<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-3703">
  <Title>Speech to Speech Translation for Medical Triage in Korean</Title>
  <Section position="4" start_page="0" end_page="1" type="intro">
    <SectionTitle>
2 Background
</SectionTitle>
    <Paragraph position="0"> Sehda is focused on creating speech translation systems to overcome language barriers in health-care settings in the U.S. The number of people in the U.S. who speak a language other than English is large and growing, and Spanish is the most commonly spoken language next to English. According to the 2000 census, 18% of the U.S. population aged 5 and older (47 million people) did not speak English at home.</Paragraph>
    <Paragraph position="1">  This represents a 48% increase from the 1990 figure. In 2000, 8% of the population (21 million) was Limited English Proficient (LEP). More than 65% of the LEP population (almost 14 million people) spoke Spanish.</Paragraph>
    <Paragraph position="2"> A body of research shows that language barriers impede access to care, compromise quality, and increase the risk of adverse outcomes. Although trained medical interpreters and bilingual health-care providers are effective in overcoming such language barriers, the use of semi-fluent healthcare professionals and ad hoc interpreters causes more interpreter errors and lower quality of care (Flores 2005).</Paragraph>
    <Paragraph position="3"> One study analyzed the problem of language barriers for hospitalized inpatients. The study, which focused on pediatric patients, sought to determine whether patients whose families have a language barrier are more likely to incur serious medical errors than patients without a language barrier (Cohen et al., 2005). The study's conclusion was that patients of LEP families had a twofold increased risk for serious medical incident compared with patients whose families did not have a language barrier. It is important to note that the LEP</Paragraph>
  </Section>
class="xml-element"></Paper>