Semantic Scholar Open Access 2017 246 sitasi

Transfer Learning for Music Classification and Regression Tasks

Keunwoo Choi György Fazekas Mark B. Sandler Kyunghyun Cho

Abstrak

In this paper, we present a transfer learning approach for music classification and regression tasks. We propose to use a pre-trained convnet feature, a concatenated feature vector using the activations of feature maps of multiple layers in a trained convolutional network. We show how this convnet feature can serve as general-purpose music representation. In the experiments, a convnet is trained for music tagging and then transferred to other music-related classification and regression tasks. The convnet feature outperforms the baseline MFCC feature in all the considered tasks and several previous approaches that are aggregating MFCCs as well as low- and high-level music features.

Topik & Kata Kunci

Penulis (4)

K

Keunwoo Choi

G

György Fazekas

M

Mark B. Sandler

K

Kyunghyun Cho

Format Sitasi

Choi, K., Fazekas, G., Sandler, M.B., Cho, K. (2017). Transfer Learning for Music Classification and Regression Tasks. https://www.semanticscholar.org/paper/d09ad42cb4f991a6ddb282cd0cf3e4f0d408b275

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2017
Bahasa
en
Total Sitasi
246×
Sumber Database
Semantic Scholar
Akses
Open Access ✓