Gallardo Antolín, AscensiónMontero Martínez, Juan Manuel2020-12-222020-12-222019Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 [Proceedings]. ISCA, 2019, Pp. 216-220https://hdl.handle.net/10016/31660Proceeding of: Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019Cognitive Load (CL) refers to the amount of mental demand that a given task imposes on an individual's cognitive system and it can affect his/her productivity in very high load situations. In this paper, we propose an automatic system capable of classifying the CL level of a speaker by analyzing his/her voice. Our research on this topic goes into two main directions. In the first one, we focus on the use of Long Short-Term Memory (LSTM) networks with different weighted pooling strategies for CL level classification. In the second contribution, for overcoming the need of a large amount of training data, we propose a novel attention mechanism that uses the Kalinli's auditory saliency model. Experiments show that our proposal outperforms significantly both, a baseline system based on Support Vector Machines (SVM) and a LSTM-based system with logistic regression attention model.5eng© 2019 ISCACognitive loadSpeechLSTMWeigthed poolingAuditory saliencyAttention modelconference paperElectrónicaTelecomunicacioneshttps://doi.org/10.21437/Interspeech.2019-1603open access216220Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019 [Proceedings]CC/0000030601