Drum Sample Retrieval from Mixed Audio via a Joint Embedding Space of Mixed and Single Audio Samples
×
Cite This
Citation & Abstract
W. Kim, and J. Nam, "Drum Sample Retrieval from Mixed Audio via a Joint Embedding Space of Mixed and Single Audio Samples," Paper 10390, (2020 October.). doi:
W. Kim, and J. Nam, "Drum Sample Retrieval from Mixed Audio via a Joint Embedding Space of Mixed and Single Audio Samples," Paper 10390, (2020 October.). doi:
Abstract: Sample-based music creation has become a mainstream practice. One of the key tasks in the creative process is searching desired samples in large collections. However, most commercial packages describe the samples using metadata, which is limited to explain subtle nuances in timbre and style. Inspired by music producers who often find instrument samples with a reference song, we propose a query-by-example scheme that takes mixed audio as a query and retrieves single audio samples. Our method is based on deep metric learning where a neural network is trained to locate single audio and their mixtures closely in the embedding space. We show that our model successfully retrieves single audio samples given mixed audio query in various evaluation scenarios.
@article{kim2020drum,
author={kim, wonil and nam, juhan},
journal={journal of the audio engineering society},
title={drum sample retrieval from mixed audio via a joint embedding space of mixed and single audio samples},
year={2020},
volume={},
number={},
pages={},
doi={},
month={october},}
@article{kim2020drum,
author={kim, wonil and nam, juhan},
journal={journal of the audio engineering society},
title={drum sample retrieval from mixed audio via a joint embedding space of mixed and single audio samples},
year={2020},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={sample-based music creation has become a mainstream practice. one of the key tasks in the creative process is searching desired samples in large collections. however, most commercial packages describe the samples using metadata, which is limited to explain subtle nuances in timbre and style. inspired by music producers who often find instrument samples with a reference song, we propose a query-by-example scheme that takes mixed audio as a query and retrieves single audio samples. our method is based on deep metric learning where a neural network is trained to locate single audio and their mixtures closely in the embedding space. we show that our model successfully retrieves single audio samples given mixed audio query in various evaluation scenarios.},}
TY - paper
TI - Drum Sample Retrieval from Mixed Audio via a Joint Embedding Space of Mixed and Single Audio Samples
SP -
EP -
AU - Kim, Wonil
AU - Nam, Juhan
PY - 2020
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2020
TY - paper
TI - Drum Sample Retrieval from Mixed Audio via a Joint Embedding Space of Mixed and Single Audio Samples
SP -
EP -
AU - Kim, Wonil
AU - Nam, Juhan
PY - 2020
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2020
AB - Sample-based music creation has become a mainstream practice. One of the key tasks in the creative process is searching desired samples in large collections. However, most commercial packages describe the samples using metadata, which is limited to explain subtle nuances in timbre and style. Inspired by music producers who often find instrument samples with a reference song, we propose a query-by-example scheme that takes mixed audio as a query and retrieves single audio samples. Our method is based on deep metric learning where a neural network is trained to locate single audio and their mixtures closely in the embedding space. We show that our model successfully retrieves single audio samples given mixed audio query in various evaluation scenarios.
Sample-based music creation has become a mainstream practice. One of the key tasks in the creative process is searching desired samples in large collections. However, most commercial packages describe the samples using metadata, which is limited to explain subtle nuances in timbre and style. Inspired by music producers who often find instrument samples with a reference song, we propose a query-by-example scheme that takes mixed audio as a query and retrieves single audio samples. Our method is based on deep metric learning where a neural network is trained to locate single audio and their mixtures closely in the embedding space. We show that our model successfully retrieves single audio samples given mixed audio query in various evaluation scenarios.
Authors:
Kim, Wonil; Nam, Juhan
Affiliation:
Graduate School of Culture Technology, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea
AES Convention:
149 (October 2020)
Paper Number:
10390
Publication Date:
October 22, 2020Import into BibTeX
Subject:
Audio Content Management
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=20927