| tool,7-1-H91-1010,ak | following describes recent work on the <term> | Lincoln CSR system | </term> . Some new variations in <term> semiphone | #21726 The following describes recent work on theLincoln CSR system. | |
| tech,4-2-H91-1010,ak | system </term> . Some new variations in <term> | semiphone modeling | </term> have been tested . A very simple | #21734 Some new variations insemiphone modeling have been tested. | |
| model,4-3-H91-1010,ak | been tested . A very simple improved <term> | duration model | </term> has reduced the <term> error rate </term> | #21744 A very simple improvedduration model has reduced the error rate by about 10% in both triphone and semiphone systems. | |
| measure(ment),9-3-H91-1010,ak | duration model </term> has reduced the <term> | error rate | </term> by about 10 % in both <term> triphone | #21749 A very simple improved duration model has reduced theerror rate by about 10% in both triphone and semiphone systems. | |
| tech,17-3-H91-1010,ak | error rate </term> by about 10 % in both <term> | triphone and semiphone systems | </term> . A new <term> training strategy </term> | #21757 A very simple improved duration model has reduced the error rate by about 10% in bothtriphone and semiphone systems. | |
| tech,2-4-H91-1010,ak | and semiphone systems </term> . A new <term> | training strategy | </term> has been tested which , by itself | #21764 A newtraining strategy has been tested which, by itself, did not provide useful improvements but suggests that improvements can be obtained by a related rapid adaptation technique. | |
| tech,27-4-H91-1010,ak | improvements can be obtained by a related <term> | rapid adaptation technique | </term> . Finally , the <term> recognizer </term> | #21789 A new training strategy has been tested which, by itself, did not provide useful improvements but suggests that improvements can be obtained by a relatedrapid adaptation technique. | |
| tech,3-5-H91-1010,ak | adaptation technique </term> . Finally , the <term> | recognizer | </term> has been modified to use <term> bigram | #21796 Finally, therecognizer has been modified to use bigram back-off language models. | |
| model,9-5-H91-1010,ak | recognizer </term> has been modified to use <term> | bigram back-off language models | </term> . The <term> system </term> was then | #21802 Finally, the recognizer has been modified to usebigram back-off language models. | |
| tech,1-6-H91-1010,ak | back-off language models </term> . The <term> | system | </term> was then transferred from the <term> | #21808 Thesystem was then transferred from the RM task to the ATIS CSR task and a limited number of development tests performed. | |
| other,7-6-H91-1010,ak | </term> was then transferred from the <term> | RM task | </term> to the <term> ATIS CSR task </term> and | #21814 The system was then transferred from theRM task to the ATIS CSR task and a limited number of development tests performed. | |
| other,11-6-H91-1010,ak | from the <term> RM task </term> to the <term> | ATIS CSR task | </term> and a limited number of <term> development | #21818 The system was then transferred from the RM task to theATIS CSR task and a limited number of development tests performed. | |
| tech,19-6-H91-1010,ak | task </term> and a limited number of <term> | development tests | </term> performed . <term> Evaluation test | #21826 The system was then transferred from the RM task to the ATIS CSR task and a limited number ofdevelopment tests performed. | |
| measure(ment),0-7-H91-1010,ak | development tests </term> performed . <term> | Evaluation test results | </term> are presented for both the <term> RM | #21830 The system was then transferred from the RM task to the ATIS CSR task and a limited number of development tests performed.Evaluation test results are presented for both the RM and ATIS CSR tasks. | |
| other,8-7-H91-1010,ak | results </term> are presented for both the <term> | RM and ATIS CSR tasks | </term> . This paper describes an implemented | #21838 Evaluation test results are presented for both theRM and ATIS CSR tasks. |
