<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2120">
  <Title>Matching a tone-based and tune-based approach to English intonation for concept-to-speech generation</Title>
  <Section position="3" start_page="0" end_page="829" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The pallet describes the main results of a con&gt; parison of /;he ToB: (Tone-and-Break-Indices) ai)proach (Pierrehumbert, 1.9801 Silverman el; al.., 19961 to annotating English speech data with information about intonation and one of the British School approaches (e.g., Brazil et al.</Paragraph>
    <Paragraph position="1"> (1980)), Systenfie Fmmtional Grammar (SFO; (Halliday, 19671 Halliday, 1970)). The goal of this comparison is the definition of a mapping between the two systems.</Paragraph>
    <Paragraph position="2"> This attempt has a two-fbld motiw~tion.</Paragraph>
    <Paragraph position="3"> First, it is motivated by computational application in concept-to-si)eech systems, in which text in spoken mode is automatically generated from an underlying abstract lneaning representation, it is widely acknowledged that in order for spoken language technology to gain wider acceptance, it has to improve on the quality of output considerably. Itere, appropriate intonation is one of the major factors (ct'. Cole et al. (1995)). The concrete goal we are pursuing is to connect an oil-the-shelf speech synthesizer for English (FESTIVAL; (Black et al., 1998)) with an automatic text generation system tbr English based on SFO (Matthiessen &amp; Bateman, 19911. Since in the SFO approach, intonation is accounted for as part of grammar rather than as an independent component, it is straightforward to extend the grammatical resources of a systemically based text generation system with an account of intonation (cf Teich et al. (1.997) iml)lenmnting such all approach for German concet/t-to-speech generation). Connecting such a system to a speech synthesizer requires mapping the OUtl)ut of the generator to the input requirements of the st)eech synth(&gt; sizer. In the FESTIVAL systei11, the intonation of the text to be synthesized can be manipulated 1)y ~mnotation with TOBI labels. Therefore, a mapl)ing betweeIl the SFC and the ToBI annotation systems is required.</Paragraph>
    <Paragraph position="4"> Second, there is a theoretical lnotivation.</Paragraph>
    <Paragraph position="5"> With a mapping between tile ToBI and the slpo systems for intonation almotation, it will be possible to link the 1)honetic analysis of speech data to an interpretation of intonational meaning as it is proposed by SFO. Existing speech corpora that are acoustically analysed and annotated with ToBI tail then be used to test some of the assumptions brought forward by SFO about the natm:e of intonation. Also, with a mapping between ~oBI and SFG annotations, an exchange of annotated corpora between ToBI and SFO users would be possible.</Paragraph>
    <Paragraph position="6"> We report on the analysis of a sl)eech corpus compiled fl'om Halliday (1970) with ToBI and SFO labels (See. 3). The intonation analysis is based on an acoustic analysis of the speech data in terms of fundamental frequency (F0).</Paragraph>
    <Paragraph position="7">  The data are represented in EMU (Cassidy &amp;; Harrington, 1996), a database system for storing speech data that provides for a nmltipletier analysis of acoustic (e.g., F0 contour and speech wavetbrm) and phonological (segmental and suprasegmental) features. We present the major differences and commonalities between ToBI and SFO (See. 2). On the basis of the corpus analysis, we identify matches between the tunes assmned by Halliday and unique sequences of To\]~I tones (See. 4). We conclude with a smmnary and a sketch of future work.</Paragraph>
  </Section>
class="xml-element"></Paper>