<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>0872-671X</journal-id>
<journal-title><![CDATA[Medicina Interna]]></journal-title>
<abbrev-journal-title><![CDATA[Medicina Interna]]></abbrev-journal-title>
<issn>0872-671X</issn>
<publisher>
<publisher-name><![CDATA[Sociedade Portuguesa de Medicina Interna]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0872-671X2024000300004</article-id>
<article-id pub-id-type="doi">10.24950/rspmi.2587</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Speech as an Emotional Load Biomarker in Clinical Applications]]></article-title>
<article-title xml:lang="pt"><![CDATA[A Fala como Biomarcador de Carga Emocional em Aplicações Clínicas]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Coelho]]></surname>
<given-names><![CDATA[L. F.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
<xref ref-type="aff" rid="Aaf"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidade do Porto Faculdade de Engenharia INESC TEC - Instituto de Sistemas e Computadores]]></institution>
<addr-line><![CDATA[Porto ]]></addr-line>
<country>Portugal</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Instituto Politécnico do Porto ISEP / P.Porto - Instituto Superior de Engenharia do Porto ]]></institution>
<addr-line><![CDATA[Porto ]]></addr-line>
<country>Portugal</country>
</aff>
<pub-date pub-type="pub">
<day>30</day>
<month>05</month>
<year>2024</year>
</pub-date>
<pub-date pub-type="epub">
<day>30</day>
<month>05</month>
<year>2024</year>
</pub-date>
<volume>31</volume>
<fpage>4</fpage>
<lpage>10</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://scielo.pt/scielo.php?script=sci_arttext&amp;pid=S0872-671X2024000300004&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://scielo.pt/scielo.php?script=sci_abstract&amp;pid=S0872-671X2024000300004&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://scielo.pt/scielo.php?script=sci_pdf&amp;pid=S0872-671X2024000300004&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract  Introduction:  Healthcare professionals often contend with significant emotional burdens in their work, including the impact of negative emotions, such as stress and anxiety, which can have profound consequences on immediate and long-term healthcare delivery. In this paper a stress estimation algorithm is proposed based on the classification of negative valence emotions in speech recordings.  Methods:  An end-to-end machine learning pipeline is proposed. Two distinct decision models are considered, VGG-16 and SqueezeNet, while sharing a common constant Q power spectrogram input for acoustic representation. The system is trained and evaluated using the RAVDESS and TESS emotional speech datasets.  Results:  The system was evaluated for individual emotion classification (multiclass problem) and also for negative and neutral or positive emotion classification (binary problem). The results achieved are comparable to previously reported systems, with the SqueezeNet model offering a significantly smaller footprint, enabling versatile applications. Further exploration of the model's parameter space holds promise for enhanced performance.  Conclusion:  The proposed system can constitute a feasible approach for the estimation of a low-cost non-invasive biomarker for negative emotions. This allows to raise alerts and develop mitigating actions to the burden of negative emotions, being an additional management tool for healthcare services that allows to maintain quality and maximize availability.]]></p></abstract>
<abstract abstract-type="short" xml:lang="pt"><p><![CDATA[Resumo  Introdução:  Os profissionais de saúde enfrentam frequentemente cargas emocionais significativas no seu trabalho, incluindo o impacto de emoções negativas, como o stress e a ansiedade, que podem ter graves consequências no desempenho das suas funções de prestação de cuidados de saúde imediatos e também na sua própria saúde a longo prazo. Neste artigo, é proposto um algoritmo de estimativa do stress baseado na classificação de emoções de valência negativa em gravações de fala.  Métodos:  É proposto um pipeline de aprendizagem automática de ponta a ponta. São considerados cenários de modelos de decisão distintos, o VGG-16 e o SqueezeNet, que partilham uma entrada comum de espetrograma de potência Q constante para representação acústica. Os sistemas são treinados e avaliados utilizando os conjuntos de dados de fala emocional RAVDESS e TESS.  Resultados:  O sistema foi avaliado para a classificação de um conjunto de emoções (problema multiclasse) e também para a classificação de emoções negativas e neutras, distinguindo-as das positivas (problema binário). Os resultados obtidos são comparáveis aos dos sistemas anteriormente registados, com o modelo SqueezeNet a oferecer uma pegada significativamente mais pequena, permitindo aplicações versáteis. Uma exploração mais aprofundada do espaço de parâmetros do modelo não foi exaustiva e por isso é promissora para a melhoria do desempenho.  Conclusão:  O sistema proposto pode constituir uma abordagem viável para a estimativa de um biomarcador não-invasivo de baixo custo para emoções negativas. Isto permite ativar alertas e desenvolver ações de mitigação para a presença de emoções negativas, sendo uma ferramenta de gestão adicional para os serviços de saúde que permite manter a qualidade e maximizar a sua disponibilidade.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[Biomarkers]]></kwd>
<kwd lng="en"><![CDATA[Emotions]]></kwd>
<kwd lng="en"><![CDATA[Machine Learning]]></kwd>
<kwd lng="en"><![CDATA[Speech.]]></kwd>
<kwd lng="pt"><![CDATA[Aprendizagem Automática]]></kwd>
<kwd lng="pt"><![CDATA[Biomarcadores]]></kwd>
<kwd lng="pt"><![CDATA[Emoções]]></kwd>
