00000ctm a22000004a 4500 UP-99796217611306122 Buklod 20230215105418.0 m |o d | ta 140609s xx d r |||| u| (iLib)UPD-00221205160 DENGII rda eng DMLUC LG 995 2014 E64 L34 Laguna, Ann Franchesca author. Philippine language identification using acoustic, phonotactic and prosodic approaches Ann Franchesca Laguna. Quezon City xxii, 129 leaves College of Engineering, University of the Philippines Diliman illustrations 2014. 300 ## 28 cm text rdacontent unmediated rdamedia volume rdacarrier Thesis (M.S. Electrical Engineering)--University of the Philippines, Diliman. An Automatic Spoken Language Identification (LID) system recognizes the language of a speech utterance. An LID system has not been previously designed for Philippine languages because of insufficient recorded speech data. The Philippine Language Database (PLD) collected by the Digital Signal Processing (DSP) Laboratory is used for this research. Three LID approaches, namely acoustic, phonotactic, and prosodic approaches are explored for this research. For the acoustic approach, Gaussian Mixture Model (GMM) using MFCC, PLP, SDC and LPC are used to discriminate between the languages. The pitch rhythmic, and energy based features are explored for the prosodic approach. A Phone Recognition followed by Language Modelling (PRLM) and Parallel Phone Recognition followed by Language Modelling (PPRLM) are used for the phonotactic approach. The acoustic approach showed the best results for the Philippine LID system 48.08% for the seven language test, and 92.23% for Tagalog and Hiligaynon pair-wise language test. Tagalog, Cebuano, Bicolano and Hiligaynon provided the best recognition rate among the languages at 80.56%, 80.26%, 78.26%, and 60.87% respectively. A PLP GMM-EM with 32 mixtures was found to be the optimal acoustic LID system for Philippine speech. The created system is best suited for language verification or for language identification systems with small number of target languages that are closely related such as Philippine languages. Speech processing systems. Automatic speech recognition. Spoken Language Identification (LID). Filipino speech corpus. Thesis FI UP UPD DARCHIVES LG 995 2014 E64 L34 UPD DENG-II LG 995 2014 E64 L34 Thesis