Paper Info
Title
A Language Space Representation For Speech Recognition
Abstract
The number of languages for which speech recognition systems have become available is growing each year. This paper proposes to view languages as points in some rich space, termed language space, where bases are eigen-languages and a particular selection of the projection determines points. Such an approach could not only reduce development costs for each new language but also provide automatic means for language analysis. For the initial proof of the concept, this paper adopts cluster adaptive training (CAT) known for inducing similar spaces for speaker adaptation needs. The CAT approach used in this paper builds on the previous work for language adaptation in speech synthesis and extends it to Gaussian mixture modelling more appropriate for speech recognition. Experiments conducted on IARPA Babel program languages show that such language space representations can outperform language independent models and discover closely related languages in an automatic way.
Year
Venue
Keywords
2015
2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP)
language space, cluster adaptive training, babel
Field
DocType
ISSN
Factored language model,Speech synthesis,Cache language model,Computer science,Computational linguistics,Speech recognition,Language identification,Universal Networking Language,Artificial intelligence,Natural language processing,Constructed language,Language model
Conference
1520-6149
Citations 
PageRank 
References 
2
0.38
19
Authors
3
Name
Order
Citations
PageRank
Anton Ragni1989.06
Mark J. F. Gales23905367.45
Kate Knill324928.02