@inproceedings{bacc10e3cc654cf1b20504e94b5e09cb,
title = "Environmental Sound Recognition Using Masked Conditional Neural Networks",
abstract = "Neural network based architectures used for sound recognition are usually adapted from other application domains, which may not harness sound related properties. The ConditionaL Neural Network (CLNN) is designed to consider the relational properties across frames in a temporal signal, and its extension the Masked ConditionaL Neural Network (MCLNN) embeds a filterbank behavior within the network, which enforces the network to learn in frequency bands rather than bins. Additionally, it automates the exploration of different feature combinations analogous to handcrafting the optimum combination of features for a recognition task. We applied the MCLNN to the environmental sounds of the ESC-10 dataset. The MCLNN achieved competitive accuracies compared to state-of-the-art convolutional neural networks and hand-crafted attempts.",
keywords = "Boltzmann machine, CLNN, CRBM, Conditional RBM, Conditional neural network, DNN, Deep neural network, ESR, Environmental sound recognition, MCLNN, Masked Conditional neural network, RBM",
author = "Fady Medhat and Chesmore, {Edwin David} and Robinson, {John Allen}",
year = "2017",
month = nov,
day = "5",
doi = "10.1007/978-3-319-69179-4_26",
language = "English",
isbn = "978-3-319-69178-7",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
pages = "373--385",
editor = "Wen-Chih Peng and Zhang, {Wei Emma} and Gao Cong and Aixin Sun and Chengliang Li",
booktitle = "Advanced Data Mining and Applications - 13th International Conference, ADMA 2017, Proceedings",
note = "Advanced Data Mining and Applications, ADMA ; Conference date: 05-11-2017",
}