File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/intro/92/c92-3164_intro.xml

Size: 2,067 bytes

Last Modified: 2025-10-06 14:05:13

<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-3164">
  <Title>A SPOKEN LANGUAGE TRANSLATION SYSTEM : SL-TRANS2</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. Introduction
</SectionTitle>
    <Paragraph position="0"> An automatic telephone interpreting system will undoubtedly be used to overcome communication barriers between people speaking different languages. Recently, great interest has been growing in this area \[Saitoh88\], \[Waibel-91l, \[Kitano-91\], \[Roe-92\]. SL-TRANS2 .1~ is an experimental system developed at ATR, which translates Japanese speech to English speech. It is composed of three basic components: speech recognition, translation and speech synthesis. This paper introduces the system with emphasis on the translation component. The discourse domain is a dialogue concerning an international conference registration. The distinctive features of the system are as follows.</Paragraph>
    <Paragraph position="1">  (1) Japanese continuous speech input can be recognized with high accuracy. Moreover, speaker independent recognition using speaker adaptation technique has been developed.</Paragraph>
    <Paragraph position="2"> (2) Various expressions peculiar to spoken  language can be accepted and translated properly into the target language. In Japanese, the style of spoken sentences is generally quite different from that of written texts. Spoken utterances are fragmentary and include the speaker's intention directly or indirectly. The system extracts the intention and then transcribes it to a proper  expression in the target language.</Paragraph>
    <Paragraph position="3"> (3) Linguistic knowledge sources necessary for  the translation are defined declaratively to the extent. Such definition improves high modularity, readability and easy maintenance of knowledge description.</Paragraph>
    <Paragraph position="4"> In the next section, the system is overviewed and a brief description of the speech recognition *1) SL-TRANS2 is the extended version of SL-</Paragraph>
  </Section>
class="xml-element"></Paper>
Download Original XML