We studied the effect of pause-internal phonetic particles(PINTs) on recall for native and non-native listeners of Englishin a listening experiment with synthesized material that simulated a university lecture. Using a neural speech synthesizertrained on recorded lectures with PINTs annotations, we generated three distinct conditions: a base version, a “silence” version where non-silence PINTs were replaced with silence, anda “nopints” version where all PINTs, including silences, wereremoved. Half of the participants were informed they were listening to computer-generated audio, while the other half weretold the audio was recorded with a poor-quality microphone.We found that neither the condition nor the participants’ nativelanguage significantly affected their overall score, and the presence of PINTs before critical information had a negative effecton recall. This study highlights the importance of consideringPINTs for educational purposes in speech synthesis systems.
Cite as: Elmers, M., Szekely, E. (2023) The Impact of Pause-Internal Phonetic Particles on Recall in Synthesized Lectures. Proc. 12th ISCA Speech Synthesis Workshop (SSW2023), 204-210, doi: 10.21437/SSW.2023-32
@inproceedings{elmers23_ssw,
author={Mikey Elmers and Eva Szekely},
title={{The Impact of Pause-Internal Phonetic Particles on Recall in Synthesized Lectures}},
year=2023,
booktitle={Proc. 12th ISCA Speech Synthesis Workshop (SSW2023)},
pages={204--210},
doi={10.21437/SSW.2023-32}
}