Topics in the Study of the Pragmatic Functions of Phonetic Reduction in Dialog
Ward, Nigel G., Ortega, Carlos A.
–arXiv.org Artificial Intelligence
Feeling that our inventory of prosodic features was incomplete, we set out to add phonetic reduction to the features handled by the Midlevel Prosodic Features Toolkit (Ward 2023). We failed in this goal, but in the process learned a lot about reduction. The headline finding was the result that phonetic reduction correlates with positive assessments in American English, and that result, plus closely related topics, reported in a journal article submission (Ward et al. 2024). However, not everything that we learned fit there, however, so this document reports the rest. Some of the discussions are stand-alone -- notably those of spectral tilt, annotation for reduction, and prosodic correlates of reduction, as found in Sections 4-5 -- but most readers will want to start with the journal article and use this document only for details and leftovers.
arXiv.org Artificial Intelligence
May-2-2024
- Country:
- North America > United States
- Europe
- Czechia > Prague (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Netherlands > Gelderland
- Nijmegen (0.04)
- Genre:
- Research Report
- Experimental Study (0.68)
- New Finding (0.46)
- Research Report
- Industry:
- Technology:
- Information Technology > Artificial Intelligence
- Natural Language (1.00)
- Speech > Speech Recognition (0.46)
- Machine Learning
- Statistical Learning (0.46)
- Neural Networks (0.46)
- Information Technology > Artificial Intelligence