<?xml version="1.0" standalone="yes"?>
<Paper uid="H92-1102">
  <Title>PROJECT GOALS The goal of speech research at Carnegie Mellon continues</Title>
  <Section position="1" start_page="0" end_page="0" type="metho">
    <SectionTitle>
SPOKEN-LANGUAGE RESEARCH AT CARNEGIE MELLON
</SectionTitle>
    <Paragraph position="0"/>
  </Section>
  <Section position="2" start_page="0" end_page="0" type="metho">
    <SectionTitle>
PROJECT GOALS
</SectionTitle>
    <Paragraph position="0"> The goal of speech research at Carnegie Mellon continues to be the development of spoken language systems that effectively integrate speech processing into the human-computer interface in a way that facilitates the use of computers in the performance of practical tasks. Research in spoken language is currently focussed in the following areas: * Improved speech recognition technologies: Extending the useful vocabulary of of SPHINX-II by use of better phonetic models and better search techniques, providing for rapid configuration for new tasks.</Paragraph>
    <Paragraph position="1"> * Fluent human/machine interfaces: Developing an understanding of how people interact by voice with computer systems, in the context of Office Management and other domains.</Paragraph>
    <Paragraph position="2"> * Understanding spontaneous spoken language: Developing flexible parsing strategies to cope with phenomena peculiar to the lexical and grammatical structure of spoken language. Development of automatic training procedures for these grammars.</Paragraph>
    <Paragraph position="3"> * Dialog modeling: Applying constraints based on dialog, semantic, and pragmatic knowledge to identify and correct inaccurate portions of recognized utterances. * Acoustical and environmental robustness: Developing procedures to enable good recognition in office environments with desktop microphones and a useful level of recognition in more severe environments.</Paragraph>
  </Section>
  <Section position="3" start_page="0" end_page="469" type="metho">
    <SectionTitle>
RECENT RESULTS
* The SPHINX-II system incorporated sex-dependent
</SectionTitle>
    <Paragraph position="0"> semi-continuous hidden Markov models, a speaker- null normalized front end using a codeword-dependent neural network, and shared-distribution phonetic models.</Paragraph>
    <Paragraph position="1"> * Vocabulary-independent recognition was improved by introducing vocabulary-adapted decision trees and vocabulary-bias training, and by incorporating the CDCN and ISDCN acoustical pre-processing algorithms. null * SPHINX-II has been extended to the Wall Street Journal CSR task by incorporating a practical form of between null word co-articulation modeling in the context of a more efficient beam search.</Paragraph>
    <Paragraph position="2"> * The Carnegie Mellon Spoken Language Shell was reimplemented and additional applications for the Office Management domain were developed, including a telephone dialer and voice editor.</Paragraph>
    <Paragraph position="3"> * Grammatical coverage in the ATIS domain was extended. An initial set of tools was developed to create the grammar in a semi-automatic fashion from a labelled corpus.</Paragraph>
    <Paragraph position="4"> * The MINDS-II system was developed which identifies and reprocesses mis-recognized portions of a spoken utterance using semantics, pragmatics, inferred speaker intentions, and dialog structure in the context of a newlydeveloped finite-state recognizer.</Paragraph>
    <Paragraph position="5"> * Acoustical pre-processing algorithms for environmental robustness were extended, made more efficient, and demonstrated in the ATIS domain. Pre-processing was combined microphone arrays and with auditory models in pilot experiments.</Paragraph>
  </Section>
  <Section position="4" start_page="469" end_page="469" type="metho">
    <SectionTitle>
PLANS FOR THE COMING YEAR
</SectionTitle>
    <Paragraph position="0"> * We will extend shared-distribution models to produce senonic baseforms, addressing the problem of new word learning and pronunciation optimization, and the the decision-tree-based senone will be made more general.</Paragraph>
    <Paragraph position="1"> The CDNN-based approach will be extended for both speaker and environment normalization. The use of long-distance semantic correlations in language models to improve the prediction capability will be explored.</Paragraph>
    <Paragraph position="2"> * We will incorporate confidence measures, audio feedback, and the latest recognition technologies into the Office Manager system. We will investigate the behavior of multi-modal systems that incorporate speech recognition.</Paragraph>
    <Paragraph position="3"> * We will develop architectures and automatic learning algorithms for SLS systems with greater integration of recognition, parsing, and dialog and pragmatics. Work will be initiated on the identification of misunderstood portions of a complete utterance, and the use of partial understanding and clarification dialogs.</Paragraph>
    <Paragraph position="4"> * We will continue to develop parallel strategies for robust speech recognition, and we will demonstrate these methods in more adverse acoustical environments.</Paragraph>
  </Section>
class="xml-element"></Paper>