emPhon : Morphologically sensitive open-source phonetic transcriber

Kulcsár Virág and Lévai Dániel: emPhon : Morphologically sensitive open-source phonetic transcriber.

[thumbnail of msznykonf_017_053-061.pdf]
Preview
Cikk, tanulmány, mű
msznykonf_017_053-061.pdf

Download (615kB) | Preview

Abstract

We propose a new emtsv module which can provide phonetic transcription based on the emMorph state-of-the-art morphological analyzer. In the first part of the paper, we present the motivation, the main problem and the method we are using to leverage Hungarian phonetic transcription with the use of morphological analyses. The second part is about evaluation both intrinsically and extrinsically – we evaluate our transcriber based on the IPA transcriptions of Wiktionary and as part of a speech synthesizer system. The code and models are fully open-source and are available under LGPL 3.0 license at https://github.com/levaid/emPhon.

Item Type: Conference or Workshop Item
Heading title: Transzkripció, transzliteráció
Journal or Publication Title: Magyar Számítógépes Nyelvészeti Konferencia
Date: 2021
Volume: 17
ISBN: 978-963-306-781-9
Page Range: pp. 53-61
Language: English
Event Title: Magyar számítógépes nyelvészeti konferencia (17.) (2021) (Szeged)
Related URLs: http://acta.bibl.u-szeged.hu/73340/
Uncontrolled Keywords: Nyelvészet - számítógép alkalmazása, Morfológia, Fonetika, Átírás
Additional Information: Bibliogr.: p. 60-61. és a lábjegyzetekben ; összefoglalás angol nyelven
Subjects: 01. Natural sciences
01. Natural sciences > 01.02. Computer and information sciences
06. Humanities
06. Humanities > 06.02. Languages and Literature
Date Deposited: 2021. Sep. 28. 10:42
Last Modified: 2022. Nov. 08. 11:49
URI: http://acta.bibl.u-szeged.hu/id/eprint/73357

Actions (login required)

View Item View Item