RT Conference Proceedings
T1 Deep Maxout Networks applied to Noise-Robust Speech Recognition
A1 Calle Silos, Fernando de la
A1 Gallardo Antolín, Ascensión
A1 Peláez Moreno, Carmen
AB Deep Neural Networks (DNN) have become very popular for acoustic modeling due to the improvements found over traditional Gaussian Mixture Models (GMM). However, not many works have addressed the robustness of these systems under noisy conditions. Recently, the machine learning community has proposed new methods to improve the accuracy of DNNs by using techniques such as dropout and maxout. In this paper, we investigate Deep Maxout Networks (DMN) for acoustic modeling in a noisy automatic speech recognition environment. Experiments show that DMNs improve substantially the recognition accuracy over DNNs and other traditional techniques in both clean and noisy conditions on the TIMIT dataset.
PB Springer
SN 978-3-319-13622-6 (print)
SN 978-3-319-13623-3 (online)
SN 0302-9743 (print)
SN 1611-3349 (online)
YR 2014
FD 2014
LK https://hdl.handle.net/10016/21528
UL https://hdl.handle.net/10016/21528
LA eng
NO Proceedings of: IberSPEECH 2014 "VIII Jornadas en Tecnologías del Habla" and "IV Iberian SLTech Workshop". Las Palmas de Gran Canaria, Spain, November 19-21, 2014.
NO This contribution has been supported by an Airbus Defense and Space Grant (Open Innovation - SAVIER) and Spanish Government-CICYT project 2011-26807/TEC.
DS e-Archivo
RD 1 jul. 2024