{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T16:10:38Z","timestamp":1737216638594,"version":"3.33.0"},"reference-count":16,"publisher":"Wiley","issue":"7","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>A simplified version of a hidden Markov model (HMM), referred to as the<jats:italic>N<\/jats:italic>\u2010segment label histogram (NLH) method, is proposed for speaker\u2010independent isolated word recognition. The NLH method can be considered as an HMM with a uniform duration for each state. It can also be treated as a statistical pattern recognition approach using linear compander and probabilistic measures. During the training, the label histograms are computed for<jats:italic>N<\/jats:italic>equal segments of the input. The probability associated with each label is computed after normalization. During the recognition, the input is partitioned into<jats:italic>N<\/jats:italic>equal segments, the corresponding label that maximizes the label probability of the input word determines the recognition result. Since the NLH method requires only about one\u2010tenth the computation of the HMM method, it is more suitable for implementation on small computers. Furthermore, it does not require alignment along the time axis as do the HMM and DP matching techniques. The utterance fluctuation along the time axis is handled statistically and is applicable to a large data set. Experimental results indicated that the NLH method rendered almost the same recognition rate as the other two methods while requiring much less computation. The linear approximation of the likelihood function enables the implementation of the proposed algorithm on the IBM PC\/AT for real time speech recognition.<\/jats:p>","DOI":"10.1002\/scj.4690200703","type":"journal-article","created":{"date-parts":[[2007,7,7]],"date-time":"2007-07-07T18:08:56Z","timestamp":1183831736000},"page":"20-28","source":"Crossref","is-referenced-by-count":0,"title":["Speaker\u2010independent isolated word recognition using n\u2010segment label histogram method"],"prefix":"10.1002","volume":"20","author":[{"given":"Osaaki","family":"Watanuki","sequence":"first","affiliation":[]},{"given":"Toyohisa","family":"Kaneko","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\/PROC.1976.10159"},{"key":"e_1_2_1_3_2","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1983.tb03115.x"},{"key":"e_1_2_1_4_2","doi-asserted-by":"crossref","unstructured":"O.WatanukiandT.Kaneko.Speaker\u2010independent isolated word recognition using label histograms. Proc. of ICASSP'86 pp.2679\u20132682(April1986).","DOI":"10.1109\/ICASSP.1986.1168581"},{"key":"e_1_2_1_5_2","unstructured":"WatanukiandKaneko.Label histogram method for speaker\u2010independent isolated word recognition. Proceedings of Acoustic Society of Japan Spring Meeting 1\u20101\u20103 (March1986)."},{"key":"e_1_2_1_6_2","unstructured":"Watanukiet al.Comparative study of DP and HMM for speaker\u2010independent isolated word recognition. Proceedings of Acoustic Society of Japan Spring Meeting 1\u20104\u201014 (March1985)."},{"key":"e_1_2_1_7_2","unstructured":"OkochiandNishimura.Modified Markov Model with Embedded State\u2010Distribution for Speech Recognition. Proceedings of the 31st Meeting of the Information Processing Society of Japan 3N\u20103 (March1985)."},{"key":"e_1_2_1_8_2","unstructured":"Watanukiet al.Speaker\u2010independent isolated word recognition using Markov model. Proceedings of the Acoustic Soc. Japan Fall Meeting 2\u20104\u201019 (Sept.1985)."},{"issue":"1","key":"e_1_2_1_9_2","first-page":"155","article-title":"Stochastic DP and statistical methods for speaker\u2010independent English word recognition","volume":"70","author":"Nakagawa S.","year":"1987","journal-title":"I.E.I.C.E. Trans. D"},{"key":"e_1_2_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1983.1164211"},{"key":"e_1_2_1_11_2","first-page":"149","article-title":"Fast and Adaptive Technique for Isolated Word Recognition","volume":"80","author":"Fujizaki","year":"1980","journal-title":"Acoustics Society of Japan"},{"key":"e_1_2_1_12_2","doi-asserted-by":"crossref","unstructured":"D. K.Burton J. T.Buck andJ. E.Shore.A generalization of isolated word recognition using vector quantization. Proc. ICASSP'83 pp.1021\u20131024(1983).","DOI":"10.1109\/ICASSP.1983.1171915"},{"key":"e_1_2_1_13_2","unstructured":"Sugawaraet al.Speech Recognition Using Markov Model with Multiple Labels. Proceedings of the 29th Meeting of Inform. Proc. Soc. Japan 4\u20136 (1984)."},{"key":"e_1_2_1_14_2","doi-asserted-by":"crossref","unstructured":"K.Sugawara M.Nishimura T.Toshioka M.Okochi andT.Kaneko.Isolated word recognition using hidden Markov models. Proc. ICASSP'85 pp.1\u20134(March1985).","DOI":"10.1109\/ICASSP.1985.1168452"},{"key":"e_1_2_1_15_2","unstructured":"Watanukiet al.IBM PC\u2010based speaker\u2010independent word recognition using N\u2010segment label histogram method. Proceedings of Acoustics Society of Japan Fall Meeting 3\u20103\u20109 (Oct.1986)."},{"issue":"12","key":"e_1_2_1_16_2","first-page":"936","article-title":"Speech Recognition Based on Hidden Markov Model","volume":"42","author":"Okochi M.","year":"1986","journal-title":"Journal of Acoust. Soc. Japan"},{"issue":"1","key":"e_1_2_1_17_2","first-page":"78","article-title":"Speaker\u2010independent Isolated Word Recognition Using Dictionary of Local Peaks","volume":"68","author":"Matsumoto","year":"1985","journal-title":"I.E.I.C.E. Trans. C"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690200703","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690200703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T15:47:56Z","timestamp":1737215276000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690200703"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1989,1]]},"references-count":16,"journal-issue":{"issue":"7","published-print":{"date-parts":[[1989,1]]}},"alternative-id":["10.1002\/scj.4690200703"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690200703","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]]}}}