Using confidence scores to improve hands-free speech based navigation in continuous dictation systems

Jinjuan Feng, Andrew L. Sears

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Speech recognition systems have improved dramatically, but recent studies confirm that error correction activities still account for 66-75% of the users' time, and 50% of that time is spent just getting to the errors that need to be corrected. While researchers have suggested that confidence scores could prove useful during the error correction process, the focus is typically on error detection. More importantly, empirical studies have failed to confirm any measurable benefits when confidence scores are used in this way within dictation-oriented applications. In this article, we provide data that explains why confidence scores are unlikely to be useful for error detection. We propose a new navigation technique for use when speech-only interactions are strongly preferred and common, desktop-sized displays are available. The results of an empirical study that highlights the potential of this new technique are reported. An informal comparison between the current study and previous research suggests the new technique reduces time spent on navigation by 18%. Future research should include additional studies that compare the proposed technique to previous non-speech and speech-based navigation solutions.

Original languageEnglish (US)
Pages (from-to)329-356
Number of pages28
JournalACM Transactions on Computer-Human Interaction
Volume11
Issue number4
DOIs
StatePublished - Dec 1 2004

Fingerprint

Navigation
Error detection
Error correction
Speech recognition
Display devices

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction

Cite this

@article{857599bb2b4046b8b6c08bf646dfe12a,
title = "Using confidence scores to improve hands-free speech based navigation in continuous dictation systems",
abstract = "Speech recognition systems have improved dramatically, but recent studies confirm that error correction activities still account for 66-75{\%} of the users' time, and 50{\%} of that time is spent just getting to the errors that need to be corrected. While researchers have suggested that confidence scores could prove useful during the error correction process, the focus is typically on error detection. More importantly, empirical studies have failed to confirm any measurable benefits when confidence scores are used in this way within dictation-oriented applications. In this article, we provide data that explains why confidence scores are unlikely to be useful for error detection. We propose a new navigation technique for use when speech-only interactions are strongly preferred and common, desktop-sized displays are available. The results of an empirical study that highlights the potential of this new technique are reported. An informal comparison between the current study and previous research suggests the new technique reduces time spent on navigation by 18{\%}. Future research should include additional studies that compare the proposed technique to previous non-speech and speech-based navigation solutions.",
author = "Jinjuan Feng and Sears, {Andrew L.}",
year = "2004",
month = "12",
day = "1",
doi = "10.1145/1035575.1035576",
language = "English (US)",
volume = "11",
pages = "329--356",
journal = "ACM Transactions on Computer-Human Interaction",
issn = "1073-0516",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

Using confidence scores to improve hands-free speech based navigation in continuous dictation systems. / Feng, Jinjuan; Sears, Andrew L.

In: ACM Transactions on Computer-Human Interaction, Vol. 11, No. 4, 01.12.2004, p. 329-356.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using confidence scores to improve hands-free speech based navigation in continuous dictation systems

AU - Feng, Jinjuan

AU - Sears, Andrew L.

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Speech recognition systems have improved dramatically, but recent studies confirm that error correction activities still account for 66-75% of the users' time, and 50% of that time is spent just getting to the errors that need to be corrected. While researchers have suggested that confidence scores could prove useful during the error correction process, the focus is typically on error detection. More importantly, empirical studies have failed to confirm any measurable benefits when confidence scores are used in this way within dictation-oriented applications. In this article, we provide data that explains why confidence scores are unlikely to be useful for error detection. We propose a new navigation technique for use when speech-only interactions are strongly preferred and common, desktop-sized displays are available. The results of an empirical study that highlights the potential of this new technique are reported. An informal comparison between the current study and previous research suggests the new technique reduces time spent on navigation by 18%. Future research should include additional studies that compare the proposed technique to previous non-speech and speech-based navigation solutions.

AB - Speech recognition systems have improved dramatically, but recent studies confirm that error correction activities still account for 66-75% of the users' time, and 50% of that time is spent just getting to the errors that need to be corrected. While researchers have suggested that confidence scores could prove useful during the error correction process, the focus is typically on error detection. More importantly, empirical studies have failed to confirm any measurable benefits when confidence scores are used in this way within dictation-oriented applications. In this article, we provide data that explains why confidence scores are unlikely to be useful for error detection. We propose a new navigation technique for use when speech-only interactions are strongly preferred and common, desktop-sized displays are available. The results of an empirical study that highlights the potential of this new technique are reported. An informal comparison between the current study and previous research suggests the new technique reduces time spent on navigation by 18%. Future research should include additional studies that compare the proposed technique to previous non-speech and speech-based navigation solutions.

UR - http://www.scopus.com/inward/record.url?scp=10844260787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10844260787&partnerID=8YFLogxK

U2 - 10.1145/1035575.1035576

DO - 10.1145/1035575.1035576

M3 - Article

AN - SCOPUS:10844260787

VL - 11

SP - 329

EP - 356

JO - ACM Transactions on Computer-Human Interaction

JF - ACM Transactions on Computer-Human Interaction

SN - 1073-0516

IS - 4

ER -