Loading...

Isolatedword recognition based on intelligent segmentation by using hybrid HTD-HMM

Kazemi, A. R ; Sharif University of Technology | 2011

674 Viewed
  1. Type of Document: Article
  2. Publisher: 2011
  3. Abstract:
  4. In recent years, IWR (Isolated Word Recognition) was one of the main concerns of speech processing. The challenging problems in this field appear when the database become so large or when we have a lot of word with similarly pronounce in the database. This paper introduces a general solution for a traditional problem in isolated similarly pronounced word recognition, especially in large databases. One the important problem of traditional IWR is referred to their segmentation algorithm, their methods were lacking in efficiency due to the following reasons: First, using equal segmentation is not at all intelligent at all and as a result, cannot produce accurate results; besides, utilizing manual segmentation based on events is not possible in large databases. In this paper, by introducing the intelligent segmentation based on HTD (Hierarchical Temporal Decomposition), we present a more satisfactory answer to these problems. Based on this method, at first by using TD algorithm we categorize words into some groups with the same number of segments and then by using HTD method, all words of each group will be segmented to the number of events of the biggest group in TD step and based on the phi functions and related events. Then these segments will be sent to HMM step. Experimental results show that the proposed method significantly improves the recognition accuracy in comparison with recognition based on traditional segmentation
  5. Keywords:
  6. General solutions ; HMM ; HTD ; Intelligent segmentation ; Isolated word recognition ; Large database ; Manual segmentation ; Recognition accuracy ; Segmentation algorithms ; Temporal decomposition ; Word recognition ; Algorithms ; Database systems ; Speech processing ; Telecommunication ; Vocabulary control ; Speech recognition
  7. Source: International Conference on Circuits, Systems, Signal and Telecommunications - Proceedings, 21 October 2010 through 23 October 2010 ; October , 2011 , Pages 38-41 ; 9789604742714 (ISBN)
  8. URL: http://dl.acm.org/citation.cfm?id=1959711