This paper presents a novel application of convolutional neural networks (CNNs) for the task of acoustic scene classification (ASC). We here propose the use of a CNN trained to classify short sequences of audio, represented by their log-mel spectrogram. We also introduce a training method that can be used under particular circumstances in order to make full use of small datasets. The proposed system is tested and evaluated on three different ASC datasets and compared to other state-of-the-art systems which competed in the “Detection and Classification of Acoustic Scenes and Events” (DCASE) challenges held in 20161 and 2013. The best accuracy scores obtained by our system on the DCASE 2016 datasets are 79.0% (development) and 86.2% (evaluation), which constitute a 6.4% and 9% improvements with respect to the baseline system. Finally, when tested on the DCASE 2013 evaluation dataset, the proposed system manages to reach a 77.0% accuracy, improving by 1% the challenge winner's score.
A convolutional neural network approach for acoustic scene classification / Valenti, Michele; Squartini, Stefano; Diment, Aleksandr; Parascandolo, Giambattista; Virtanen, Tuomas. - ELETTRONICO. - 2017-:(2017), pp. 1547-1554. (Intervento presentato al convegno 2017 International Joint Conference on Neural Networks, IJCNN 2017 tenutosi a usa nel 2017) [10.1109/IJCNN.2017.7966035].
A convolutional neural network approach for acoustic scene classification
Valenti, Michele;Squartini, Stefano;
2017-01-01
Abstract
This paper presents a novel application of convolutional neural networks (CNNs) for the task of acoustic scene classification (ASC). We here propose the use of a CNN trained to classify short sequences of audio, represented by their log-mel spectrogram. We also introduce a training method that can be used under particular circumstances in order to make full use of small datasets. The proposed system is tested and evaluated on three different ASC datasets and compared to other state-of-the-art systems which competed in the “Detection and Classification of Acoustic Scenes and Events” (DCASE) challenges held in 20161 and 2013. The best accuracy scores obtained by our system on the DCASE 2016 datasets are 79.0% (development) and 86.2% (evaluation), which constitute a 6.4% and 9% improvements with respect to the baseline system. Finally, when tested on the DCASE 2013 evaluation dataset, the proposed system manages to reach a 77.0% accuracy, improving by 1% the challenge winner's score.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
