{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T06:41:16Z","timestamp":1698043276839},"reference-count":10,"publisher":"Wiley","issue":"14","license":[{"start":{"date-parts":[[2007,3,21]],"date-time":"2007-03-21T00:00:00Z","timestamp":1174435200000},"content-version":"vor","delay-in-days":5923,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems &amp; Computers in Japan"],"published-print":{"date-parts":[[1991,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Many researchers achieved high phoneme recognition rates by multilayered neural networks with linear discrimination neural (LDN) units. However, it is difficult to analyze which components of the input are important to each unit in those LDN networks.<\/jats:p><jats:p>This paper proposed a multilayer neural network with elliptic discrimination neural (EDN) units so that the functions of each unit in the network may be interpreted more definitely. The center of the elliptic discrimination boundary of a neural unit corresponds to a typical point in an input space. The radii of the ellipse express the extent of the corresponding components in the input space, hence it becomes clear which components of the input space are important to each unit in the EDN network.<\/jats:p><jats:p>To compare the performance of EDN and LDN networks, recognition experiments of phonemes \/b, d, g\/ in 5240 tokens of a Japanese speech database were carried out. In the experiments, recognition rates were obtained by EDN networks as high as the rate by an LDN network. Also, it was confirmed which components of the input space are important to each unit in the EDN network.<\/jats:p>","DOI":"10.1002\/scj.4690221407","type":"journal-article","created":{"date-parts":[[2007,7,7]],"date-time":"2007-07-07T20:26:09Z","timestamp":1183839969000},"page":"90-100","source":"Crossref","is-referenced-by-count":0,"title":["Phoneme recognition with elliptic discrimination neural units"],"prefix":"10.1002","volume":"22","author":[{"given":"Noboru","family":"Kanedera","sequence":"first","affiliation":[]},{"given":"Tetsuo","family":"Funada","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2007,3,21]]},"reference":[{"key":"e_1_2_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"e_1_2_1_3_2","first-page":"47","article-title":"A procedure for designing three\u2010layer neural networks for pattern recognition applications","volume":"88","author":"Kawahara H.","year":"1988","journal-title":"I.E.C.E. Tech. Rep."},{"key":"e_1_2_1_4_2","first-page":"133","article-title":"Analysis of internal representation in neural network consisting of higher\u2010order neurons","volume":"88","author":"Saito O.","year":"1988","journal-title":"Papers of Technical Group on Medical and Biological Engineering, I.E.C.E."},{"key":"e_1_2_1_5_2","unstructured":"N.KanederaandT.Funada.Phoneme recognition of continuous speech using higher\u2010order neural networks. In: Proc. Fall Meet. Acoust. Soc. Japan (Oct.1989)."},{"key":"e_1_2_1_6_2","unstructured":"N.KanederaandT.Funada.\/b d g\/ recognition with elliptic discrimination neuron. In: Proc. Spring Meet. Acoust. Soc. Japan (March1990)."},{"key":"e_1_2_1_7_2","first-page":"25","article-title":"Construction of an acoustically phonetically transcribed Japanese speech database","volume":"87","author":"Takeda K.","year":"1987","journal-title":"I.E.C.E. Tech. Rep."},{"key":"e_1_2_1_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"issue":"1","key":"e_1_2_1_9_2","first-page":"72","article-title":"A neural network for phonetic segmentation of continuous speech","volume":"73","author":"Kanedera N.","year":"1990","journal-title":"Trans. I.E.I.C.E., Japan"},{"issue":"11","key":"e_1_2_1_10_2","first-page":"827","article-title":"Speaker\u2010independent discrimination of Japanese consonants in isolated syllables using pairwise discrimination method","volume":"45","author":"Doshita S.","year":"1989","journal-title":"The Journal of the Acoust. Soc. Japan"},{"issue":"3","key":"e_1_2_1_11_2","first-page":"531","article-title":"A continuous speech recognition system with a powerful environment for the knowledge\u2010base construction","volume":"71","author":"Tujino K.","year":"1988","journal-title":"Trans. I.E.I.C.E., Japan"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690221407","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690221407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T01:20:25Z","timestamp":1698024025000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690221407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1991,1]]},"references-count":10,"journal-issue":{"issue":"14","published-print":{"date-parts":[[1991,1]]}},"alternative-id":["10.1002\/scj.4690221407"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690221407","archive":["Portico"],"relation":{},"ISSN":["0882-1666","1520-684X"],"issn-type":[{"value":"0882-1666","type":"print"},{"value":"1520-684X","type":"electronic"}],"subject":[],"published":{"date-parts":[[1991,1]]}}}