Title: Bottleneck ANN: dealing with small amount of data in shift-MLLR adaptation
Other Titles: Bottleneck ANN: shift-MLLR adaptace pro malé množství dat
Authors: Zají­c, Zbyněk
Machlica, Lukáš
Müller, Luděk
Citation: ZAJÍC, Zbyněk; MACHLICA, Lukáš; MüLLER, Luděk. Bottleneck ANN: dealing with small amount of data in shift-MLLR adaptation. In: IEEE 11th international conference on signal processing. Beijing: IEEE Press, 2012, p. 507-510.
Issue Date: 2012
Publisher: IEEE Press
Document type: článek
URI: http://www.kky.zcu.cz/cs/publications/ZbynekZajic_2012_BottleneckANN
Keywords: ASR;adaptace;shift-MLLR;ANN;bottleneck
Keywords in different language: ASR;adaptation;shift-MLLR;ANN;bottleneck
Abstract: Článek popisuje řešení nedostatečného množství dat pro shift-MLLR adaptaci pomocí neuonové sítě bottelneck.
Abstract in different language: The aim of this work is to propose a refinement of the shift-MLLR (shift Maximum Likelihood Linear Regression) adaptation of an acoustics model in the case of limited amount of adaptation data, which can lead to ill-conditioned transformations matrices. We try to suppress the influence of badly estimated transformation parameters utilizing the bottleneck Artificial Neural Network (ANN). The ill-conditioned shift-MLLR transformation is propagated through a bottleneck ANN (suitably trained beforehand), and the output of the net is used as the new refined transformation. To train the ANN the well and the badly conditioned shift-MLLR transformations are used as outputs and inputs of ANN, respectively.
Rights: © Zbyněk Zajíc - Lukáš Machlica - Luděk Müller
Appears in Collections:Články / Articles (KKY)
Články / Articles (NTIS)

Files in This Item:
File Description SizeFormat 
ZbynekZajic_2012_BottleneckANN.pdfPlný text168,33 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/16950

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.