Search

1 Mar 2000: That system was constructed using HMMs trained on the Wall Street Journal (WSJ) corpus as a base and then adapted to individual data types of broadcast news data using supervised maximum ... Siegler M.A., Jain U., Raj B. & Stern R.M. (1997).

1 Mar 2000: The transcription of broadcast news requires techniques to deal with the large variety of data types present. ... The distribution of broadcast news data suitable for GMM training can be seen in Table 1.

2 Mar 2000: Significant progress in the accurate transcription of broadcast news data has been made over the last few years so that we are now at a point where such systems can be ... The paper is arranged as follows. We first give details of the broadcast news data

10 Apr 2000: and then adapted to individ-ual data types of broadcast news data using supervised maximumlikelihood linear regression (MLLR) [4, 2]. ... The rest of the paper is arranged as follows. We first give de-tails of the broadcast news data used, and then

1 Mar 2000: That system was constructed using HMMs trained on the Wall Street Journal (WSJ) corpus as a base and then adapted to individual data types of broadcast news data using supervised maximum ... Siegler M.A., Jain U., Raj B. & Stern R.M. (1997).

8 Mar 2000: 1. IntroductionThe transcription of broadcast news requires techniques to deal withthe large variety of data types present. ... The distribution of broadcast news data suitable for GMM trainingcan be seen in Table 1.

8 Mar 2000: level language models to combine datafrom different types of source rather than simply pooling thetexts; the use of more broadcast news language model train-ing data; and an extra acoustic adaptation ... The paper is arranged as follows. We first give

8 Mar 2000: The aim was to calibrate the dif-ficulty of the broadcast news transcription problem and de-termine the effectiveness of both different front-end analysesand unsupervised adaptation on this data. ... For the other portions of FX, a “global” model was