Please use this identifier to cite or link to this item: http://ricaxcan.uaz.edu.mx/jspui/handle/20.500.11845/1714
Title: Training deep neural networks with non-uniform frame-level cost function for automatic speech recognition
Authors: Becerra, Aldonso
De la Rosa Vargas, José Ismael
González Ramírez, Efrén
Pedroza, David
Escalante, N. Iracemi
Issue Date: Oct-2018
Publisher: Springer
Abstract: The aim of this paper is to exhibit two new variations of the frame-level cost function for training a deep neural network in order to achieve better word error rates in speech recognition. Optimization methods and their minimization functions are underlying aspects to consider when someone is working on neural nets, and hence their improvement is one of the salient objectives of researchers, and this paper deals in part with such a situation. The first proposed framework is based on the concept of extropy, the complementary dual function of an uncertainty measure. The conventional cross entropy function can be mapped to a non-uniform loss function based on its corresponding extropy, enhancing the frames that have ambiguity in their belonging to specific senones. The second proposal makes a fusion of the presented mapped cross-entropy function and the idea of boosted cross-entropy, which emphasizes those frames with low target posterior probability.
URI: http://ricaxcan.uaz.edu.mx/jspui/handle/20.500.11845/1714
https://doi.org/10.48779/mz95-hr57
ISSN: 1380-7501
1573-7721
Other Identifiers: info:eu-repo/semantics/publishedVersion
Appears in Collections:*Documentos Académicos*-- M. en Ciencias del Proc. de la Info.

Files in This Item:
File Description SizeFormat 
26_Becerra_DelaRosa MTAP P1 2018.pdfBecerra_DelaRosa MTAP 2018495,86 kBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons