The Journal of the Acoustical Society of Korea

The Acoustical Society of Korea (한국음향학회)
권호 표지

Automatic Detection of Korean Accentual Phrase Boundaries

  • Lee, Ki-Yeong (Dep. Of Electronic Communication Engineering in Kwandong University) ;
  • Song, Min-Suck (Dep. Of English Language and Literature in Kwandong University)
  • Published : 1999.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

Recent linguistic researches have brought into focus the relations between prosodic structures and syntactic, semantic or phonological structures. Most of them prove that prosodic information is available for understanding syntactic, semantic and discourse structures. But this result has not been integrated yet into recent Korean speech recognition or understanding systems. This study, as a part of integrating prosodic information into the speech recognition system, proposes an automatic detection technique of Korean accentual phrase boundaries by using one-stage DP, and the normalized pitch pattern. For making the normalized pitch pattern, this study proposes a method of modified normalization for Korean spoken language. For the experiment, this study employs 192 sentential speech data of 12 men's voice spoken in standard Korean, in which 720 accentual phrases are included, and 74.4% of the accentual phrase boundaries are correctly detected while 14.7% are the false detection rate.

Keywords

References

  1. Phonology and Syntax, E.O.Selkirk,
  2. Prosodic Phonology M.Nespor,;I.Vogel,
  3. Phonology Yearbook v.3 Intonational structure in Japanese and English M.Beckman,;J.Pierrehumbert,;J.Ohala,(ed.)
  4. IEEE Trans.Speech,Audio Processing v.2 no.4 Automatic labeling of prosodic patterns C.W.Wightman,;M.Ostendorf,
  5. Proc.of IEEE Int. Conf. ASSP Automatic reognition of intonational features C.W.Wightman,;M.Ostendorf,
  6. Proc.of ICSLP96 Automatic detection and segmentation of pronunciation variants in German speech corpora A.Kipp,;M.Wesenick,;F.Schiel,
  7. Proc.of IEEE Int.Conf.ASSP Prosodic phrase segmentation by pitch pattern clustering H.Shimodaira,;M.Nakai,
  8. Proc.of IEEE Int.Conf.ASSP Prosodic phrase segmentation by pitch pattern clustering H.Shimodaira,;M.Nakai,
  9. Proc.of the 12th Workshop for Speech Communication and Signal Processing Automatic recognition of sentence-final intonational patterns for Korean predicates Kiyoung Lee,;Minsuck Song,
  10. The Journal of the Acoustic Society of Korea v.14 no.4 Intonation conversion using the other speaker's excitation signal Kiyoung Lee,;Minsuck Song,
  11. Doctoral Dissertation The Phonetics and Phonology of Korean Prosody Sun-Ah Jun,
  12. Proc.of the 1994 Conference of HCI(Human and Computer Interface) A theoretical model of spoken language processing Minsuck Song,(et al.)
  13. Annual Report of Korea Telecom Research and Development Group A Study of Korean Prosody and Disourse for the Development of Speech Synthesis/Recognition System Kook Chung,(et al.)
  14. IEEE Trans. Acoustics, Speech and Signal Processing v.ASSP-32 no.2 The use of a one-stage dynamic programming algorithm for connected word recognition Hermann Ney,
  15. Digital Processing of Speech Signals L.R.Rabiner,;R.W.Schafer,