Evaluation of a novel fuzzy sequential pattern recognition tool (fuzzy elastic matching machine) and its applications in speech and handwriting recognition

Abstract

Sequential pattern recognition has long been an important topic of soft computing research with a wide area of applications including speech and handwriting recognition. In this paper, the performance of a novel fuzzy sequential pattern recognition tool named “Fuzzy Elastic Matching Machine” has been investigated. This tool overcomes the shortcomings of the HMM including its inflexible mathematical structure and inconsistent mathematical assumptions with imprecise input data. To do so, “Fuzzy Elastic Pattern” was introduced as the basic element of FEMM. It models the elasticity property of input data using fuzzy vectors. A sequential pattern such as a word in speech or a piece of writing is treated as a sequence of parts in which each part has an elastic nature (i.e. can skew or stretch depending on the speaker/writer's style). To present FEMM as a sequential pattern recognition tool, three basic problems, including evaluation, assignment, and training problems, were defined and their solutions were presented for FEMMs. Finally, we implemented FEMM for speech and handwriting recognition on some large databases including TIMIT database and Dr. Kabir's Persian handwriting database. In speech recognition, FEMM achieved 71% and 75.5% recognition rates in phone and word recognition, respectively. Also, 75.9% recognition accuracy was obtained in Persian handwriting recognition. The results indicated 18.2% higher recognition speed and 9–16% more immunity to noise in speech recognition in addition to 5% higher recognition rate in handwriting recognition compared to the HMM.