Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Katsuhiko TSUJINO"'
Autor:
Hiroyuki ISHIZAKI, Masahiro INOUE, Kazunori MANO, Takashi YUKAWA, Katsuhiko TSUJINO, Akiko Ryu INNES-TAYLOR, Tomoko ADACHI, Yukitoshi NAGAHARA, Atsuko K. YAMAZAKI, Khairiyah Bte Mohd. Yusof, Maria Anityasari
Publikováno v:
Journal of JSEE. 70:5_67-5_73
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3d23765616805a9001f903af18005a18
https://doi.org/10.4307/jsee.70.5_67
https://doi.org/10.4307/jsee.70.5_67
Autor:
Masahiro INOUE, Hiroyuki ISHIZAKI, Kazunori MANO, Takashi YUKAWA, Katsuhiko TSUJINO, Akiko Ryu INNES-TAYLOR, Tomoko ADACHI, Yukitoshi NAGAHARA, Atsuko K. YAMAZAKI
Publikováno v:
Journal of JSEE. 70:5_61-5_66
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80e40f12e2c386b9433fe29226d29ec3
https://doi.org/10.4307/jsee.70.5_61
https://doi.org/10.4307/jsee.70.5_61
Publikováno v:
IEEJ Transactions on Industry Applications. 119:1451-1460
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::de6a8afb4376be9e88ddb5af1aff49a4
https://doi.org/10.1541/ieejias.119.1451
https://doi.org/10.1541/ieejias.119.1451
Publikováno v:
International Journal of Human-Computer Studies. 45:499-526
This paper describes a framework for knowledge acquisition based on analysing and interpreting flaws in decision trees. The decision trees inductively learned are analysed using domain and task specific knowledge to detect improper states called flaw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::819850447c1689ba9852c4a275f478d3
https://doi.org/10.1006/ijhc.1996.0065
https://doi.org/10.1006/ijhc.1996.0065
Autor:
Shogo Nishida, Katsuhiko Tsujino
Publikováno v:
Artificial Intelligence in Engineering. 9:265-276
Decision tree induction is one of the most effective techniques for acquiring classification knowledge. However, appropriate pre- and post-processors have to be prepared to achieve continuous input/output mapping, because the decision trees basically
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e752a92917ea04ce5ae147c89565bb6d
https://doi.org/10.1016/0954-1810(95)00005-4
https://doi.org/10.1016/0954-1810(95)00005-4
Autor:
Shogo Nishida, Katsuhiko Tsujino
Publikováno v:
Statistics and Computing. 2:75-81
This paper describes the design philosophy of and current issues concerning a knowledge acquisition system namedkaiser. This system is an intelligent workbench for construction of knowledge bases for classification tasks by domain experts themselves.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b533eaa0876f0c03d8cf93be3806b268
https://doi.org/10.1007/bf01889585
https://doi.org/10.1007/bf01889585
Autor:
Osamu Kakusho, Katsuhiko Tsujino, Yasuo Nomura, Shunsuke Chigusa, Toru Sakurai, Riichiro Mizoguchi
Publikováno v:
Systems and Computers in Japan. 20:34-49
SPREX II is a continuous speech recognition system which uses the knowledge of experts able to recognize speech by inspecting trajectories of its feature parameters. This system has a powerful environment which supports the construction of its knowle
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a8e69fb7feebd6e0c9a8d96d1b7cfcde
https://doi.org/10.1002/scj.4690200504
https://doi.org/10.1002/scj.4690200504
Publikováno v:
Systems and Computers in Japan. 19:73-84
In the continuously uttered speech, it is often difficult to extract the features of the individual phoneme due to the interaction between phonemes called co-articulation. In such a case, a large amount of empirical knowledge is required for recognit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cb4cb809feaa9243fa576f5eb7041ccd
https://doi.org/10.1002/scj.4690190607
https://doi.org/10.1002/scj.4690190607
Publikováno v:
The Journal of the Acoustical Society of America. 84:S168-S169
Conventional speech recognition systems employ procedural languages such as FORTRAN to encode a large amount of heuristic knowledge, which makes the systems inflexible. SPREX (a SPeech Recognition EXpert) is implemented as a knowledge‐based system
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eedb79aac9b566f0f499749828beaded
https://doi.org/10.1121/1.2025950
https://doi.org/10.1121/1.2025950
Publikováno v:
The Journal of the Acoustical Society of America. 84:S170-S170
A continuous speech recognition expert system named SPREX has been constructed. It simulates the behavior of human experts who can recognize speech by inspecting the trajectories of feature parameters such as formant and power [R. Mizoguchi et al., P
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd52e6b300df6623afbd1f939b042bc3
https://doi.org/10.1121/1.2025962
https://doi.org/10.1121/1.2025962