@inproceedings{tilson-foerster-2024-toward,
title = "Toward Real Time Word Based Prosody Recognition",
author = "Tilson, Alex and
Foerster, Frank",
editor = "Qiu, Amy and
Noble, Bill and
Pagmar, David and
Maraev, Vladislav and
Ilinykh, Nikolai",
booktitle = "Proceedings of the 2024 CLASP Conference on Multimodality and Interaction in Language Learning",
month = oct,
year = "2024",
address = "Gothenburg, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clasp-1.9",
pages = "62--67",
abstract = "Prosodic salience is a heuristic based on word-level prosody in child-directed speech that is thought to serve as a cue for attentional focus. It has been used in the context of robotic language acquisition to extract the contextually most relevant words from a human tutor{'}s speech to ground them in a robot{'}s sensorimotor data. However, the pipeline for performing word-based prosody-recognition operated in a semi-automatic manner and required substantial manual effort. We describe our efforts to automate the existing pipeline by including real time prosody recognition, and a modern speech recognition and forced alignment model. The intention is to enable its use in real time for human-in-the-loop robotic language acquisition and other socially driven forms of online learning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tilson-foerster-2024-toward">
<titleInfo>
<title>Toward Real Time Word Based Prosody Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Tilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Foerster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 CLASP Conference on Multimodality and Interaction in Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amy</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bill</namePart>
<namePart type="family">Noble</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Pagmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Maraev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gothenburg, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prosodic salience is a heuristic based on word-level prosody in child-directed speech that is thought to serve as a cue for attentional focus. It has been used in the context of robotic language acquisition to extract the contextually most relevant words from a human tutor’s speech to ground them in a robot’s sensorimotor data. However, the pipeline for performing word-based prosody-recognition operated in a semi-automatic manner and required substantial manual effort. We describe our efforts to automate the existing pipeline by including real time prosody recognition, and a modern speech recognition and forced alignment model. The intention is to enable its use in real time for human-in-the-loop robotic language acquisition and other socially driven forms of online learning.</abstract>
<identifier type="citekey">tilson-foerster-2024-toward</identifier>
<location>
<url>https://aclanthology.org/2024.clasp-1.9</url>
</location>
<part>
<date>2024-10</date>
<extent unit="page">
<start>62</start>
<end>67</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Toward Real Time Word Based Prosody Recognition
%A Tilson, Alex
%A Foerster, Frank
%Y Qiu, Amy
%Y Noble, Bill
%Y Pagmar, David
%Y Maraev, Vladislav
%Y Ilinykh, Nikolai
%S Proceedings of the 2024 CLASP Conference on Multimodality and Interaction in Language Learning
%D 2024
%8 October
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F tilson-foerster-2024-toward
%X Prosodic salience is a heuristic based on word-level prosody in child-directed speech that is thought to serve as a cue for attentional focus. It has been used in the context of robotic language acquisition to extract the contextually most relevant words from a human tutor’s speech to ground them in a robot’s sensorimotor data. However, the pipeline for performing word-based prosody-recognition operated in a semi-automatic manner and required substantial manual effort. We describe our efforts to automate the existing pipeline by including real time prosody recognition, and a modern speech recognition and forced alignment model. The intention is to enable its use in real time for human-in-the-loop robotic language acquisition and other socially driven forms of online learning.
%U https://aclanthology.org/2024.clasp-1.9
%P 62-67
Markdown (Informal)
[Toward Real Time Word Based Prosody Recognition](https://aclanthology.org/2024.clasp-1.9) (Tilson & Foerster, CLASP 2024)
ACL
- Alex Tilson and Frank Foerster. 2024. Toward Real Time Word Based Prosody Recognition. In Proceedings of the 2024 CLASP Conference on Multimodality and Interaction in Language Learning, pages 62–67, Gothenburg, Sweden. Association for Computational Linguistics.