Disentangled Multidimensional Metric Learning for Music Similarity

Cited 10 time in webofscience Cited 6 time in scopus
  • Hit : 354
  • Download : 0
Music similarity search is useful for a variety of creative tasks such as replacing one music recording with another recording with a similar "feel", a common task in video editing. For this task, it is typically necessary to define a similarity metric to compare one recording to another. Music similarity, however, is hard to define and depends on multiple simultaneous notions of similarity (i.e. genre, mood, instrument, tempo). While prior work ignore this issue, we embrace this idea and introduce the concept of multidimensional similarity and unify both global and specialized similarity metrics into a single, semantically disentangled multidimensional similarity metric. To do so, we adapt a variant of deep metric learning called conditional similarity networks to the audio domain and extend it using track-based information to control the specificity of our model. We evaluate our method and show that our single, multidimensional model outperforms both specialized similarity spaces and alternative baselines. We also run a user-study and show that our approach is favored by human annotators as well.
Publisher
IEEE
Issue Date
2020-05-05
Language
English
Citation

2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, pp.6 - 10

ISSN
1520-6149
DOI
10.1109/ICASSP40776.2020.9053442
URI
http://hdl.handle.net/10203/274609
Appears in Collection
GCT-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 10 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0