@inproceedings{littell-etal-2022-readalong,
title = "{R}ead{A}long Studio: Practical Zero-Shot Text-Speech Alignment for Indigenous Language Audiobooks",
author = "Littell, Patrick and
Joanis, Eric and
Pine, Aidan and
Tessier, Marc and
Huggins Daines, David and
Torkornoo, Delasie",
editor = "Melero, Maite and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.sigul-1.4",
pages = "23--32",
abstract = "While the alignment of audio recordings and text (often termed {``}forced alignment{''}) is often treated as a solved problem, in practice the process of adapting an alignment system to a new, under-resourced language comes with significant challenges, requiring experience and expertise that many outside of the speech community lack. This puts otherwise {``}solvable{''} problems, like the alignment of Indigenous language audiobooks, out of reach for many real-world Indigenous language organizations. In this paper, we detail ReadAlong Studio, a suite of tools for creating and visualizing aligned audiobooks, including educational features like time-aligned highlighting, playing single words in isolation, and variable-speed playback. It is intended to be accessible to creators without an extensive background in speech or NLP, by automating or making optional many of the specialist steps in an alignment pipeline. It is well documented at a beginner-technologist level, has already been adapted to 30 languages, and can work out-of-the-box on many more languages without adaptation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="littell-etal-2022-readalong">
<titleInfo>
<title>ReadAlong Studio: Practical Zero-Shot Text-Speech Alignment for Indigenous Language Audiobooks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Littell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Joanis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aidan</namePart>
<namePart type="family">Pine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Tessier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Huggins Daines</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Delasie</namePart>
<namePart type="family">Torkornoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While the alignment of audio recordings and text (often termed “forced alignment”) is often treated as a solved problem, in practice the process of adapting an alignment system to a new, under-resourced language comes with significant challenges, requiring experience and expertise that many outside of the speech community lack. This puts otherwise “solvable” problems, like the alignment of Indigenous language audiobooks, out of reach for many real-world Indigenous language organizations. In this paper, we detail ReadAlong Studio, a suite of tools for creating and visualizing aligned audiobooks, including educational features like time-aligned highlighting, playing single words in isolation, and variable-speed playback. It is intended to be accessible to creators without an extensive background in speech or NLP, by automating or making optional many of the specialist steps in an alignment pipeline. It is well documented at a beginner-technologist level, has already been adapted to 30 languages, and can work out-of-the-box on many more languages without adaptation.</abstract>
<identifier type="citekey">littell-etal-2022-readalong</identifier>
<location>
<url>https://aclanthology.org/2022.sigul-1.4</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>23</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReadAlong Studio: Practical Zero-Shot Text-Speech Alignment for Indigenous Language Audiobooks
%A Littell, Patrick
%A Joanis, Eric
%A Pine, Aidan
%A Tessier, Marc
%A Huggins Daines, David
%A Torkornoo, Delasie
%Y Melero, Maite
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F littell-etal-2022-readalong
%X While the alignment of audio recordings and text (often termed “forced alignment”) is often treated as a solved problem, in practice the process of adapting an alignment system to a new, under-resourced language comes with significant challenges, requiring experience and expertise that many outside of the speech community lack. This puts otherwise “solvable” problems, like the alignment of Indigenous language audiobooks, out of reach for many real-world Indigenous language organizations. In this paper, we detail ReadAlong Studio, a suite of tools for creating and visualizing aligned audiobooks, including educational features like time-aligned highlighting, playing single words in isolation, and variable-speed playback. It is intended to be accessible to creators without an extensive background in speech or NLP, by automating or making optional many of the specialist steps in an alignment pipeline. It is well documented at a beginner-technologist level, has already been adapted to 30 languages, and can work out-of-the-box on many more languages without adaptation.
%U https://aclanthology.org/2022.sigul-1.4
%P 23-32
Markdown (Informal)
[ReadAlong Studio: Practical Zero-Shot Text-Speech Alignment for Indigenous Language Audiobooks](https://aclanthology.org/2022.sigul-1.4) (Littell et al., SIGUL 2022)
ACL