lr-prod,1-1-H92-1074,ak evaluation methodology </term> . The <term> CSR ( Connected Speech Recognition ) corpus </term> represents a new <term> DARPA speech
other,11-1-H92-1074,ak Recognition ) corpus </term> represents a new <term> DARPA speech recognition technology development initiative </term> to advance the state of the art in
tech,25-1-H92-1074,ak to advance the state of the art in <term> CSR </term> . This <term> corpus </term> essentially
lr-prod,7-2-H92-1074,ak essentially supersedes the now old <term> Resource Management ( RM ) corpus </term> that has fueled <term> DARPA speech
other,16-2-H92-1074,ak RM ) corpus </term> that has fueled <term> DARPA speech recognition technology development </term> for the past 5 years . The new <term>
lr-prod,2-3-H92-1074,ak </term> for the past 5 years . The new <term> CSR corpus </term> supports research on major new problems
other,18-3-H92-1074,ak , natural <term> grammar </term> , and <term> spontaneous speech </term> . This paper presents an overview
lr-prod,7-4-H92-1074,ak paper presents an overview of the <term> CSR corpus </term> , reviews the definition and development
lr-prod,17-4-H92-1074,ak definition and development of the <term> CSR pilot corpus </term> , and examines the dynamic challenge
lr-prod,29-4-H92-1074,ak dynamic challenge of extending the <term> CSR corpus </term> to meet future needs . <term> Language
hide detail