Durational cues to word boundaries in clear speech
Speech Communication
Predicting hyperarticulate speech during human-computer error resolution
Speech Communication
Spoken Language Processing: A Guide to Theory, Algorithm, and System Development
Spoken Language Processing: A Guide to Theory, Algorithm, and System Development
Toward conversational human-computer interaction
AI Magazine
Automated Natural Spoken Dialog
Computer
How to find trouble in communication
Speech Communication - Special issue on speech and emotion
The intelligent voice-interactive interface
CHI '82 Proceedings of the 1982 Conference on Human Factors in Computing Systems
Characterizing and recognizing spoken corrections in human-computer dialogue
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Targeted help for spoken dialogue systems: intelligent feedback improves naive users' performance
EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
HLT '91 Proceedings of the workshop on Speech and Natural Language
Characterizing and Predicting Corrections in Spoken Dialogue Systems
Computational Linguistics
A Conversational Telephone Messaging System
IEEE Transactions on Consumer Electronics
Reducing working memory load in spoken dialogue systems
Interacting with Computers
Using reinforcement learning to create communication channel management strategies for diverse users
SLPAT '10 Proceedings of the NAACL HLT 2010 Workshop on Speech and Language Processing for Assistive Technologies
How does the representation of the computer evolve during human-computer dialogue?
Proceedings of the 30th European Conference on Cognitive Ergonomics
CHI '13 Extended Abstracts on Human Factors in Computing Systems
| Hi-index | 0.00 |
In this paper we examine the two-way relationship between hyperarticulation and evidence of misrecognition of computer-directed speech. We report the results of an experiment in which speakers spoke to a simulated speech recognizer and received text feedback about what had been ''recognized''. At pre-determined points in the dialog, recognition errors were staged, and speakers made repairs. Each repair utterance was paired with the utterance preceding the staged recognition error and coded for adaptations associated with hyperarticulate speech: speaking rate and phonetically clear speech. Our results demonstrate that hyperarticulation is a targeted and flexible adaptation rather than a generalized and stable mode of speaking. Hyperarticulation increases after evidence of misrecognition and then decays gradually over several turns in the absence of further misrecognitions. When repairing misrecognized speech, speakers are more likely to clearly articulate constituents that were apparently misrecognized than those either before or after the troublesome constituents, and more likely to clearly articulate content words than function words. Finally, we found no negative impact of hyperarticulation on speech recognition performance.