Search

11 Jan 2008: end. Figure 4: Calculating Decision Tree Divergence. 5. ResultsExperiments were performed on a Broadcast News Arabic task.Each system was trained using 101.8 hours of data and a PLPfrontend. ... Sinha, and S.E. Tranter, “Progress in the CU-HTK

26 Mar 2008: Results for both Chinese-English and Arabic-English on two text development sets as well asa broadcast news development set used by the AGILE team in theGALE program4. ... Furthermore the actual evaluation results from the2006 test are included. The 2006

11 Jan 2008: Experi-ments were carried out on a Mandarin broadcast transcription taskusing both Broadcast News (BN) and Broadcast Conversation (BC)data. ... The CU-HTK Mandarin Broadcast News Transcription System,” Proc.ICASSP 2006, Toulouse. 4.

11 Jan 2008: Makhoul,“Recent progress in Arabic broadcast news transcription atBBN,” in Proc. InterSpeech, 2005. ... ICASSP 2006, May, 2006, pp. 1056–1059. [10] L. Wang, M.J.F. Gales, and Woodland P.C., “Unsupervisedtraining for Mandarin broadcast news and

11 Jan 2008: A total of 942 hours of broad-cast news (BN) and broadcast conversation (BC) speech audio datawere used for acoustic model training. ... Tranter. Progress in the CU-HTK broadcast news tran-scription system, IEEE Transactions Speech and Audio Pro-cessing,

26 Mar 2008: Makhoul,“Recent progress in Arabic broadcast news transcription atBBN,” in Proc. InterSpeech, 2005. ... ICASSP 2006, May, 2006, pp. 1056–1059. [10] L. Wang, M.J.F. Gales, and Woodland P.C., “Unsupervisedtraining for Mandarin broadcast news and

11 Jan 2008: 1. INTRODUCTION. Adaptive training [1, 2] has become popular as the use of founddata, such as Broadcast News, has increased.

3 Dec 2008: 1. IntroductionSpeech recognition systems are increasingly being built withfound data such as broadcast news and conversational tele-phone speech recordings.

26 Mar 2008: A total of 942 hours of broad-cast news (BN) and broadcast conversation (BC) speech audio datawere used for acoustic model training. ... Tranter. Progress in the CU-HTK broadcast news tran-scription system, IEEE Transactions Speech and Audio Pro-cessing,

19 Mar 2008: The reviewconcludes with a case study of LVCSR for Broadcast News andConversation transcription in order to illustrate the techniquesdescribed. ... Much of this development was driven by a series of DARPAand NSA programmes [188] which set ever more

9 Jul 2008: 7.4 Summary. 92. 8 Experimental Setup 94. 8.1 Broadcast News Training and Decoding. ... 13110.2.6 MBRL on Broadcast News Mandarin. 131. 10.3 Addressing Alignment Issues.

16 Feb 2008: hours of speech data, for example from broadcast news television feeds.

17 Sep 2008: 1208.2.4 Combined Systems. 122. 8.3 Summary. 124. 9 Experimental Results on Recorded Noisy Speech 1259.1 Broadcast News Transcription. ... as Broadcast News and Toshiba Research Europe’s internal collection of in-carspeech data.

16 Feb 2008: are often available as aligned documents, such as news stories, which usually need to. ... 72. 5.9 Percentage of Usable Arabic-English Bitext. English tokens for Arabic-English news and UN parallel corpora under different alignment pro-cedures.

16 Feb 2008: Minimum Bayes-Risk Techniquesin Automatic Speech Recognition. and Statistical Machine Translation. Shankar Kumar. A dissertation submitted to the Johns Hopkins University in conformity with the. requirements for the degree of Doctor of Philosophy.