Speech-music discrimination using deep visual feature extractors

作者：

Highlights：

• CNNs provide state-of-the-art results in speech-music discrimination.

• Transfer learning can be used to transfer knowledge across different modalities.

• CNNs & transfer-learning can significantly reduce the training data requirements.

• Data augmentation and representation play important role when training audio-CNNs.

摘要

•CNNs provide state-of-the-art results in speech-music discrimination.•Transfer learning can be used to transfer knowledge across different modalities.•CNNs & transfer-learning can significantly reduce the training data requirements.•Data augmentation and representation play important role when training audio-CNNs.

论文关键词：CNNs,Speech-music discrimination,Transfer learning,Audio analysis

论文评审过程：Received 3 January 2018, Revised 11 May 2018, Accepted 12 May 2018, Available online 19 May 2018, Version of Record 4 August 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.05.016