@inproceedings{tits-2023-must,
title = "{MUST}{\&}{P}-{SRL}: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning",
author = "Tits, No{\'e}",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.8",
doi = "10.18653/v1/2023.emnlp-industry.8",
pages = "74--82",
abstract = "In this paper, we present a methodology for linguistic feature extraction, focusing particularly on automatically syllabifying words in multiple languages, with a design to be compatible with a forced-alignment tool, the Montreal Forced Aligner (MFA). In both the textual and phonetic domains, our method focuses on the extraction of phonetic transcriptions from text, stress marks, and a unified automatic syllabification (in text and phonetic domains). The system was built with open-source components and resources. Through an ablation study, we demonstrate the efficacy of our approach in automatically syllabifying words from several languages (English, French and Spanish). Additionally, we apply the technique to the transcriptions of the CMU ARCTIC dataset, generating valuable annotations available online (https://github.com/noetits/MUST{\_}P-SRL) that are ideal for speech representation learning, speech unit discovery, and disentanglement of speech factors in several speech-related fields.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tits-2023-must">
<titleInfo>
<title>MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Noé</namePart>
<namePart type="family">Tits</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 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</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>In this paper, we present a methodology for linguistic feature extraction, focusing particularly on automatically syllabifying words in multiple languages, with a design to be compatible with a forced-alignment tool, the Montreal Forced Aligner (MFA). In both the textual and phonetic domains, our method focuses on the extraction of phonetic transcriptions from text, stress marks, and a unified automatic syllabification (in text and phonetic domains). The system was built with open-source components and resources. Through an ablation study, we demonstrate the efficacy of our approach in automatically syllabifying words from several languages (English, French and Spanish). Additionally, we apply the technique to the transcriptions of the CMU ARCTIC dataset, generating valuable annotations available online (https://github.com/noetits/MUST_P-SRL) that are ideal for speech representation learning, speech unit discovery, and disentanglement of speech factors in several speech-related fields.</abstract>
<identifier type="citekey">tits-2023-must</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.8</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.8</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>74</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning
%A Tits, Noé
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F tits-2023-must
%X In this paper, we present a methodology for linguistic feature extraction, focusing particularly on automatically syllabifying words in multiple languages, with a design to be compatible with a forced-alignment tool, the Montreal Forced Aligner (MFA). In both the textual and phonetic domains, our method focuses on the extraction of phonetic transcriptions from text, stress marks, and a unified automatic syllabification (in text and phonetic domains). The system was built with open-source components and resources. Through an ablation study, we demonstrate the efficacy of our approach in automatically syllabifying words from several languages (English, French and Spanish). Additionally, we apply the technique to the transcriptions of the CMU ARCTIC dataset, generating valuable annotations available online (https://github.com/noetits/MUST_P-SRL) that are ideal for speech representation learning, speech unit discovery, and disentanglement of speech factors in several speech-related fields.
%R 10.18653/v1/2023.emnlp-industry.8
%U https://aclanthology.org/2023.emnlp-industry.8
%U https://doi.org/10.18653/v1/2023.emnlp-industry.8
%P 74-82
Markdown (Informal)
[MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning](https://aclanthology.org/2023.emnlp-industry.8) (Tits, EMNLP 2023)
ACL