<kwd lng="pt"><![CDATA[Fala.]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<label>1</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cohen]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Kamarck]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Mermelstein]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<source><![CDATA[Perceived Stress Scale]]></source>
<year>1983</year>
<publisher-loc><![CDATA[Chicago ]]></publisher-loc>
<publisher-name><![CDATA[APA Psyc Tests]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B2">
<label>2</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Loera]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Converso]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Viotti]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Evaluating the Psychometric Properties of the Maslach Burnout Inventory-Human Services Survey (MBI-HSS) among Italian Nurses How Many Factors Must a Researcher Consider?]]></article-title>
<source><![CDATA[PLoS One]]></source>
<year>2014</year>
<volume>9</volume>
</nlm-citation>
</ref>
<ref id="B3">
<label>3</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Coelho]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Reis]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Moreira]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Cardoso]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Sequeira]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Coelho]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Benchmarking Computer-Vision Based Facial Emotion Classification Algorithms While Wearing Surgical Masks]]></article-title>
<source><![CDATA[Engineering Proceedings]]></source>
<year>2023</year>
</nlm-citation>
</ref>
<ref id="B4">
<label>4</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Vieira]]></surname>
<given-names><![CDATA[FMP]]></given-names>
</name>
<name>
<surname><![CDATA[Ferreira]]></surname>
<given-names><![CDATA[MA]]></given-names>
</name>
<name>
<surname><![CDATA[Dias]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Cunha]]></surname>
<given-names><![CDATA[JPS]]></given-names>
</name>
</person-group>
<source><![CDATA[VitalSticker: A novel multimodal physiological wearable patch device for health monitoring]]></source>
<year>2023</year>
<conf-name><![CDATA[ IEEE 7th Portuguese Meeting on Bioengineering (ENBENG)]]></conf-name>
<conf-date>2023</conf-date>
<conf-loc> </conf-loc>
<page-range>100-3</page-range></nlm-citation>
</ref>
<ref id="B5">
<label>5</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Deepa]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Khilar]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Speech technology in healthcare Measurement]]></article-title>
<source><![CDATA[Sensors]]></source>
<year>2022</year>
<volume>24</volume>
<page-range>100565</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>6</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Vigo]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
<name>
<surname><![CDATA[Coelho]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Reis]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Speech- and Language-Based Classification of Alzheimer's Disease A Systematic Review]]></article-title>
<source><![CDATA[Bioengineering]]></source>
<year>2022</year>
<volume>9</volume>
<page-range>27</page-range></nlm-citation>
</ref>
<ref id="B7">
<label>7</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Vieira]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Costa]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
<name>
<surname><![CDATA[Sousa]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Reis]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Coelho]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Voice-Based classification of amyotrophic lateral sclerosis where are we and where are we going? A systematic review]]></article-title>
<source><![CDATA[Neurodegener Dis]]></source>
<year>2019</year>
<volume>19</volume>
<page-range>163-70</page-range></nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Braga]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Madureira]]></surname>
<given-names><![CDATA[AM]]></given-names>
</name>
<name>
<surname><![CDATA[Coelho]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Abraham]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Neurodegenerative Diseases Detection Through Voice Analysis]]></article-title>
<person-group person-group-type="editor">
<name>
<surname><![CDATA[Abraham]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Muhuri]]></surname>
<given-names><![CDATA[PKr]]></given-names>
</name>
<name>
<surname><![CDATA[Muda]]></surname>
<given-names><![CDATA[AK]]></given-names>
</name>
<name>
<surname><![CDATA[Gandhi]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
</person-group>
<source><![CDATA[Hybrid Intelligent Systems]]></source>
<year>2018</year>
<page-range>213-23</page-range><publisher-loc><![CDATA[Cham ]]></publisher-loc>
<publisher-name><![CDATA[Springer International Publishing]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B9">
<label>9</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lindquist]]></surname>
<given-names><![CDATA[KA]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Emotions Emerge from More Basic Psychological Ingredients A Modern Psychological Constructionist Model]]></article-title>
<source><![CDATA[Emotion Rev]]></source>
<year>2013</year>
<volume>5</volume>
<page-range>356-68</page-range></nlm-citation>
</ref>
<ref id="B10">
<label>10</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Livingstone]]></surname>
<given-names><![CDATA[SR]]></given-names>
</name>
<name>
<surname><![CDATA[Russo]]></surname>
<given-names><![CDATA[FA]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) A dynamic, multimodal set of facial and vocal expressions in North American English]]></article-title>
<source><![CDATA[PLoS One]]></source>
<year>2018</year>
<volume>13</volume>
</nlm-citation>
</ref>
<ref id="B11">
