The causes of pronunciation reduction in 8458 occurrences of ten frequent English function words in a four-hour sample from conversations from the Switchboard corpus were examined. Using ordinary linear and logistic regression models, we examined the length of the words, the form of their vowel (basic, full, or reduced), and final obstruent deletion. For %words with a final obstruent, whether it was present or not. For all of these we found strong, independent effects of speaking rate, predictability, the form of the following word, and %following disfluencies symptomatic of planning problem disfluencies. The results bear on issues in speech recognition, models of speech production, and conversational analysis.
Cite as: Jurafsky, D., Bell, A., Fosler-Lussier, E., Girand, C., Raymond, W. (1998) Reduction of English function words in switchboard. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0669, doi: 10.21437/ICSLP.1998-801
@inproceedings{jurafsky98_icslp,
author={Daniel Jurafsky and Alan Bell and Eric Fosler-Lussier and Cynthia Girand and William Raymond},
title={{Reduction of English function words in switchboard}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0669},
doi={10.21437/ICSLP.1998-801}
}