Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4973713 | Computer Speech & Language | 2017 | 16 Pages |
Abstract
Multilingual training of neural networks has proven to be simple yet effective way to deal with multilingual training corpora. It allows to use several resources to jointly train a language independent representation of features, which can be encoded into low-dimensional feature set by embedding narrow bottleneck layer to the network. In this paper, we analyze such features on the task of spoken language recognition (SLR), focusing on practical aspects of training bottleneck networks and analyzing their integration in SLR. By comparing properties of mono and multilingual features we show the suitability of multilingual training for SLR. The state-of-the-art performance of these features is demonstrated on the NIST LRE09 database.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
Radek Fér, Pavel MatÄjka, FrantiÅ¡ek Grézl, OldÅich Plchot, Karel Veselý, Jan Honza Äernocký,