<label>11</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Pichora-Fuller]]></surname>
<given-names><![CDATA[MK]]></given-names>
</name>
<name>
<surname><![CDATA[Dupuis]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Toronto emotional speech set (TESS)]]></article-title>
<source><![CDATA[Borealis]]></source>
<year>2020</year>
</nlm-citation>
</ref>
<ref id="B12">
<label>12</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[McFee]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Raffel]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Liang]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Ellis]]></surname>
<given-names><![CDATA[DPW]]></given-names>
</name>
<name>
<surname><![CDATA[McVicar]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Battenberg]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[librosa: Audio and Music Signal Analysis in Python]]></article-title>
<source><![CDATA[Proceedings of the 14th Python in Science Conference]]></source>
<year>2015</year>
<page-range>18-24</page-range></nlm-citation>
</ref>
<ref id="B13">
<label>13</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Paszke]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Gross]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Massa]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Lerer]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Bradbury]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Chanan]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[PyTorch: An Imperative Style, High-Performance Deep Learning Library]]></article-title>
<source><![CDATA[arXiv]]></source>
<year>2019</year>
</nlm-citation>
</ref>
<ref id="B14">
<label>14</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Boersma]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Weenink]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
</person-group>
<source><![CDATA[Praat: doing phonetics by computer]]></source>
<year>2018</year>
</nlm-citation>
</ref>
<ref id="B15">
<label>15</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Eyben]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Scherer]]></surname>
<given-names><![CDATA[KR]]></given-names>
</name>
<name>
<surname><![CDATA[Schuller]]></surname>
<given-names><![CDATA[BW]]></given-names>
</name>
<name>
<surname><![CDATA[Sundberg]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[André]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Busso]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[The Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing]]></article-title>
<source><![CDATA[IEEE Trans Affective Comput]]></source>
<year>2016</year>
<volume>7</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>190-202</page-range></nlm-citation>
</ref>
<ref id="B16">
<label>16</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Eyben]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Wöllmer]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Schuller]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[openSMILE - The Munich Versatile and Fast Open-Source Audio Feature Extractor]]></article-title>
<source><![CDATA[MM&#8217;10 - Proceedings of the ACM Multimedia 2010 International Conference]]></source>
<year>2010</year>
<page-range>1459</page-range></nlm-citation>
</ref>
<ref id="B17">
<label>17</label><nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Cabral]]></surname>
<given-names><![CDATA[JP]]></given-names>
</name>
<name>
<surname><![CDATA[Oliveira]]></surname>
<given-names><![CDATA[LC]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Emovoice: a system to generate emotions in speech]]></article-title>
<source><![CDATA[Interspeech 2006]]></source>
<year>2006</year>
<publisher-name><![CDATA[ISCA]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B18">
<label>18</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Simonyan]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Zisserman]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Very Deep Convolutional Networks for Large-Scale Image Recognition]]></article-title>
<source><![CDATA[arXiv]]></source>
<year>2015</year>
</nlm-citation>
</ref>
<ref id="B19">
<label>19</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[de Lope]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Graña]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[An ongoing review of speech emotion recognition]]></article-title>
<source><![CDATA[Neurocomputing]]></source>
<year>2023</year>
<volume>528</volume>
<page-range>1-11</page-range></nlm-citation>
</ref>
<ref id="B20">
<label>20</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Iandola]]></surname>
<given-names><![CDATA[FN]]></given-names>
</name>
<name>
<surname><![CDATA[Han]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Moskewicz]]></surname>
<given-names><![CDATA[MW]]></given-names>
</name>
<name>
<surname><![CDATA[Ashraf]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Dally]]></surname>
<given-names><![CDATA[WJ]]></given-names>
</name>
<name>
<surname><![CDATA[Keutzer]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and &lt;0.5MB model size]]></article-title>
<source><![CDATA[arXiv]]></source>
<year>2016</year>
</nlm-citation>
</ref>
<ref id="B21">
<label>21</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Deng]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Dong]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
<name>
<surname><![CDATA[Socher]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[LJ]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Fei-Fei]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[ImageNet: A large-scale hierarchical image database]]></article-title>
<source><![CDATA[2009 IEEE Conference on Computer Vision and Pattern Recognition]]></source>
<year>2009</year>
<page-range>248-55</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
