We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Comparing machine and human performance for caller’s directory assistance requests.
- Authors
Chang, Harry M.
- Abstract
To understand how to systematically construct the machine models for automating Directory Assistance (DA) that are capable of reaching the performance level of human DA operators, we conducted a number of studies over the years. This paper describes the methods used for such studies and the results of laboratory experiments. These include a series of benchmark tests configured specifically for DA related tasks to evaluate the performance of state-of-the-art and commercially-available Hidden Markov Model (HMM) based Automatic Speech Recognition (ASR) technologies. The results show that the best system achieves a 57.9% task completion rate on the city-state-recognition benchmark test. For the most frequently-requested-listing benchmark test, the best system achieves a 40% task completion rate.
- Subjects
TELEPHONE directory assistance; TELEPHONE operators; HIDDEN Markov models; AUTOMATIC speech recognition; TECHNOLOGICAL innovations; SPEECH perception
- Publication
International Journal of Speech Technology, 2008, Vol 10, Issue 2/3, p75
- ISSN
1381-2416
- Publication type
Article
- DOI
10.1007/s10772-009-9020-1