Publication Details
Discriminative Semi-supervised Training for Keyword Search in Low Resource Languages
Ng Tim (Raytheon BBN)
Grézl František, Ing., Ph.D. (DCGM FIT BUT)
Karakos Damianos (Raytheon BBN)
Tsakalidis Stavros (Raytheon BBN)
Nguyen Long (Raytheon BBN)
Schwartz Richard (Raytheon BBN)
semi-supervised training, low resource languages, keyword spotting
This article is about Discriminative Semi-supervised Training for Keyword Search in Low Resource Languages.
In this paper, we investigate semi-supervised training for low resource languages where the initial systems may have high error rate ( 70.0% word eror rate). To handle the lack of data, we study semi-supervised techniques including data selection, data weighting, discriminative training and multilayer perceptron learning to improve system performance. The entire suite of semi-supervised methods presented in this paper was evaluated under the IARPA Babel program for the keyword spotting tasks. Our semi-supervised system had the best performance in the OpenKWS13 surprise language evaluation for the limited condition. In this paper, we describe our work on the Turkish and Vietnamese systems.
@INPROCEEDINGS{FITPUB10508, author = "Roger Hsiao and Tim Ng and Franti\v{s}ek Gr\'{e}zl and Damianos Karakos and Stavros Tsakalidis and Long Nguyen and Richard Schwartz", title = "Discriminative Semi-supervised Training for Keyword Search in Low Resource Languages", pages = "440--445", booktitle = "Proceedings of ASRU 2013", year = 2013, location = "Olomouc, CZ", publisher = "IEEE Signal Processing Society", ISBN = "978-1-4799-2755-5", language = "english", url = "https://www.fit.vut.cz/research/publication/10508" }