speaker identiﬁcation ◦ emotion classiﬁcation ◦ accent recognition ◦ music genre classiﬁcation ◦ language identiﬁcation • single channel • 16 kHz sampling rate Meta data • number of classes (is greater than 2 and less than 100) • number of training instances (varies from hundreds to thousands) • time budget (is 1800 seconds for all the datasets) 2 Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
from pretrained model trained on data01 • optimizer: SGD ◦ lr: 0.01 ◦ momentum: 0.9 ◦ decay: 1e-06 • batch size: 32 Compute the validation score every 5 epochs and resume training if it is not the highest • the ratio of training and validation data is 9:1 Stop training when the remaining time is less than 0.125 * time_budget 8 Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
pretrained model • data augmentation Unsuccessful work • complex network architecture like EﬃcientNet [Tan & Le, '19] Future work • automated data augmentation Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.
On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras." In arXiv, 2017. DeVries, T., and Taylor G. W., "Improved Regularization of Convolutional Neural Networks with Cutout." In arXiv, 2017. Tan, M., and Le, Q. V., "EﬃcientNet: Rethinking Model Scaling for Convolutional Neural Networks." In Proceedings of ICML, pp. 6105-6114, 2019. Zhang, H., Cisse, M., Dauphin, Y. N., and Lopez-Paz, D., "mixup: Beyond Empirical Risk Minimization." In Proceedings of ICLR, 2018. Copyright (C) 2019 NS Solutions Corporation, All Rights Reserved.