@inproceedings{roll-etal-2023-psst,
title = "{PSST}! Prosodic Speech Segmentation with Transformers",
author = "Roll, Nathan and
Graham, Calbert and
Todd, Simon",
editor = "Jiang, Jing and
Reitter, David and
Deng, Shumin",
booktitle = "Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.conll-1.31",
doi = "10.18653/v1/2023.conll-1.31",
pages = "476--487",
abstract = "We develop and probe a model for detecting the boundaries of prosodic chunks in untranscribed conversational English speech. The model is obtained by fine-tuning a Transformer-based speech-to-text (STT) model to integrate the identification of Intonation Unit (IU) boundaries with the STT task. The model shows robust performance, both on held-out data and on out-of-distribution data representing different dialects and transcription protocols. By evaluating the model on degraded speech data, and comparing it with alternatives, we establish that it relies heavily on lexico-syntactic information inferred from audio, and not solely on acoustic information typically understood to cue prosodic structure. We release our model as both a transcription tool and a baseline for further improvements in prosodic segmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roll-etal-2023-psst">
<titleInfo>
<title>PSST! Prosodic Speech Segmentation with Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Roll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Calbert</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Todd</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Reitter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shumin</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We develop and probe a model for detecting the boundaries of prosodic chunks in untranscribed conversational English speech. The model is obtained by fine-tuning a Transformer-based speech-to-text (STT) model to integrate the identification of Intonation Unit (IU) boundaries with the STT task. The model shows robust performance, both on held-out data and on out-of-distribution data representing different dialects and transcription protocols. By evaluating the model on degraded speech data, and comparing it with alternatives, we establish that it relies heavily on lexico-syntactic information inferred from audio, and not solely on acoustic information typically understood to cue prosodic structure. We release our model as both a transcription tool and a baseline for further improvements in prosodic segmentation.</abstract>
<identifier type="citekey">roll-etal-2023-psst</identifier>
<identifier type="doi">10.18653/v1/2023.conll-1.31</identifier>
<location>
<url>https://aclanthology.org/2023.conll-1.31</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>476</start>
<end>487</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PSST! Prosodic Speech Segmentation with Transformers
%A Roll, Nathan
%A Graham, Calbert
%A Todd, Simon
%Y Jiang, Jing
%Y Reitter, David
%Y Deng, Shumin
%S Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F roll-etal-2023-psst
%X We develop and probe a model for detecting the boundaries of prosodic chunks in untranscribed conversational English speech. The model is obtained by fine-tuning a Transformer-based speech-to-text (STT) model to integrate the identification of Intonation Unit (IU) boundaries with the STT task. The model shows robust performance, both on held-out data and on out-of-distribution data representing different dialects and transcription protocols. By evaluating the model on degraded speech data, and comparing it with alternatives, we establish that it relies heavily on lexico-syntactic information inferred from audio, and not solely on acoustic information typically understood to cue prosodic structure. We release our model as both a transcription tool and a baseline for further improvements in prosodic segmentation.
%R 10.18653/v1/2023.conll-1.31
%U https://aclanthology.org/2023.conll-1.31
%U https://doi.org/10.18653/v1/2023.conll-1.31
%P 476-487
Markdown (Informal)
[PSST! Prosodic Speech Segmentation with Transformers](https://aclanthology.org/2023.conll-1.31) (Roll et al., CoNLL 2023)
ACL
- Nathan Roll, Calbert Graham, and Simon Todd. 2023. PSST! Prosodic Speech Segmentation with Transformers. In Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL), pages 476–487, Singapore. Association for Computational Linguistics.