Department of Computer Graphics and Multimedia

Events, Seminars

20.2.2012L.F. d'Haro: LID/SID - Research Stay at BUT
3.2.2012Viorela Ila: Fundamental Methodologies for Large-scale Robotic Applications
9.1.2012O. Plchot: Building a Robust Speaker Recognition System
4.1.2012M. Hannemann: Ping-pong decoding Combining forward and backward search
4.1.2012T. Mikolov: Language Modeling with Recurrent Neural Networks
2.12.2011M. Seeman: Poznatky z fyziologie zrakového aparátu pro zobrazování na monitorech
7.11.2011S. Rath: f-MLLR using QR decomposition
24.10.2011E. Egorova: Multilingual speech recogniser
10.10.2011O. Glembek: Brno276 system for NIST 2011 Language recognition evaluation
5.10.2011L.F.D'Haro: Introduction and past work in language identification
23.9.2011J. Navrátil: High-quality Shadows with Improved Paraboloid Mapping
23.9.2011M. Hradiš, I. Řezníček, K. Behúň: BUT@MediaEval2011
12.9.2011Sandro Cumani: Pair-wise SVM for speaker indentification
9.9.2011Niko Brümmer: Automatic differentiation for optimization
29.6.2011Karel Veselý: Phnrec reloaded
29.6.2011Shakti Rath: Acoustic region-specific feature space transformation for speaker adaptation
13.6.2011Miloš Janda: Speech recognition on GlobalPhone databases
7.6.2011R. Bednarik: Eye-tracking in Problem Solving: Interaction, User Modeling and Strategy Inference
9.5.2011Mehdi Soufifar: iVector approach to Phonotactic LRE
2.5.2011Karel Veselý: Large CTS corpora tandem features - The positives of TNet using GPGPU
18.4.2011Shakti Rath: F-MLLR and Region specific F-MLLR for Speaker Adaptation
25.3.2011Large-Scale Physics-Based Terrain Editing
25.3.2011M. Dubská, A, Herout, J. Havel: PClines - Line Detection Using Parallel Coordinates
25.3.2011M. Hradiš, P. Zemčík: Obrazové příznaky pro detekci objektů
25.3.2011M. Španěl, P. Kršek: Delaunay-based Vector Segmentation of Volumetric Medical Images
25.3.2011R.Juranek, P.Zemcik: Optimalizace extrakce příznaků v SIMD
7.3.2011O. Glembek: Discriminative training of i-vector extractor
25.2.2011Leoš Červený: ŠKODA AUTO VYUŽITÍ POČÍTAČOVÉ GRAFIKY, MOŽNOSTI SPOLUPRÁCE
23.2.2011Lukáš Burget: Recognizing a Million Voices: Low Dimensional Audio Representations for Speaker Identification
27.1.2011O. Yilmaz: SRE Experiments with Microphone and Interview I-Vector Extractor
10.1.2011Shakti Rath: Computationally Efficient Approach to Global and Acoustic class specific VTLN warping
20.12.2010David Martinez: Advances in language recognition during internship at Speech@FIT
3.12.2010M. Hradiš : Exploiting neighbors for faster scanning window detection in images
3.12.2010R. Juránek : FPGA Platform for Object Detection
22.10.2010M. Dubská: PClines - detekcia čiar pomocou paralelných súradníc
13.10.2010P. Matějka, O. Glembek, J. Pešán : Verifikace řečníka na mobilním telefonu v projektu MOBIO
1.10.2010M. Hradiš : PASCAL VOC a TRECVID SIN
1.10.2010T. Starka : Shadow volumes, odvrácená strana
6.9.2010Yonatan Vaizman: Schizophrenia and Depression - Evidence in Speech Prosody
1.9.2010Tomáš Mikolov: Recurrent neural network based language model
19.8.2010Michael Riley: Weighted Finite-state Transducers in Speech and Language Processing II
18.8.2010Michael Riley: Weighted Finite-state Transducers in Speech and Language Processing
21.7.2010Josef Kittler: Multiple kernel learning and feature space denoising with application to information retrieval from image and video databases
11.6.2010Manuel José Cabral dos S. Reis: Discrete Finite Frames and Robust Signal Representation and Reconstruction
4.6.2010František Grézl:Neural Net Based Features for Speaker Recognition
28.5.2010V. Beran, M. Šolony, P. Žák : Lokalizace kamery pomocí vizuálních markerů
12.3.2010R. Bendařík: Eye tracking and Usability - University of Eastern Finland
22.1.2010Mirko Hannemann: Similarity Measure for Detected OOVs based on Alignment Error Model
22.1.2010Stefan Kombrink: OOV Word Detection in TED Talks using a hybrid word/subword recognizer
18.1.2010Tomáš Mikolov: Character based language models

Your IPv4 address: 38.107.179.220
Switch to IPv6 connection

DNSSEC [dnssec]