• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2
• /
• pp.199-210
• /
• 2002

In this paper, we carried out the study on speech recognition using the KM-Net topology design algorithm based on decision tree state-clustering to improve the performance of acoustic models in speech recognition. The Korean has many allophonic and grammatical rules compared to other languages, so we investigate the allophonic variations, which defined the Korean phonetics, and construct the phoneme question set for phonetic decision tree. The basic idea of the HM-Net topology design algorithm is that it has the basic structure of SSS (Successive State Splitting) algorithm and split again the states of the context-dependent acoustic models pre-constructed. That is, it have generated. the phonetic decision tree using the phoneme question sets each the state of models, and have iteratively trained the state sequence of the context-dependent acoustic models using the PDT-SSS (Phonetic Decision Tree-based SSS) algorithm. To verify the effectiveness of the above algorithm we carried out the speech recognition experiments for 452 words of center for Korean language Engineering (KLE452) and 200 sentences of air flight reservation task (YNU200). Experimental results show that the recognition accuracy has progressively improved according to the number of states variations after perform the splitting of states in the phoneme, word and continuous speech recognition experiments respectively. Through the experiments, we have got the average 71.5%, 99.2% of the phoneme, word recognition accuracy when the state number is 2,000, respectively and the average 91.6% of the continuous speech recognition accuracy when the state number is 800. Also we haute carried out the word recognition experiments using the HTK (HMM Too1kit) which is performed the state tying, compared to share the parameters of the HM-Net topology design algorithm. In word recognition experiments, the HM-Net topology design algorithm has an average of 4.0% higher recognition accuracy than the context-dependent acoustic models generated by the HTK implying the effectiveness of it.

• Korean Journal of Food Science and Technology
• /
• v.30 no.4
• /
• pp.862-870
• /
• 1998

This study shows the application of Ci-ELISA method for monitoring the denaturation of myosin by the frozen treatment in order to differentiate thawed beef from chilled. Hanwoo M.Semitendinosus (n=25) was treated under the two different frozen process as follows; simple frozen treatment (Exp-1) at 4 different temperatures, -10, -20, -50 and $-80^{\circ}C$, respectively, and repeated thawing-refreezing treatment (Exp-2) stored at 4 different temperatures, -10, -20, -50 and $-80^{\circ}C$, respectively. Antibodies (Abs) were produced from rabbits immunized with myosin whole molecule (MWM) isolated from beef round, heavy meromyosin S-1 (S-1) and light meromyosin (LMM) prepared by digestion of MWM. Each immunoglobulin G (IgG) was separated from antiserum. At 6 month storage, IA of anti-MWM IgG for myosin was decreased to 32.67, 32. 23, 51.52 and 34.27% in Exp-1 and to 14.82, 15.61, 25.3 and 23.7% in Exp-2 at -10, -20, -50 and $-80^{\circ}C$, respectively (P<0.05). In Exp-1, the reactivities of anti-LMM IgG were decreased to 25.12, 21.42, 49.05 and 28.96%, and those of Exp-2 were to 11.88, 9.56, 20.63 and 12.64% at -10, -20, -50 and $-80^{\circ}C$, respectively, at 6 times thawing (P<0.05). Conclusively, myosin was denaturated by freezing treatment and LMM or myosin rod part might have suffered from more extreme demage than HMM S-1, and samples at $-50^{\circ}C$ were slightly injured less than others by freezing treatment.