@inproceedings{linke-etal-2022-conversational,
title = "Conversational Speech Recognition Needs Data? Experiments with {A}ustrian {G}erman",
author = "Linke, Julian and
Garner, Philip N. and
Kubin, Gernot and
Schuppler, Barbara",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.500/",
pages = "4684--4691",
abstract = "Conversational speech represents one of the most complex of automatic speech recognition (ASR) tasks owing to the high inter-speaker variation in both pronunciation and conversational dynamics. Such complexity is particularly sensitive to low-resourced (LR) scenarios. Recent developments in self-supervision have allowed such scenarios to take advantage of large amounts of otherwise unrelated data. In this study, we characterise an (LR) Austrian German conversational task. We begin with a non-pre-trained baseline and show that fine-tuning of a model pre-trained using self-supervision leads to improvements consistent with those in the literature; this extends to cases where a lexicon and language model are included. We also show that the advantage of pre-training indeed arises from the larger database rather than the self-supervision. Further, by use of a leave-one-conversation out technique, we demonstrate that robustness problems remain with respect to inter-speaker and inter-conversation variation. This serves to guide where future research might best be focused in light of the current state-of-the-art."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="linke-etal-2022-conversational">
<titleInfo>
<title>Conversational Speech Recognition Needs Data? Experiments with Austrian German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Linke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="given">N</namePart>
<namePart type="family">Garner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gernot</namePart>
<namePart type="family">Kubin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Schuppler</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 Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</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>Conversational speech represents one of the most complex of automatic speech recognition (ASR) tasks owing to the high inter-speaker variation in both pronunciation and conversational dynamics. Such complexity is particularly sensitive to low-resourced (LR) scenarios. Recent developments in self-supervision have allowed such scenarios to take advantage of large amounts of otherwise unrelated data. In this study, we characterise an (LR) Austrian German conversational task. We begin with a non-pre-trained baseline and show that fine-tuning of a model pre-trained using self-supervision leads to improvements consistent with those in the literature; this extends to cases where a lexicon and language model are included. We also show that the advantage of pre-training indeed arises from the larger database rather than the self-supervision. Further, by use of a leave-one-conversation out technique, we demonstrate that robustness problems remain with respect to inter-speaker and inter-conversation variation. This serves to guide where future research might best be focused in light of the current state-of-the-art.</abstract>
<identifier type="citekey">linke-etal-2022-conversational</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.500/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4684</start>
<end>4691</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Conversational Speech Recognition Needs Data? Experiments with Austrian German
%A Linke, Julian
%A Garner, Philip N.
%A Kubin, Gernot
%A Schuppler, Barbara
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F linke-etal-2022-conversational
%X Conversational speech represents one of the most complex of automatic speech recognition (ASR) tasks owing to the high inter-speaker variation in both pronunciation and conversational dynamics. Such complexity is particularly sensitive to low-resourced (LR) scenarios. Recent developments in self-supervision have allowed such scenarios to take advantage of large amounts of otherwise unrelated data. In this study, we characterise an (LR) Austrian German conversational task. We begin with a non-pre-trained baseline and show that fine-tuning of a model pre-trained using self-supervision leads to improvements consistent with those in the literature; this extends to cases where a lexicon and language model are included. We also show that the advantage of pre-training indeed arises from the larger database rather than the self-supervision. Further, by use of a leave-one-conversation out technique, we demonstrate that robustness problems remain with respect to inter-speaker and inter-conversation variation. This serves to guide where future research might best be focused in light of the current state-of-the-art.
%U https://aclanthology.org/2022.lrec-1.500/
%P 4684-4691
Markdown (Informal)
[Conversational Speech Recognition Needs Data? Experiments with Austrian German](https://aclanthology.org/2022.lrec-1.500/) (Linke et al., LREC 2022)
ACL