Conference paper

EGOROVA Ekaterina, VESELÝ Karel, KARAFIÁT Martin, JANDA Miloš and ČERNOCKÝ Jan. Manual and Semi-Automatic Approaches to Building a Multilingual Phoneme Set. In: Proceedings of ICASSP 2013. Vancouver: IEEE Signal Processing Society, 2013, pp. 7324-7328. ISBN 978-1-4799-0355-9.
Publication language:english
Original title:Manual and Semi-Automatic Approaches to Building a Multilingual Phoneme Set
Title (cs):Manuální a poloautomatické přístupy k tvorbě multilingvální fonémové sady
Pages:7324-7328
Proceedings:Proceedings of ICASSP 2013
Conference:38th International Conference on Acoustics, Speech, and Signal Processing
Place:Vancouver, CA
Year:2013
ISBN:978-1-4799-0355-9
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2013/egorova_icassp2013_0007324.pdf [PDF]
Files: 
+Type Name Title Size Last modified
iconegorova_icassp2013_0007324.pdf221 KB2017-03-01 19:04:24
^ Select all
With selected:
Keywords
multilingual speech recognition, phoneme set mapping, phoneme confusion matrix
Annotation
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.
Abstract
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.
BibTeX:
@INPROCEEDINGS{
   author = {Ekaterina Egorova and Karel Vesel{\'{y}} and Martin
	Karafi{\'{a}}t and Milo{\v{s}} Janda and Jan
	{\v{C}}ernock{\'{y}}},
   title = {Manual and Semi-Automatic Approaches to Building a
	Multilingual Phoneme Set},
   pages = {7324--7328},
   booktitle = {Proceedings of ICASSP 2013},
   year = {2013},
   location = {Vancouver, CA},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4799-0355-9},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=10323}
}

Your IPv4 address: 54.158.31.149
Switch to IPv6 connection

DNSSEC [dnssec]