@inproceedings{kimura-etal-2022-ssr7000,
title = "{SSR}7000: A Synchronized Corpus of Ultrasound Tongue Imaging for End-to-End Silent Speech Recognition",
author = "Kimura, Naoki and
Su, Zixiong and
Saeki, Takaaki and
Rekimoto, Jun",
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-1.741/",
pages = "6866--6873",
abstract = "This article presents SSR7000, a corpus of synchronized ultrasound tongue and lip images designed for end-to-end silent speech recognition (SSR). Although neural end-to-end models are successfully updating the state-of-the-art technology in the field of automatic speech recognition, SSR research based on ultrasound tongue imaging has still not evolved past cascaded DNN-HMM models due to the absence of a large dataset. In this study, we constructed a large dataset, namely SSR7000, to exploit the performance of the end-to-end models. The SSR7000 dataset contains ultrasound tongue and lip images of 7484 utterances by a single speaker. It contains more utterances per person than any other SSR corpus based on ultrasound imaging. We also describe preprocessing techniques to tackle data variances that are inevitable when collecting a large dataset and present benchmark results using an end-to-end model. The SSR7000 corpus is publicly available under the CC BY-NC 4.0 license."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kimura-etal-2022-ssr7000">
<titleInfo>
<title>SSR7000: A Synchronized Corpus of Ultrasound Tongue Imaging for End-to-End Silent Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Kimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zixiong</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takaaki</namePart>
<namePart type="family">Saeki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Rekimoto</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>This article presents SSR7000, a corpus of synchronized ultrasound tongue and lip images designed for end-to-end silent speech recognition (SSR). Although neural end-to-end models are successfully updating the state-of-the-art technology in the field of automatic speech recognition, SSR research based on ultrasound tongue imaging has still not evolved past cascaded DNN-HMM models due to the absence of a large dataset. In this study, we constructed a large dataset, namely SSR7000, to exploit the performance of the end-to-end models. The SSR7000 dataset contains ultrasound tongue and lip images of 7484 utterances by a single speaker. It contains more utterances per person than any other SSR corpus based on ultrasound imaging. We also describe preprocessing techniques to tackle data variances that are inevitable when collecting a large dataset and present benchmark results using an end-to-end model. The SSR7000 corpus is publicly available under the CC BY-NC 4.0 license.</abstract>
<identifier type="citekey">kimura-etal-2022-ssr7000</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.741/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6866</start>
<end>6873</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SSR7000: A Synchronized Corpus of Ultrasound Tongue Imaging for End-to-End Silent Speech Recognition
%A Kimura, Naoki
%A Su, Zixiong
%A Saeki, Takaaki
%A Rekimoto, Jun
%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 kimura-etal-2022-ssr7000
%X This article presents SSR7000, a corpus of synchronized ultrasound tongue and lip images designed for end-to-end silent speech recognition (SSR). Although neural end-to-end models are successfully updating the state-of-the-art technology in the field of automatic speech recognition, SSR research based on ultrasound tongue imaging has still not evolved past cascaded DNN-HMM models due to the absence of a large dataset. In this study, we constructed a large dataset, namely SSR7000, to exploit the performance of the end-to-end models. The SSR7000 dataset contains ultrasound tongue and lip images of 7484 utterances by a single speaker. It contains more utterances per person than any other SSR corpus based on ultrasound imaging. We also describe preprocessing techniques to tackle data variances that are inevitable when collecting a large dataset and present benchmark results using an end-to-end model. The SSR7000 corpus is publicly available under the CC BY-NC 4.0 license.
%U https://aclanthology.org/2022.lrec-1.741/
%P 6866-6873
Markdown (Informal)
[SSR7000: A Synchronized Corpus of Ultrasound Tongue Imaging for End-to-End Silent Speech Recognition](https://aclanthology.org/2022.lrec-1.741/) (Kimura et al., LREC 2022)
ACL