{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T05:22:36Z","timestamp":1737264156787,"version":"3.33.0"},"reference-count":18,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2007,3,21]],"date-time":"2007-03-21T00:00:00Z","timestamp":1174435200000},"content-version":"vor","delay-in-days":6653,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems &amp;amp; Computers in Japan"],"published-print":{"date-parts":[[1989,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper discusses the high\u2010speed DP\u2010matching as the speech recognition algorithm including connected word sequence recognition. The first improvement is the frame synchronization. By this elaboration, an improvement of the speed by approximately one order of magnitude is achieved, compared with the consecutive word recognition of two\u2010level DP\u2010matching type, where DP\u2010matching is iterated by assuming that any time in the input speech can be the word boundary. The second improvement is the introduction of the beam search.<\/jats:p><jats:p>This paper discusses the practical aspects of combining the beam search and DP\u2010matching. The discussion includes the construction of the work area, control of DP recursive expression and other problems, aiming at an effective reduction of the computational complexity for the recursive expression. The third improvement is the built\u2010in vector quantization. It is shown that an effective reduction of the computational complexity for the local distance can be produced through a skillful integration of the beam search and the vector quantization.<\/jats:p><jats:p>Through an evaluation experiment for the discrete word, it is seen that there is a possibility of achieving the speed improvement by a factor of 30. This corresponds to the speed improvement of two or more orders of magnitude, compared with the two\u2010level DP\u2010matching for the consecutive word sequence recognition algorithm.<\/jats:p>","DOI":"10.1002\/scj.4690201104","type":"journal-article","created":{"date-parts":[[2007,7,7]],"date-time":"2007-07-07T17:30:32Z","timestamp":1183829432000},"page":"33-45","source":"Crossref","is-referenced-by-count":4,"title":["A high\u2010speed dp\u2010matching algorithm based on frame synchronization, beam search and vector quantization"],"prefix":"10.1002","volume":"20","author":[{"given":"Hiroaki","family":"Sakoe","sequence":"first","affiliation":[]},{"given":"Hiromi","family":"Fujii","sequence":"additional","affiliation":[]},{"given":"Kazunaga","family":"Yoshida","sequence":"additional","affiliation":[]},{"given":"Masao","family":"Watari","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\/TASSP.1979.1163310"},{"issue":"11","key":"e_1_2_1_3_2","first-page":"649","article-title":"A generalized two\u2010level DP\u2010matching algorithm for continuous speech recognition","volume":"65","author":"Sakoe H.","year":"1982","journal-title":"Trans. I.E.C.E., Japan"},{"key":"e_1_2_1_4_2","article-title":"Recognition of continuously spoken numerals using semi\u2010word and standard pattern","volume":"1407","author":"Sakoe H.","year":"1982","journal-title":"Nat. Conv. Gen. I.E.C.E., Japan"},{"key":"e_1_2_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"e_1_2_1_6_2","first-page":"88","article-title":"Connected speech recognition system DP\u2010100","volume":"56","author":"Tsuruta S.","year":"1980","journal-title":"NEC Research & Development"},{"key":"e_1_2_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.1985.1146207"},{"key":"e_1_2_1_8_2","article-title":"Clockwise propagating DP\u2010matching algorithm for connected word recognition","volume":"81","author":"Sakoe H.","year":"1981","journal-title":"Tech. Rep. Speech, Acoust. Soc., Japan"},{"key":"e_1_2_1_9_2","article-title":"A high\u2010speed DP\u2010matching algorithm based on beam search and vector quantization","volume":"87","author":"Sakoe H.","year":"1987","journal-title":"Tech. Rep. I.E.C.I.E., Japan"},{"issue":"8","key":"e_1_2_1_10_2","first-page":"1041","article-title":"Large vocabulary word recognition using pseudophoneme templates","volume":"65","author":"Sugamura N.","year":"1982","journal-title":"Trans. (D), I.E.C.E., Japan"},{"key":"e_1_2_1_11_2","doi-asserted-by":"crossref","unstructured":"J.Bridle M.Brown andM.Chamberlain.An algorithm for connected word recognition. Proc. ICASSP'82 pp.899\u2013902(May1982).","DOI":"10.1007\/978-94-009-7879-9_11"},{"key":"e_1_2_1_12_2","doi-asserted-by":"crossref","unstructured":"H.Ney D.Mergel A.Noll andA.Passeler.A data driven organization of the dynamic programming beam search for continuous speech recognition. Proc. ICASSP'87 pp.833\u2013836(May1987).","DOI":"10.1109\/ICASSP.1987.1169844"},{"key":"e_1_2_1_13_2","first-page":"171","volume-title":"Two\u2010level DP\u2010matching efficiently recognizing continuously spoken word","author":"Sakoe H.","year":"1983"},{"key":"e_1_2_1_14_2","article-title":"Recognition of continuously spoken word based on two\u2010level DP\u2010matching","volume":"75","author":"Sakoe H.","year":"1975","journal-title":"Tech. Rep. Speech, Acoust. Soc., Japan"},{"key":"e_1_2_1_15_2","unstructured":"B.Lowere.The HARPY speech recognition system. Ph.D. Thesis Carnegie\u2010Mellon Univ. (April1976)."},{"key":"e_1_2_1_16_2","first-page":"55","article-title":"Evaluation of high\u2010speed DP\u2010matching algorithm for speech recognition with integration of beam search and vector quantization","volume":"2","author":"Fujii H.","year":"1987","journal-title":"Proc. Acoust. Soc., Japan"},{"key":"e_1_2_1_17_2","article-title":"A speech recognition system using high\u2010speed DP\u2010matching algorithm based on beam search and vector quantization. Nat. Conv. Inf","volume":"173","author":"Shimizu","year":"1987","journal-title":"I.E.C.I.E., Japan"},{"key":"e_1_2_1_18_2","doi-asserted-by":"crossref","unstructured":"T. K.Vintsyuk.Element\u2010wise recognition of continuous speech consisting of words in a given vocabulary. Kiber\u2010netika (Cybernetics) pp.361\u2013372(March\u2010April 1971).","DOI":"10.1007\/BF01071812"},{"key":"e_1_2_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163527"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690201104","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690201104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T15:25:13Z","timestamp":1737213913000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690201104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1989,1]]},"references-count":18,"journal-issue":{"issue":"11","published-print":{"date-parts":[[1989,1]]}},"alternative-id":["10.1002\/scj.4690201104"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690201104","archive":["Portico"],"relation":{},"ISSN":["0882-1666","1520-684X"],"issn-type":[{"type":"print","value":"0882-1666"},{"type":"electronic","value":"1520-684X"}],"subject":[],"published":{"date-parts":[[1989,1]]}}}