{"title":"The Impact of Pause-Internal Phonetic Particles on Recall in Synthesized Lectures","authors":"Mikey Elmers, Éva Székely","doi":"10.21437/ssw.2023-32","DOIUrl":null,"url":null,"abstract":"We studied the effect of pause-internal phonetic particles (PINTs) on recall for native and non-native listeners of English in a listening experiment with synthesized material that simulated a university lecture. Using a neural speech synthesizer trained 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, and a “nopints” version where all PINTs, including silences, were removed. Half of the participants were informed they were listening to computer-generated audio, while the other half were told the audio was recorded with a poor-quality microphone. We found that neither the condition nor the participants’ native language significantly affected their overall score, and the presence of PINTs before critical information had a negative effect on recall. This study highlights the importance of considering PINTs for educational purposes in speech synthesis systems.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"12th ISCA Speech Synthesis Workshop (SSW2023)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21437/ssw.2023-32","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
We studied the effect of pause-internal phonetic particles (PINTs) on recall for native and non-native listeners of English in a listening experiment with synthesized material that simulated a university lecture. Using a neural speech synthesizer trained 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, and a “nopints” version where all PINTs, including silences, were removed. Half of the participants were informed they were listening to computer-generated audio, while the other half were told the audio was recorded with a poor-quality microphone. We found that neither the condition nor the participants’ native language significantly affected their overall score, and the presence of PINTs before critical information had a negative effect on recall. This study highlights the importance of considering PINTs for educational purposes in speech synthesis systems.