“I'll get that off the audio”: a case study of salvaging multimedia meeting records
Proceedings of the ACM SIGCHI Conference on Human factors in computing systems
| Hi-index | 0.01 |
This paper briefly examines the design space of speech recognition as an input device. I discuss the particular advantages of speech recognition over other button-pushing modes of input. The goal of this paper is to examine speech devices that operate as a reflective tool for Human-Computer Interaction. I detail the construction and implementation of a simple speech recognition device, the Speech Patternizer, which specifies the frequency of indicated words in recorded speech. Through the prototyping of this device and a longitudinal study of it, I inspect the more nuanced models of Human-Computer Interaction that make speech patterns more transparent and interpretable. The value of the ability to examine and assess speech interaction between computers and humans is also discussed.