<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1088">
  <Title>ROBUST CONTINUOUS SPEECH RECOGNITION</Title>
  <Section position="1" start_page="0" end_page="0" type="metho">
    <SectionTitle>
ROBUST CONTINUOUS SPEECH RECOGNITION
</SectionTitle>
    <Paragraph position="0"/>
  </Section>
  <Section position="2" start_page="0" end_page="0" type="metho">
    <SectionTitle>
BBN Systems and Technologies
70 Fawcett St.
Cambridge, MA 02138
1. PROJECT GOALS
</SectionTitle>
    <Paragraph position="0"> The primary objective of this basic research program is to develop robust methods and models for speaker-independent acoustic recognition of spontaneously-produced, continuous speech. The work has focussed on developing accurate and detailed models of phonemes and their coartieulation for the purpose of large-vocabulary continuous speech recognition.</Paragraph>
    <Paragraph position="1"> Important goals of this work are to achieve the highest possible word recognition accuracy in cominuous speech and to develop methods for the rapid adaptation of phonetic models to the voice of a new speaker.</Paragraph>
  </Section>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2. RECENT RESULTS
</SectionTitle>
    <Paragraph position="0"> During the last year, we have: Developed a new 5-pass decoding algorithm that allows us to incorporate trigram language models and cross-word coarticulation models directly within the N-best search. The new decoder is considerably faster than the previous one and results in slightly higher accuracy.</Paragraph>
    <Paragraph position="1"> Participated in the December 1993 ARPA evaluations. On the baseline hub test, we achieved a 14.3% word error rate. Our result for the primary test in which we expanded the vocabulary and grammar was 12.3%, which was substantially better than any result produced by an ARPA site, and second only to one other result.</Paragraph>
    <Paragraph position="2"> In a spoke test for outlier speakers, our overall results show that the baseline performance for speakers with foreign accents is 4 times worse than that for native speakers. By using speaker adaptation, the error rate was reduced by more than a factor of 2.</Paragraph>
    <Paragraph position="3"> In a spoke test for known alternate microphones, our recognition performance with the boom microphone in the cross-channel condition did not degrade much relative to the control condition.</Paragraph>
    <Paragraph position="4"> In the spoke for spomaneous dictation, we increased the vocabulary from 20K to 4OK words, and also added about i000 words that occurred in the spontaneous training data but not in the original vocabulary. This reduced the word error from 26% to 20%.</Paragraph>
    <Paragraph position="5"> Considered several powerful models to use in search algorithms, including segmental neural networks (under a separate effort), a 13-state phoneme model, and a stochastic segment model (in collaboration with Boston University). The combination of all of the models produced the lowest error rate.</Paragraph>
    <Paragraph position="6"> Began exploring a new method for system adaptation to speakers, called auto-adaptation. This method will improve performance by making appropriate use of the information that a whole utterance is spoken by the same speaker in a single envLonment.</Paragraph>
    <Paragraph position="7"> Performed experiments to better understand issues relating to microphone independence. We developed a technique in which the training is performed with a single high quality microphone, and the test utterance with the unknown microphone is transformed to resemble the training microphone as much as possible. We found that our algorithm was able to classify the microphone into the correct microphone class about 98% of the time, and the resulting normalization reduced the word error rate by 33%. ChaSed the CCCC (CSR Corpus Coordinating Committee), and participated in other committees. The CCCC was responsible for developing the &amp;quot;hub and spokes&amp;quot; paradigm for the evaluation of CSR systems.</Paragraph>
  </Section>
  <Section position="4" start_page="0" end_page="445" type="metho">
    <SectionTitle>
3. PLANS FOR THE COMING YEAR
</SectionTitle>
    <Paragraph position="0"> We will continue our work on improving speech recognition performance both on the Wall Street Journal corpus and on the spontaneous ATIS speech corpus. Work will focus on improved phonetic models, adaptation methods, and robustness against different acoustic channels and new vocabularies and grammars.</Paragraph>
  </Section>
class="xml-element"></Paper>