Calle Silos, Fernando de laGallardo Antolín, AscensiónPeláez Moreno, Carmen2015-09-042014Navarro Mesa, J. L., et al. (eds.) (2014). Advances in Speech and Language Technologies for Iberian Languages: Second International Conference, IberSPEECH 2014, Las Palmas de Gran Canaria, Spain, November 19-21, 2014. Proceedings. (pp. 109-118). (Lecture Notes in Computer Science; 8854). Springer International Publishing.978-3-319-13622-6 (print)978-3-319-13623-3 (online)0302-9743 (print)1611-3349 (online)https://hdl.handle.net/10016/21528Proceedings of: IberSPEECH 2014 "VIII Jornadas en Tecnologías del Habla" and "IV Iberian SLTech Workshop". Las Palmas de Gran Canaria, Spain, November 19-21, 2014.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.10application/pdfeng© 2014 Springer International Publishing SwitzerlandNoise robustnessDeep neural networksDropoutDeep maxout networksSpeech recognitionDeep learningconference paperTelecomunicaciones10.1007/978-3-319-13623-3_12open access109118Advances in Speech and Language Technologies for Iberian Languages: Second International Conference, IberSPEECH 2014, Las Palmas de Gran Canaria, Spain, November 19-21, 2014. Proceedings.CC/0000022425