Publication Details
Manual and Semi-Automatic Approaches to Building a Multilingual Phoneme Set
Veselý Karel, Ing., Ph.D. (DCGM)
Karafiát Martin, Ing., Ph.D. (DCGM)
Janda Miloš, Ing.
Černocký Jan, prof. Dr. Ing. (DCGM)
multilingual speech recognition, phoneme set mapping, phoneme confusion matrix
This articles describes a comparison between manual and semi-automatic approaches to building a multilingual phoneme set. The two approaches were compared in cases of 1) a multilingual system with abundant data for all the languages, 2) multilingual systems excluding target language 3) multilingual systems with small amount of data for target languages. The work shows that careful choice of merging methods can help improve recognition of languages with no or little training data and reasonably reduce multilingual phoneme set without losing a lot of accuracy.
The paper addresses manual and semi-automatic approaches to building a multilingual phoneme set for automatic speech recognition. The first approach involves mapping and reduction of the phoneme set based on IPA and expert knowledge, the later one involves phoneme confusion matrix generated by a neural network. The comparison is done for 8 languages selected from GlobalPhone on three scenarios: 1) multilingual system with abundant data for all the languages, 2) multilingual systems excluding target language 3) multilingual systems with small amount of data for target languages. For 3), the multilingual system brought improvement for languages close enough to the others in the set.
@inproceedings{BUT103490,
author="Ekaterina {Egorova} and Karel {Veselý} and Martin {Karafiát} and Miloš {Janda} and Jan {Černocký}",
title="Manual and Semi-Automatic Approaches to Building a Multilingual Phoneme Set",
booktitle="Proceedings of ICASSP 2013",
year="2013",
pages="7324--7328",
publisher="IEEE Signal Processing Society",
address="Vancouver",
isbn="978-1-4799-0355-9",
url="https://www.fit.vut.cz/research/publication/10323/"
}