other,8-1-H01-1017,bq users in robust , <term> mixed-initiative speech dialogue interactions </term> which reach
tech,4-2-H01-1055,bq within reach . However , the improved <term> speech recognition </term> has brought to light
other,26-1-N01-1003,bq syntactic structure </term> for elementary <term> speech acts </term> and the decision of how to combine
other,10-2-N03-1012,bq of <term> scoring </term> alternative <term> speech recognition hypotheses ( SRH ) </term> in
other,18-3-N03-1012,bq semantically coherent and incoherent <term> speech recognition hypotheses </term> . An evaluation
other,9-1-N03-2003,bq language modeling </term> of <term> conversational speech </term> are limited . In this paper , we
tech,15-3-P03-1030,bq enhancing techniques including <term> part of speech tagging </term> , new <term> similarity measures
tech,19-3-P03-1031,bq due to the <term> ambiguity </term> of <term> speech understanding </term> , it is not appropriate
other,8-1-C04-1103,bq important role in many <term> multilingual speech and language applications </term> . In this
other,12-3-I05-5003,bq <term> PER </term> which leverages <term> part of speech information </term> of the <term> words </term>
tech,36-12-J05-1003,bq ranking tasks </term> , for example , <term> speech recognition </term> , <term> machine translation
other,70-5-E06-1035,bq <term> cue phrases </term> and <term> overlapping speech </term> , are better indicators for the top-level
tech,16-2-C90-3014,bq computational <term> phonological system </term> : <term> speech recognition </term> and <term> synthesis system
other,7-1-H90-1060,bq contributions to <term> large vocabulary continuous speech recognition </term> . First , we present
lr,27-2-H90-1060,bq </term> , which uses a large amount of <term> speech </term> from a few <term> speakers </term> instead
lr,41-2-H90-1060,bq traditional practice of using a little <term> speech </term> from many <term> speakers </term> . In
lr,27-3-H90-1060,bq than the usual pooling of all the <term> speech data </term> from many <term> speakers </term>
lr,23-6-H90-1060,bq corpus </term> and a small amount of <term> speech </term> from the new ( target ) <term> speaker
tech,5-1-C92-3165,bq introduces a robust <term> interactive method for speech understanding </term> . The <term> generalized
other,35-3-H92-1003,bq <term> utterances </term> of <term> spontaneous speech </term> from five sites for use in a <term>
hide detail