Publication Details
Discriminative Acoustic Language Recognition via Channel-Compensated GMM Statistics
Strasheim Albert (USB)
Hubeika Valiantsina, Ing. (DCGM FIT BUT)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
acoustic language recognition, intersession variability compensation, discriminative training
The paper is on Discriminative Acoustic Language Recognition via Channel-Compensated GMM Statistics. The results are reported on NIST LRE'07.
We propose a novel design for acoustic feature-based automatic spoken language recognizers. Our design is inspired by recent advances in text-independent speaker recognition, where intraclass variability is modeled by factor analysis in Gaussian mixture model (GMM) space. We use approximations to GMMlikelihoods which allow variable-length data sequences to be represented as statistics of fixed size. Our experiments on NIST LRE'07 show that variability-compensation of these statistics can reduce error-rates by a factor of three. Finally, we show that further improvements are possible with discriminative logistic regression training.
@INPROCEEDINGS{FITPUB9042, author = "Niko Br{\"{u}}mmer and Albert Strasheim and Valiantsina Hubeika and Pavel Mat\v{e}jka and Luk\'{a}\v{s} Burget and Ond\v{r}ej Glembek", title = "Discriminative Acoustic Language Recognition via Channel-Compensated GMM Statistics", pages = "2187--2190", booktitle = "Proc. Interspeech 2009", journal = "Proceedings of Interspeech - on-line", number = 9, year = 2009, location = "Brighton, GB", publisher = "International Speech Communication Association", ISBN = "978-1-61567-692-7", ISSN = "1990-9772", language = "english", url = "https://www.fit.vut.cz/research/publication/9042" }