In order to overcome defects of the classical hidden Markov model (HMM), Markov family model (MFM), a new statistical model was proposed. Markov family model was applied to speech recognition and natural language proc...In order to overcome defects of the classical hidden Markov model (HMM), Markov family model (MFM), a new statistical model was proposed. Markov family model was applied to speech recognition and natural language processing. The speaker independently continuous speech recognition experiments and the part-of-speech tagging experiments show that Markov family model has higher performance than hidden Markov model. The precision is enhanced from 94.642% to 96.214% in the part-of-speech tagging experiments, and the work rate is reduced by 11.9% in the speech recognition experiments with respect to HMM baseline system.展开更多
In order to utilize the spontaneous accumulation of heat (SAH) reasonably and obtain the high quality sinter with low energy consumption, a lower fuel consumption modeling based on raw materials of a certain steel wor...In order to utilize the spontaneous accumulation of heat (SAH) reasonably and obtain the high quality sinter with low energy consumption, a lower fuel consumption modeling based on raw materials of a certain steel works was built. An air-flow segregation feeding (ASF) experimental equipment was designed to simulate strand feeding process and calculate the lower fuel consumption quantity. Compared with baseline test, the ASF experimental equipment was adopted. The results of sinter pot tests show that the solid fuel consumption is lower than that in baseline test, which is decreased by 5.8%. Meanwhile, other sinter indexes, such as pan yeild, tumbler strength and strand productivity are improved. The mineralogical examination indicates that the mineral compositions and micostructures are improved in sinter.展开更多
基金Project(60763001)supported by the National Natural Science Foundation of ChinaProjects(2009GZS0027,2010GZS0072)supported by the Natural Science Foundation of Jiangxi Province,China
文摘In order to overcome defects of the classical hidden Markov model (HMM), Markov family model (MFM), a new statistical model was proposed. Markov family model was applied to speech recognition and natural language processing. The speaker independently continuous speech recognition experiments and the part-of-speech tagging experiments show that Markov family model has higher performance than hidden Markov model. The precision is enhanced from 94.642% to 96.214% in the part-of-speech tagging experiments, and the work rate is reduced by 11.9% in the speech recognition experiments with respect to HMM baseline system.
基金Project(NECT-04-0748) supported by New Century Excellent Talents Program of China
文摘In order to utilize the spontaneous accumulation of heat (SAH) reasonably and obtain the high quality sinter with low energy consumption, a lower fuel consumption modeling based on raw materials of a certain steel works was built. An air-flow segregation feeding (ASF) experimental equipment was designed to simulate strand feeding process and calculate the lower fuel consumption quantity. Compared with baseline test, the ASF experimental equipment was adopted. The results of sinter pot tests show that the solid fuel consumption is lower than that in baseline test, which is decreased by 5.8%. Meanwhile, other sinter indexes, such as pan yeild, tumbler strength and strand productivity are improved. The mineralogical examination indicates that the mineral compositions and micostructures are improved in sinter.
