@inproceedings{matos-etal-2016-dirha,
title = "The {DIRHA} {P}ortuguese Corpus: A Comparison of Home Automation Command Detection and Recognition in Simulated and Real Data.",
author = "Matos, Miguel and
Abad, Alberto and
Serralheiro, Ant{\'o}nio",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1633/",
pages = "4012--4018",
abstract = "In this paper, we describe a new corpus -named DIRHA-L2F RealCorpus- composed of typical home automation speech interactions in European Portuguese that has been recorded by the INESC-ID{'}s Spoken Language Systems Laboratory (L2F) to support the activities of the Distant-speech Interaction for Robust Home Applications (DIRHA) EU-funded project. The corpus is a multi-microphone and multi-room database of real continuous audio sequences containing read phonetically rich sentences, read and spontaneous keyword activation sentences, and read and spontaneous home automation commands. The background noise conditions are controlled and randomly recreated with noises typically found in home environments. Experimental validation on this corpus is reported in comparison with the results obtained on a simulated corpus using a fully automated speech processing pipeline for two fundamental automatic speech recognition tasks of typical `always-listening' home-automation scenarios: system activation and voice command recognition. Attending to results on both corpora, the presence of overlapping voice-like noise is shown as the main problem: simulated sequences contain concurrent speakers that result in general in a more challenging corpus, while real sequences performance drops drastically when TV or radio is on."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="matos-etal-2016-dirha">
<titleInfo>
<title>The DIRHA Portuguese Corpus: A Comparison of Home Automation Command Detection and Recognition in Simulated and Real Data.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Matos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">António</namePart>
<namePart type="family">Serralheiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe a new corpus -named DIRHA-L2F RealCorpus- composed of typical home automation speech interactions in European Portuguese that has been recorded by the INESC-ID’s Spoken Language Systems Laboratory (L2F) to support the activities of the Distant-speech Interaction for Robust Home Applications (DIRHA) EU-funded project. The corpus is a multi-microphone and multi-room database of real continuous audio sequences containing read phonetically rich sentences, read and spontaneous keyword activation sentences, and read and spontaneous home automation commands. The background noise conditions are controlled and randomly recreated with noises typically found in home environments. Experimental validation on this corpus is reported in comparison with the results obtained on a simulated corpus using a fully automated speech processing pipeline for two fundamental automatic speech recognition tasks of typical ‘always-listening’ home-automation scenarios: system activation and voice command recognition. Attending to results on both corpora, the presence of overlapping voice-like noise is shown as the main problem: simulated sequences contain concurrent speakers that result in general in a more challenging corpus, while real sequences performance drops drastically when TV or radio is on.</abstract>
<identifier type="citekey">matos-etal-2016-dirha</identifier>
<location>
<url>https://aclanthology.org/L16-1633/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4012</start>
<end>4018</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The DIRHA Portuguese Corpus: A Comparison of Home Automation Command Detection and Recognition in Simulated and Real Data.
%A Matos, Miguel
%A Abad, Alberto
%A Serralheiro, António
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F matos-etal-2016-dirha
%X In this paper, we describe a new corpus -named DIRHA-L2F RealCorpus- composed of typical home automation speech interactions in European Portuguese that has been recorded by the INESC-ID’s Spoken Language Systems Laboratory (L2F) to support the activities of the Distant-speech Interaction for Robust Home Applications (DIRHA) EU-funded project. The corpus is a multi-microphone and multi-room database of real continuous audio sequences containing read phonetically rich sentences, read and spontaneous keyword activation sentences, and read and spontaneous home automation commands. The background noise conditions are controlled and randomly recreated with noises typically found in home environments. Experimental validation on this corpus is reported in comparison with the results obtained on a simulated corpus using a fully automated speech processing pipeline for two fundamental automatic speech recognition tasks of typical ‘always-listening’ home-automation scenarios: system activation and voice command recognition. Attending to results on both corpora, the presence of overlapping voice-like noise is shown as the main problem: simulated sequences contain concurrent speakers that result in general in a more challenging corpus, while real sequences performance drops drastically when TV or radio is on.
%U https://aclanthology.org/L16-1633/
%P 4012-4018
Markdown (Informal)
[The DIRHA Portuguese Corpus: A Comparison of Home Automation Command Detection and Recognition in Simulated and Real Data.](https://aclanthology.org/L16-1633/) (Matos et al., LREC 2016)
ACL