Dept. of Electr. Eng., National Taiwan Univ.Shen, Jia-LinJia-LinShenWang, Hsin-MinHsin-MinWangBai, Bo-RenBo-RenBaiLIN-SHAN LEE2007-04-192018-07-062007-04-192018-07-061994-0415206149http://ntur.lib.ntu.edu.tw//handle/246246/2007041910032488https://www.scopus.com/inward/record.uri?eid=2-s2.0-0344493149&doi=10.1109%2fICASSP.1994.389701&partnerID=40&md5=23dd7c9d0243d86b2347cf0aae1783a7This paper presents an initial study to perform Iarge-vocabuIary continuous Mandarin speech recognition based on a Segmental Probability Model(SPM) approach. SPM was first proposed for recognition of isolated Mandarin syllables, in which every syllable must be equally segmented before recognition. Therefore, A concatenated syllable matching algorithm in place of the conventional Viterbi search algorithm is therefore introduced t o perform the recognition process based on SPM. In addition, a training procedure is also proposed to reestimate the SPM parameters for continuous speech. Preliminary simulation results indicate that significant improvements in both recognition rates and speed can be achieved as compared to the conventional HMM-based Viterbi search approaches. © 1994 IEEEapplication/pdf320059 bytesapplication/pdfen-US[SDGs]SDG4Signal processing; Viterbi algorithm; Continuous speech; Mandarin speech recognition; Mandarin syllable; Matching algorithm; Recognition process; Segmental probability model; Training procedures; Viterbi search algorithms; Speech recognitionconference paper10.1109/ICASSP.1994.3897012-s2.0-0344493149http://ntur.lib.ntu.edu.tw/bitstream/246246/2007041910032488/1/00389701.pdf