Sökning: (hsv:(NATURVETENSKAP)) lar1:(kmh)
> (2021) >
Pitch-Informed Inst...
Pitch-Informed Instrument Assignment using a Deep Convolutional Network with Multiple Kernel Shapes
-
- Ahlbäck, Sven, 1960- (författare)
- Kungl. Musikhögskolan,Institutionen för folkmusik,Kungliga Musikhögskolan, Stockholm
-
Kungl Musikhögskolan Institutionen för folkmusik (creator_code:org_t)
- 2021
- 2021
- Engelska.
- Relaterad länk:
-
https://urn.kb.se/re...
Abstract
Ämnesord
Stäng
- This paper proposes a deep convolutional neural network for performing note-level instrument assignment. Given a polyphonic multi-instrumental music signal along with its ground truth or predicted notes, the objective is to assign an instrumental source for each note. This problem is addressed as a pitch-informed classification task where each note is analysed individually. We also propose to utilise several kernel shapes in the convolutional layers in order to facilitate learning of timbre-discriminative feature maps. Experiments on the MusicNet dataset using 7 instrument classes show that our approach is able to achieve an average F-score of 0.904 when the original multi-pitch annotations are used as the pitch information for the system, and that it also excels if the note information is provided using third-party multi-pitch estimation algorithms. We also include ablation studies investigating the effects of the use of multiple kernel shapes and comparing different input representations for the audio and the note-related information.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Annan data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Other Computer and Information Science (hsv//eng)
Nyckelord
- Harmonic-Percussive Source Separation
- Music Information Retrieval
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
- kfu (ämneskategori)