Discovering Cues to Error Detection in Speech Recognition Output: A User-Centered Approach.

Author List: Zhou, Lina; Shi, Yongmei; Zhang, Dongsong; Sears, Andrew;
Journal of Management Information Systems, 2006, Volume 22, Issue 4, Page 237-270.
The great potential of speech recognition systems in freeing users' hands while interacting with computers has inspired a variety of promising applications. However, given the performance of the state-of-the-art speech recognition technology today, widespread acceptance of speech recognition technology would not be realistic without designing and developing new approaches to detecting and correcting recognition errors effectively. In seeking solutions to the above problem, identifying cues to error detection (CERD) is central. Our survey of the extant literature on the detection and correction of speech recognition errors reveals that the system-initiated, data-driven approach is dominant, but that heuristics from human users have been largely overlooked. This may have hindered the advance of speech technology. In this research, we propose a user-centered approach to discovering CERD. User studies are carried out to implement the approach. Content analysis of the collected verbal protocols lends itself to a taxonomy of CERD. The CERD discovered in this study can improve our knowledge on CERD by not only validating CERD from a user's perspective but also suggesting promising new CERD for detecting speech recognition errors. Moreover, the analysis of CERD in relation to error types and other CERD provides new insights into the context where specific CERD are effective. The findings of this study can be used to not only improve speech recognition output but also to provide context-aware support for error detection. This will help break the barrier for mainstream adoption of speech technology in a variety of information systems and applications.
Keywords: cues to error detection; speech recognition; taxonomy; verbal protocol analysis
Algorithm:

List of Topics

#60 0.166 analysis techniques structured categories protocol used evolution support methods protocols verbal improve object-oriented difficulties analyses category benchmark comparison provided recognition
#96 0.145 errors error construction testing spreadsheet recovery phase spreadsheets number failures inspection better studies modules rate replicated detection correction optimal discovering
#175 0.126 taxonomy systems different concept isd alternative generalization mechanistic distinction types generalizability theoretical speech richer induction original form inductive empirical organic
#81 0.112 applications application reasoning approach cases support hypertext case-based prototype problems consistency developed benchmarking described efficient practical address activity demonstrate effective
#116 0.111 research study influence effects literature theoretical use understanding theory using impact behavior insights examine influences mechanisms specifically context perspective findings
#284 0.102 users user new resistance likely benefits potential perspective status actual behavior recognition propose user's social associated existing base using acceptance
#159 0.074 systems information objectives organization organizational development variety needs need efforts technical organizations developing suggest given effective designing lack help recent
#7 0.072 detection deception assessment credibility automated fraud fake cues detecting results screening study detect design indicators science important theory performance improved
#35 0.054 technology organizational information organizations organization new work perspective innovation processes used technological understanding technologies transformation consequences perspectives use administrative economic