000 04076nas|a2200469 i 4500
005 20260818175617.0
008 290501s2000 th uzm rtt 00| a1eng d
035 _a.b11826848
099 9 _aAIT Diss. no. TC-00-01
100 0 _aTanee Demeechai
245 1 0 _aRecognition of syllables in tone languages
260 _aBangkok :
_bAsian Institute of Technology,
_c2000
300 _a91 p.
490 1 _aDissertation ;
_vno. TC-00-01
500 _aA dissertaion submitted in partial fulfillment of the requirements for the degree of Doctor of Engineering, School of Engineering and Technology
520 _aSpcech recognition of tone languages requires detection of the tone in addition to detection of the consonants and vowels of a syllable. Two approaches for recognition of tonal syllables have been proposed in the literature: joint detection and sequential detection. In joint detection, recognition is done by employing a hidden Markov model (HMM) of connected tonal syllasbles, in which the pitch and its time derivative are included into the feaure vector in addition to the phonetic features. In sequential detection, base syllables (syllables ignoring their tones) are recognized by using a HMM of connected base syllables only; the estimated syllable boundaries are then used for subsequent tone recognition in a separate HMM of tones. Joint detection performs better than sequential detection, but its computational complexity is higher. In this thesis, a new approach caled linked detection is proposed to achieve performance close to that of joint detection with computational complexity close to that of sequential detection. In linked detection, the recognition in the HMM of connected base sykkabkes is modified to periodically take into account also tonal likelihood computed form a HMM of tones. Likeed detection can provide performance that is comparable to the performance of joint detection and superior to that of sequential detection. For a large vocabulary task, the computational complexity of linked detection is much lower than that of joint detection while it is only slightly higher than that of sequential detection. In our experiment on recognition of 173 Thai-language syllables, the worst recognition rate obtained from sequential detection is 72% This result is comparable to results of the IBM Mandarin Call Home system (LIU et al., 1996), where a syllable recognition rate of 50% is reported for an experiment, in which the speech data are conversational telephone speech data and a word-pair language model is applied so that the perplexity is 15.
502 _aThesis (Ph.D.) - Asian Institute of Technology
650 1 0 _aTone (Phonetics)
650 1 0 _aSpeech perception
650 1 0 _aSpeech processing systems
700 1 _aMakelainen, Kimmo,
_eChairperson
700 1 _aSadanada, Ramakoti,
_eExamination committee
700 1 _aAhmed, Kazi Mohiuddin,
_eExamination Committee
700 1 _aRajatheva, R.M.A.P,
_eExamination Committee
700 1 _aLee, Chin-Hui,
_eExamination committee
710 2 _aRoyal Thai Govenment (RTG),
_eScholarship Donor
810 2 _aAsian Institute of Technology.
_tDissertation ;
_vno. TC-00-01
856 _3Full-Text
_uhttp://203.159.5.9/ait-thesis/detail.php?q=B00038
907 _a.b11826848
_bmnait
_cu
902 _a240507
998 _b0
_c010529
_dm
_ea
_fu
_g0
945 _lmnait
945 _lmnait
945 _lmnarc
942 _c22
942 _c40
942 _c20
909 _aBarcode : 30050120565600
_bCREATED : 2012-08-31
_cRECORD # : i12691859
_dLPATRON : 1015151
_eLCHKIN : 2018-07-07
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 1
_jTOT RENEW : 0
909 _aBarcode : 30050120235238
_bCREATED : 2016-03-29
_cRECORD # : i12911112
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
909 _aBarcode : 30050211023725
_bCREATED : 2022-02-02
_cRECORD # : i13361703
_dLPATRON : 0
_eLCHKIN : -
_f# RENEWALS : 0
_g# OVERDUE : 0
_hIUSE3 : 0
_iTOT CHKOUT : 0
_jTOT RENEW : 0
999 _c98000
_d98000