Proceedings. VLSI and Computer Peripherals. COMPEURO 89
DOI: 10.1109/cmpeur.1989.93377
|View full text |Cite
|
Sign up to set email alerts
|

Experimenting natural-language dictation with a 20000-word speech recognizer

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Publication Types

Select...
2
2

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 6 publications
0
3
0
Order By: Relevance
“…However, formal evaluations of dictation systems reported either only small productivity increases [Alto et al 1989], lack of user acceptance despite significant productivity increases [Lai and Vergo 1987], or no gain at all [Karat et al 1999], unless users learn efficient error correction strategies through extended exposure to the dictation system [Karat et al 2000]. By applying the performance model, this article inferred lower bounds on recognition accuracy and error correction speed for realizing productivity gains with dictation systems.…”
Section: Discussionmentioning
confidence: 93%
“…However, formal evaluations of dictation systems reported either only small productivity increases [Alto et al 1989], lack of user acceptance despite significant productivity increases [Lai and Vergo 1987], or no gain at all [Karat et al 1999], unless users learn efficient error correction strategies through extended exposure to the dictation system [Karat et al 2000]. By applying the performance model, this article inferred lower bounds on recognition accuracy and error correction speed for realizing productivity gains with dictation systems.…”
Section: Discussionmentioning
confidence: 93%
“…These scripts used dialogue from established natural speech authoring actions, such as re-speaking and self-repair [39,43], or issuing commands [18]. In line with natural speech for dictation and text editing [1,18], the scripts involved a combination of Editing-after-Composition (EAC) strategies (e.g., "stars, don't need 'stars', delete 'stars' ") and Editing-while-Composing (EWC) strategies, such as re-speaking for overwriting.…”
Section: Mainmentioning
confidence: 99%
“…Speaking is considered to be one of the most natural input modalities for text input and for general interactions with a computer. Current statistics show that voice search is used by 41% of adults at least once a day 1 , showing how the use of speech as primary modality for user engagement is becoming increasingly widespread [19]. Smart speakers, conversational agents (CAs), dictation interfaces, and other speech-based systems and environments can be found in our homes, workplaces, public spaces, and even in our pockets.…”
Section: Introductionmentioning
confidence: 99%