tech,3-1-H01-1055,bq Recent advances in <term> Automatic Speech Recognition technology </term> have put the goal of naturally
tech,4-2-H01-1055,bq reach . However , the improved <term> speech recognition </term> has brought to light a new problem
tech,26-2-N03-1001,bq achieved using conventional <term> word-trigram recognition </term> requiring <term> manual transcription
tech,23-3-N03-1001,bq domain </term> ; the <term> output </term> of <term> recognition </term> with this <term> model </term> is then
other,10-2-N03-1012,bq <term> scoring </term> alternative <term> speech recognition hypotheses ( SRH ) </term> in terms of their
other,18-3-N03-1012,bq semantically coherent and incoherent <term> speech recognition hypotheses </term> . An evaluation of our
model,7-1-N03-1018,bq generative probabilistic optical character recognition ( OCR ) model </term> that describes an end-to-end
tech,27-2-N03-2003,bq and/or <term> topic </term> of the target <term> recognition task </term> , but also that it is possible
tech,36-12-J05-1003,bq tasks </term> , for example , <term> speech recognition </term> , <term> machine translation </term>
other,5-3-P80-1004,bq generalized metaphor </term> contains a <term> recognition network </term> , a <term> basic mapping </term>
tech,14-4-P80-1004,bq from a <term> reconstruction </term> to a <term> recognition task </term> . Implications towards automating
tech,5-4-P84-1047,bq addition , it facilitates <term> fragmentary recognition </term> and the use of <term> multiple parsing
tech,22-4-P84-1047,bq is particularly useful for robust <term> recognition of extra-grammatical input </term> . Several
other,6-12-J86-3001,bq processing description specifies in these <term> recognition tasks </term> the role of information from
tech,16-2-C90-3014,bq <term> phonological system </term> : <term> speech recognition </term> and <term> synthesis system </term> .
other,7-1-H90-1060,bq <term> large vocabulary continuous speech recognition </term> . First , we present a new paradigm
tech,6-4-H90-1060,bq <term> training speakers </term> for <term> SI recognition </term> , we achieved a 7.5 % <term> word error
tech,4-3-C92-4199,bq mechanism includes <term> title-driven name recognition </term> , <term> adaptive dynamic word formation
measure(ment),16-3-H92-1016,bq modifications combined to reduce the <term> speech recognition word and sentence error rates </term> by
tech,17-3-H92-1036,bq approach for the following four <term> speech recognition </term> applications , namely <term> parameter
hide detail