<?xml version="1.0" standalone="yes"?>
<Paper uid="A92-1004">
  <Title>A PARSER FOR REAL-TIME SPEECH SYNTHESIS OF CONVERSATIONAL TEXTS</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1. INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Text-to-speech researchers and developers tend to assume that applications of their technology will focus on edited text, either &amp;quot;canned&amp;quot; material such as name and address lists, or free text like the AP newswire. There has been much effort aimed at preparing text-to-speech for applications such as caller identification and newsreading services, in which texts are generally proofed and the primary challenges come from issues of name pronunciation, intonation contouring, etc. In this paper, we concern ourselves with an application of text-to-speech for speech-impaired, deaf, ~md hard of hearing people. The application is unusual because it requires text-to-speech synthesis of unedited, spontaneously generated conversational text. Moreover the synthesis must occur in near real time as the user is typing.</Paragraph>
    <Paragraph position="1"> We will describe a parser that prepares conversational texts for synthesis by first performing lexical regularization of nonstandard forms and then identifying prosodic phrase boundaries. The parser is derived from the prosodic phrase system presented in Bachenko and Fitzpatrick (1990) and has been implemented as the front end of a version of the Bell Laboratories text-to-speech synthesizer (Olive and Liberman 1985). As a component of the text-to-speech system, the parser has undergone rigorous testing during a successful three-month field trial at an AT&amp;T telecommunications center in California. In addition, laboratory evaluations indicate that the parser's performance compares favorably with human judgments about phrasing. In Section 2 of the paper we describe the application and the texts. Section 3 provides a technical description of the parser and Section 4 discusses evaluation of the parser's performance.</Paragraph>
  </Section>
class="xml-element"></Paper>