012 Conference on Empirical Methods in Natural Language Processing  
Unfortunately, prior work has focused largely on deterministic incremental decision making, rendering system behaviour less flexible and adaptive than is desirable.  ...  Incremental processing allows system designers to address several discourse phenomena that have previously been somewhat neglected in interactive systems, such as backchannels or barge-ins, but that can  ...  A Reward Function for Incremental Dialogue Based on Information Density To train the HRL agent, we use a partially datadriven reward function.  ... 
dblp:conf/emnlp/DethlefsHRL12 fatcat:q635cxywlvd5zeb7vxcqwoqg6a

A Multimodal In-Car Dialogue System That Tracks The Driver's Attention

Spyros Kousidis, Casey Kennington, Timo Baumann, Hendrik Buschmeier, Stefan Kopp, David Schlangen
2014 Proceedings of the 16th International Conference on Multimodal Interaction - ICMI '14  
In-car dialogue systems ignore these important aspects, making them more distracting than even cell-phone conversations.  ...  We developed and tested a "situationally-aware" dialogue system that can interrupt its speech when a situation which requires more attention from the driver is detected, and can resume when driving conditions  ...  The authors would like to thank Oliver Eickmeyer and Michael Bartholdt for helping implement the system setup, as well as Gerdis Anderson and Fabian Wohlgemuth for assisting as experimenters.  ... 
doi:10.1145/2663204.2663244 dblp:conf/icmi/KousidisKBBKS14 fatcat:4qb4umcctfasrllkpd2braxtde

An Event-Based Conversational System for the Nao Robot [chapter]

Ivana Kruijff-Korbayová, Georgios Athanasopoulos, Aryel Beck, Piero Cosi, Heriberto Cuayáhuitl, Tomas Dekens, Valentin Enescu, Antoine Hiolle, Bernd Kiefer, Hichem Sahli, Marc Schröder, Giacomo Sommavilla (+2 others)
2011 Proceedings of the Paralinguistic Information and its Integration in Spoken Dialogue Systems Workshop  
Parts of the research reported on in this paper were performed in the context of the EU-FP7 project ALIZ-E (ICT-248116), which develops embodied cognitive robots for believable any-depth affective interactions  ...  Automatic Speech Recognition (ASR) We chose CMU Sphinx 2 for its robust coverage of the features important for speech recognition in the project: large-vocabulary continuous ASR, N-best list output and  ...  Further planned improvements include incremental ASR implementation and dynamic language model creation.  ... 
doi:10.1007/978-1-4614-1335-6_14 fatcat:s6lwip72pve45lkfcqxe7w7b6m
« Previous Showing results 1 — 15 out of 440 results