| tech,17-2-H92-1016,bq | model </term> in conjunction with a <term> | probabilistic LR parser | </term> , and refinements made to the <term> | #18726 These include context-dependent phonetic modelling, the use of a bigram language model in conjunction with aprobabilistic LR parser, and refinements made to the lexicon. |
| lr,12-4-H92-1016,bq | language system </term> on the same <term> | test set | </term> is 49.3 % . Similar results were | #18789 The weighted error for the entire spoken language system on the sametest set is 49.3%. |
| lr-prod,7-5-H92-1016,bq | results were also obtained on the <term> | February '92 benchmark evaluation | </term> . This paper describes three relatively | #18802 Similar results were also obtained on theFebruary '92 benchmark evaluation. |
| lr-prod,35-3-H92-1016,bq | 2.5 and 1.6 , respectively , on the <term> | October '91 test set | </term> . The weighted error for the entire | #18772 Together with the use of a larger training set, these modifications combined to reduce the speech recognition word and sentence error rates by a factor of 2.5 and 1.6, respectively, on theOctober '91 test set. |
| tool,7-1-H92-1016,bq | paper describes the status of the <term> | MIT ATIS system | </term> as of February 1992 , focusing especially | #18690 This paper describes the status of theMIT ATIS system as of February 1992, focusing especially on the changes made to the SUMMIT recognizer. |
| lr,26-2-H92-1016,bq | </term> , and refinements made to the <term> | lexicon | </term> . Together with the use of a larger | #18735 These include context-dependent phonetic modelling, the use of a bigram language model in conjunction with a probabilistic LR parser, and refinements made to thelexicon. |
| tech,2-2-H92-1016,bq | SUMMIT recognizer </term> . These include <term> | context-dependent phonetic modelling | </term> , the use of a <term> bigram language | #18711 These includecontext-dependent phonetic modelling, the use of a bigram language model in conjunction with a probabilistic LR parser, and refinements made to the lexicon. |
| tool,23-1-H92-1016,bq | especially on the changes made to the <term> | SUMMIT recognizer | </term> . These include <term> context-dependent | #18706 This paper describes the status of the MIT ATIS system as of February 1992, focusing especially on the changes made to theSUMMIT recognizer. |
| lr,7-3-H92-1016,bq | Together with the use of a larger <term> | training set | </term> , these modifications combined to | #18744 Together with the use of a largertraining set, these modifications combined to reduce the speech recognition word and sentence error rates by a factor of 2.5 and 1.6, respectively, on the October '91 test set. |
| tech,6-4-H92-1016,bq | The weighted error for the entire <term> | spoken language system | </term> on the same <term> test set </term> is | #18783 The weighted error for the entirespoken language system on the same test set is 49.3%. |
| model,10-2-H92-1016,bq | phonetic modelling </term> , the use of a <term> | bigram language model | </term> in conjunction with a <term> probabilistic | #18719 These include context-dependent phonetic modelling, the use of abigram language model in conjunction with a probabilistic LR parser, and refinements made to the lexicon. |
| measure(ment),16-3-H92-1016,bq | modifications combined to reduce the <term> | speech recognition word and sentence error rates | </term> by a factor of 2.5 and 1.6 , respectively | #18753 Together with the use of a larger training set, these modifications combined to reduce thespeech recognition word and sentence error rates by a factor of 2.5 and 1.6, respectively, on the October '91 test set. |
