Konferensartikel

From speech corpus to intonation corpus: clustering phrase pitch contours of Lithuanian

Gailius Raškinis
Vytautas Magnus University, Kaunas, Lithuania

Asta Kazlauskienė
Vytautas Magnus University, Kaunas, Lithuania

Ladda ner artikel

Ingår i: Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013); May 22-24; 2013; Oslo University; Norway. NEALT Proceedings Series 16

Linköping Electronic Conference Proceedings 85:32, s. 353-363

NEALT Proceedings Series 16:32, p. 353-363

Visa mer +

Publicerad: 2013-05-17

ISBN: 978-91-7519-589-6

ISSN: 1650-3686 (tryckt), 1650-3740 (online)

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.

Nyckelord

Corpus; prosody; intonation; pitch; syllable; dynamic time warping; k-means clustering; Lithuanian

Referenser

Beckman; M. E.; Hirschberg; J.; and Shattuck-Hufnagel; S. (2005). The original ToBI system and the evolution of the ToBI framework. In S.-A. Jun (ed.) Prosodic Typology -- The Phonology of Intonation and Phrasing.

Boersma; P.; and Weenink; D. (2006). Praat: doing phonetics by computer [Computer program]. Version 4.4.26; retrieved 24 July 2006 from http://www.praat.org/

Hartigan; J. A.; Wong; M. A. (1979). Algorithm AS 136: A K-Means Clustering Algorithm. Journal of the Royal Statistical Society; Series C (Applied Statistics) 28(1):100–108.

Kundrotas; G. (2008). Lietuviu kalbos intonaciniu konturu fonetiniai požymiai (Phonetic features of Lithuanian intonation contours). Žmogus ir žodis. Didaktine lingvistika. Mokslo darbai; Vilnius; 10(1): 43-55.

Kundrotas; G. (2009). Lyginamoji lietuviu ir rusu kalbu intonaciniu sistemu analize (A comparative analysis of intonation systems of Lithuanian and Russian); Vilnius Pedagogical University.

Levow; G.-A. (2008). Automatic Prosodic Labeling with Conditional Random Fields and Rich Acoustic Features. In Proceedings of International Joint Conference on Natural Language Processing (IJCNLP); pages. 217-224.

Heggtveit; P. O.; Natvig; J. E. (2004). Automatic prosody labelling of read Norwegian. In Proceedings of the International Conference on Spoken Language Processing (ICSLP); vol. 4; pages 2741-2744.

Escudero-Mancebo; D.; Vizcaíno-Ortega; F.; González-Ferreras; C.; Vivaracho-Pascual; C.; Cabrera-Abreu; M.; Estebas-Vilaplana; E.; and Valenítn Cardeñoso-Payo; V. (2012). Multiclass Pitch Accent Classification for Assisting Manual Prosodic Labeling. In Proceedings of IberSPEECH 2012; pages 73-82.

Norkevicius; G.; Raškinis; G.; and Kazlauskiene; A. (2005). Knowledge-based graphemeto- phoneme conversion of Lithuanian words. In Proceedings of the 10th International Conference on Speech and Computer – Specom; Patras; Greece. pages 235–238.

Raškinis; G. (2000). Lietuviu liaudies dainu užrašymas muzikos simboliu sekomis (Automatic transcription of Lithuanian folk songs); Phd Thesis; Vytautas Magnus University.

Vaiciunas; A. (2006). Lietuviu kalbos statistiniu modeliu ir ju taikymo šnekos atpažinimui tyrimas; kai naudojami labai dideli žodynai (Investigation of Lithuanian statistic language models and of their application to speech recognition in case of very large vocabularies); Phd Thesis; Vytautas Magnus University.

Vereecken; H.; Martens; J.-P.; Grover; C.; Fackrell; J.; and Van Coile; B. (1998). Automatic prosodic labeling of 6 languages. In Proceedings of the 5th International Conference on Spoken Language Processing; Sidney Australia.

Vintsyuk; T. K. (1968). Speech discrimination by dynamic programming. Kibernetika; 4:81-88.

Young; S.; Evermann; G.; Kershaw; D.; Moore; G.; Odell; J.; Ollason; D.; Povey; D.; Valtchev; V.; and Woodland; P. (2002). The HTK Book (for HTK Version 3.2); Microsoft Corporation; Cambridge University Engineering Department; pages 22-44.

Xu; Y. (2004). Transmitting tone and intonation simultaneously - the parallel encoding and target approximation (PENTA) model. In Proceedings of the International Symposium on Tonal Aspects of Languages (TAL) - 2004; pages 215–220.

Wightman; C.; and Ostendorf; M. (1994) Automatic labeling of prosodic patterns; IEEE Transactions on Speech and Audio Processing; 2(4):469–481.

Citeringar i Crossref