Third-party error detection support mechanisms for dictation speech recognition

Abstract

a b s t r a c tAlthough speech recognition has improved significantly in recent years, its adoption continues to be limited, in part, by the effort and frustration associated with correcting speech recognition errors. Error detection is a particularly challenging issue in third-party error correction where different individuals are responsible for the original dictation and correcting the resulting text. This research aims to address the difficulty experienced in third-party error detection by developing and evaluating a variety of support mechanisms. Drawing on a growing body of literature on human computer interaction and speech recognition, four support mechanisms were designed and evaluated, namely indexed audio, speech summarization, error prediction, and the presentation of alternative hypotheses. A user study assessed the impact of these support mechanisms on both performance and perceptions during error detection tasks. Performance measures included effectiveness and efficiency, and perception measures included confidence, perceived usefulness, and cognitive workload. The results provide strong support for the use of indexed audio in the context of third-party error detection. The results also confirm that consecutive error rate, or the percentage of recognition errors immediately adjacent to another error, has a negative impact on the effectiveness of third-party error detection. Other support mechanisms failed to improve either effectiveness or perceptions, but they did negate the negative impact as consecutive error rate increased. These findings have significant implications for speech recognition error detection research and the design of error detection support solutions.

Seven Important Theories in Information Management and Information System Empirical Research: A Systematic Review and Future Directions

“…The quality of IS is described as a multi-dimensional entity reflecting different stakeholders, which will affect the IS use. Similarly, information quality, service quality, and system quality will affect the flow experience of users (Aladwani & Palvia, 2002;Zhou, Shi, & Sears, 2010). In the online shopping context, it is suggested that the navigation, interface presentation, and even color of the website will also affect the flow experience (Ettis, 2017;Landers et al, 2015;Liu & Suh, 2017).…”

Writing with speech: A qualitative user evaluation study

“…On the other hand, error correction is known to be a writing sub-process that increases the cognitive load during writing. Parallel to improving the performance of the recognizer, many error correction strategies emerged, see [5] and [6]. Our method to improve the error correction described in Section III.…”

Confidence measure by substring comparison for automatic speech recognition

“…Recently applying Bayes based confidence measure for reinforced learning was also tested [8]. Confidence measures were also applied in a new third-party error detection system [9]. Confidence measures are even more important in speaker recognition.…”