Improved parallel model combination techniques with split Gaussian mixtures for speech recognition under noisy conditions.

Hung, Jeih-weihJeih-weihHungShen, Jia-LinJia-LinShenLIN-SHAN LEE2020-06-112020-06-111999https://scholars.lib.ntu.edu.tw/handle/123456789/498622Improved parallel model combination techniques with split Gaussian mixtures for speech recognition under noisy conditions.conference paper10.1109/ICASSP.1999.758156https://doi.org/10.1109/ICASSP.1999.758156