{"title":"A k-climax neighbors policy based viterbi decoding for large vocabulary mandarin speech recognition","authors":"Pei Zhao, Xihong Wu","doi":"10.1109/CINC.2010.5643797","DOIUrl":null,"url":null,"abstract":"In this paper, we apply the k-climax neighbors (k-CN) policy derived from the Bayesian Ying-Yang (BYY) learning framework to Viterbi decoding for Hidden Markov Model based large vocabulary mandarin speech recognition, to adaptively obtain a more precise state decision boundary in the decoding phase. When calculating the posterior probability for each state on a given frame, k Gaussian components from these states are selected by the k-CN policy as the most reliable descriptions, which make the decision boundaries among the competitive candidate states more precise. The experimental results show that a 2.1% relative reduction of the character error rate is achieved on Hub-4 test by adopting the proposed approach.","PeriodicalId":227004,"journal":{"name":"2010 Second International Conference on Computational Intelligence and Natural Computing","volume":"48 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 Second International Conference on Computational Intelligence and Natural Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CINC.2010.5643797","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, we apply the k-climax neighbors (k-CN) policy derived from the Bayesian Ying-Yang (BYY) learning framework to Viterbi decoding for Hidden Markov Model based large vocabulary mandarin speech recognition, to adaptively obtain a more precise state decision boundary in the decoding phase. When calculating the posterior probability for each state on a given frame, k Gaussian components from these states are selected by the k-CN policy as the most reliable descriptions, which make the decision boundaries among the competitive candidate states more precise. The experimental results show that a 2.1% relative reduction of the character error rate is achieved on Hub-4 test by adopting the proposed approach.