University of the Basque Country (EHU) Systems for the 2011 NIST Language Recognition Evaluation
作者： Mikel Penagarikano , Luis Javier Rodriguez-Fuentes , German Bordel , Mireia Diez , Amparo Varona
DOI:
关键词: Czech 、 Average cost 、 Language recognition 、 Software 、 Natural language processing 、 Computer science 、 Artificial intelligence 、 Speech recognition 、 Set (abstract data type) 、 NIST 、 Measure (data warehouse) 、 Duration (project management)
摘要: This paper describes the systems developed by Software Technologies Working Group (http://gtts.ehu.es) of University Basque Country for 2011 NIST Language Recognition Evaluation. Four different (one primary and three contrastive) were submitted, consisting a fusion five subsystems: Linearized Eigenchannel GMM (LE-GMM) subsystem, an iVector subsystem phone-lattice-SVM subsystems based on publicly available BUT decoders Czech, Hungarian Russian. The four submitted identical except backend approach development dataset used to estimate parameters. Multiclass was performed separately each nominal duration. A set defined, including evaluation sets LRE07 LRE09 data provided 9 additional languages in LRE11. Systems evaluated 10 random partitions set, using one half estimating parameters other testing. average cost as defined LRE11 plan performance measure. system yielded actual 0.038 (±0.002), being Hindi-Urdu, far, most challenging pair, with 0.222.
参考文章(13)
Valiantsina Hubeika, Albert Strasheim, Niko Brümmer, Ondrej Glembek, Lukás Burget, Pavel Matejka, Discriminative Acoustic Language Recognition via Channel-Compensated GMM Statistics conference of the international speech communication association. pp. 2187- 2190 ,(2009)
Fadi Biadsy, Julia Bell Hirschberg, Daniel P. W. Ellis, Dialect and Accent Recognition using Phonetic-Segmentation Supervectors conference of the international speech communication association. pp. 745- 748 ,(2011) , 10.7916/D8P84MCW
Mikel Penagarikano, Luis Javier Rodriguez, German Bordel, Maider Zamalloa, Juan Pedro Uribe, University of the Basque Country + Ikerlan System for NIST 2008 Speaker Recognition Evaluation ,(2008)
Mikel Peñagarikano, Luis Javier Rodríguez, Germán Bordel, Mireia Díez, Amparo Varona, The Albayzin 2010 Language Recognition Evaluation conference of the international speech communication association. pp. 1529- 1532 ,(2011)
Niko Brummer, David Van Leeuwen, On calibration of language recognition scores 2006 IEEE Odyssey - The Speaker and Language Recognition Workshop. pp. 1- 8 ,(2006) , 10.1109/ODYSSEY.2006.248106
Roland Auckenthaler, Michael Carey, Harvey Lloyd-Thomas, Score Normalization for Text-Independent Speaker Verification Systems Digital Signal Processing. ,vol. 10, pp. 42- 54 ,(2000) , 10.1006/DSPR.1999.0360
F. S. Richardson, W. M. Campbell, Language recognition with discriminative keyword selection international conference on acoustics, speech, and signal processing. pp. 4145- 4148 ,(2008) , 10.1109/ICASSP.2008.4518567
Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Chih-Jen Lin, Xiang-Rui Wang, LIBLINEAR: A Library for Large Linear Classification Journal of Machine Learning Research. ,vol. 9, pp. 1871- 1874 ,(2008)
Pedro A Torres-Carrasquillo, Elliot Singer, Terry Gleason, Alan McCree, Douglas A Reynolds, Fred Richardson, Douglas Sturim, None, The MITLL NIST LRE 2009 language recognition system 2010 IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 4994- 4997 ,(2010) , 10.1109/ICASSP.2010.5495080
Niko Brummer, Lukas Burget, Jan Cernocky, Ondrej Glembek, Frantisek Grezl, Martin Karafiat, David A. van Leeuwen, Pavel Matejka, Petr Schwarz, Albert Strasheim, Fusion of Heterogeneous Speaker Recognition Systems in the STBU Submission for the NIST Speaker Recognition Evaluation 2006 IEEE Transactions on Audio, Speech, and Language Processing. ,vol. 15, pp. 2072- 2084 ,(2007) , 10.1109/TASL.2007.902870