Please use this identifier to cite or link to this item:https://hdl.handle.net/20.500.12259/50513
Type of publication: Straipsnis recenzuojamoje užsienio tarptautinės konferencijos medžiagoje / Article in peer-reviewed foreign international conference proceedings (P1d)
Field of Science: Informatika / Computer science (N009)
Author(s): Raškinis, Gailius;Kazlauskienė, Asta
Title: From speech corpus to intonation corpus : clustering phrase pitch contours of Lithuanian
Is part of: NODALIDA 2013 : proceedings of the 19th Nordic conference of computational linguistics, May 22–24, 2013, Oslo university, Norway / eds. Stephan Oepen, Kristin Hagen, Janne Bondi Johannesse. Linköping : Linköping University Electronic Press, 2013
Extent: p. 353-363
Date: 2013
Series/Report no.: (NEALT Proceedings, Vol. 16 1650-3740)
Note: ISSN (print): 1650-3686
Keywords: Garsynas;Intonacija;Prozodija;Pagrindinis tonas;K-vidurkių klasterizcija;Lietuvių kalba;Lietuvių kalbos intonacijų garsynas;Dinaminis laiko ištiesinimas;Intonation corpus;Prosody;Pitch;Syllable;Dynamic time warping;Lithuanian intonation corpus
ISBN: 9789175195896
Abstract: This paper presents our research in preparation to compile a Lithuanian intonation corpus. The main objective of this research was to discover characteristic patterns of Lithuanian intonation through clustering of pitch contours of intermediate intonation phrases. The paper covers the set of procedures that were used to extend an ordinary speech corpus to make it suitable for intonation analysis. The process of intonation analysis included pitch extraction, pitch normalization, estimation of the representative frequency of a syllable, measurement of an inter-phrase similarity, k-means phrase clustering, and visualisation of clustering results. These computational procedures were applied to 23 hours of read speech containing 41417 phrases. The clustering results revealed some interesting intonation patterns of Lithuanian that could be related to the well known linguistic-prosodic phenomena. Language-independence is an important feature of computational procedures covered by this paper. If speech waveforms and the knowledge of phone and phrase boundaries are given, these procedures can be used for the analysis of intonation of other languages
Internet: http://www.ep.liu.se/ecp/085/032/ecp1385032.pdf
http://www.ep.liu.se/ecp/085/032/ecp1385032.pdf
http://vddb.library.lt/obj/LT-eLABa-0001:J.04~2013~ISSN_1736-6305.V_16.PG_353-363
Affiliation(s): Informatikos fakultetas
Sistemų analizės katedra
Vytauto Didžiojo universitetas
Appears in Collections:Universiteto mokslo publikacijos / University Research Publications

Files in This Item:
marc.xml8.68 kBXMLView/Open

MARC21 XML metadata

Show full item record

Page view(s)

130
checked on Nov 2, 2019

Download(s)

10
checked on Nov 2, 2019

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.