Vibrary: A Consumer-Trainable Music Tagging Utility

Hawley S, Bagley J, Porter B, Traynham D. Vibrary: A Consumer-Trainable Music Tagging Utility. In: AES Convention 147. Audio Engineering Society; 2019. Paper 562. Available from: https://aes.org/publications/elibrary-page/?id=20585

@inproceedings{Hawley2019_20585,
  author = {Hawley, Scott and Bagley, Jason and Porter, Brett and Traynham, Daisey},
  title = {{Vibrary: A Consumer-Trainable Music Tagging Utility}},
  booktitle = {AES Convention 147},
  note = {Paper 562},
  year = {2019},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20585}
}

TY  - CPAPER
TI  - Vibrary: A Consumer-Trainable Music Tagging Utility
AU  - Hawley, Scott
AU  - Bagley, Jason
AU  - Porter, Brett
AU  - Traynham, Daisey
T2  - AES Convention 147
M1  - Paper 562
PY  - 2019
DA  - 2019/10/06
UR  - https://aes.org/publications/elibrary-page/?id=20585
PB  - Audio Engineering Society
LA  - en
AB  - We present the engineering underlying a consumer application to help music industry professionals find audio clips and samples of personal interest within their large audio libraries typically consisting of heterogeneously-labeled clips supplied by various vendors. We enable users to train an indexing system using their own custom tags (e.g., instruments, genres, moods), by means of convolutional neural networks operating on spectrograms. Since the intended users are not data scientists and may not possess the required computational resources (i.e., Graphics Processing Units, GPUs), our primary contributions consist of (i) designing an intuitive user experience for a local client application to help users create representative spectrogram datasets, and (ii) "seamless" integration with a cloud-based GPU server for efficient neural network training.
ER  -