Reducing Model Complexity For DNN Based Large-scale Audio Classification

Abstract

Audio classification is the task of identifying the sound categories that are associated with a given audio signal. This paper presents an investigation on large-scale audio classification based on the recently released AudioSet database. AudioSet comprises 2 millions of audio samples from YouTube, which are human-annotated with 527 sound category labels. Audio classification experiments with the balanced training set and the evaluation set of AudioSet are carried out by applying different types of neural network models. The classification performance and the model complexity of these models are compared and analyzed. While the CNN models show better performance than MLP and RNN, its model complexity is relatively high and undesirable for practical use. We propose two different strategies that aim at constructing low-dimensional embedding feature extractors and hence reducing the number of model parameters. It is shown that the simplified CNN model has only 1/22 model parameters of the

Stats

• citations18
• S2 citations—
• github stars0
• HF likes0
• heat score9.59
• arxiv keywu2017reducing

Related papers

• A Deep Neural Network For Audio Classification With A Classifier Attention Mechanism (2020)0.00
• Variational Information Bottleneck For Effective Low-resource Audio Classification (2021)7.81
• Audio Concept Classification With Hierarchical Deep Neural Networks (2017)0.00
• Fully Dnn-based Multi-label Regression For Audio Tagging (2016)0.00
• Dynamic Convolutional Neural Networks As Efficient Pre-trained Audio Models (2023)0.00
• Effective Audio Classification Network Based On Paired Inverse Pyramid Structure And Dense MLP Block (2022)9.06
• How Low Can You Go? Reducing Frequency And Time Resolution In Current CNN Architectures For Music Auto-tagging (2019)4.52
• Convolutional Gated Recurrent Neural Network Incorporating Spatial Features For Audio Tagging (2017)13.23