ML Anthology

Audio Feature Learning with Triplet-Based Embedding Network

Xiaoyu Qi, Deshun Yang, Xiaoou Chen
AAAI 2017 pp. 4979-4980
doi:10.1609/AAAI.V31I1.11071 /aaai/2017/qi2017aaai-audio/

Abstract

We propose a triplet-based network for audio feature learning for version identification. Existing methods use hand-crafted features for a music as a whole while we learn features by a triplet-based neural network on segment-level, focusing on the most similar parts between music versions. We conduct extensive experiments and demonstrate our merits.

PDF AAAI Semantic Scholar

Cite

Text

Qi et al. "Audio Feature Learning with Triplet-Based Embedding Network." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.11071

Markdown

[Qi et al. "Audio Feature Learning with Triplet-Based Embedding Network." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/qi2017aaai-audio/) doi:10.1609/AAAI.V31I1.11071

BibTeX

@inproceedings{qi2017aaai-audio,
  title     = {{Audio Feature Learning with Triplet-Based Embedding Network}},
  author    = {Qi, Xiaoyu and Yang, Deshun and Chen, Xiaoou},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {4979-4980},
  doi       = {10.1609/AAAI.V31I1.11071},
  url       = {https://mlanthology.org/aaai/2017/qi2017aaai-audio/}
}