Welcome to the UPF Digital Repository

Browsing Informes (Departament de Tecnologies de la Informació i les Comunicacions) by Author "Bogdanov, Dmitry"

Browsing Informes (Departament de Tecnologies de la Informació i les Comunicacions) by Author "Bogdanov, Dmitry"

Sort by: Order: Results:

  • Efficient supervised training of audio transformers for music representation learning
    Alonso Jiménez, Pablo; Serra, Xavier; Bogdanov, Dmitry (2023-10-03)
    In this work, we address music representation learning using convolution-free transformers. We build on top of existing spectrogram-based audio transformers such as AST and train our models on a supervised task using ...
  • Essentia API: a web API for music audio analysis
    Correya, Albin Andrew; Bogdanov, Dmitry; Alonso Jiménez, Pablo; Serra, Xavier (2023-01-10)
    We present Essentia API, a web API to access a collection of state-of-the-art music audio analysis and description algorithms based on Essentia, an open-source library and machine learning (ML) models for audio and music ...
  • Leveraging pre-trained autoencoders for interpretable prototype learning of music audio
    Alonso Jiménez, Pablo; Pepino, Leonardo; Batlle-Roca, Roser; Zinemanas, Pablo; Bogdanov, Dmitry; Serra, Xavier; Rocamora, Martín (Institute of Electrical and Electronics Engineers (IEEE), 2024)
    We present PECMAE an interpretable model for music audio classification based on prototype learning. Our model is based on a previous method, APNet, which jointly learns an autoencoder and a prototypical network. Instead, ...
  • MUSAV: a dataset of relative arousal-valence annotations for validation of audio models
    Bogdanov, Dmitry; Lizarraga Seijas, Xavier; Alonso-Jiménez, Pablo; Serra, Xavier (2022-09-27)
    We present MusAV, a new public benchmark dataset for comparative validation of arousal and valence (AV) regression models for audio-based music emotion recognition. To gather the ground truth, we rely on relative ...
  • Music representation learning based on editorial metadata from discogs
    Alonso-Jiménez, Pablo; Serra, Xavier; Bogdanov, Dmitry (2022-09-22)
    This paper revisits the idea of music representation learning supervised by editorial metadata, contributing to the state of the art in two ways. First, we exploit the public editorial metadata available on Discogs, an ...
  • Pre-Training Strategies Using Contrastive Learning and Playlist Information for Music Classification and Similarity
    Alonso-Jiménez, Pablo; Favory, Xavier; Foroughmand, Hadrien; Bourdalas, Grigoris; Serra, Xavier; Lidy, Thomas; Bogdanov, Dmitry (2023-04-25)
    In this work, we investigate an approach that relies on contrastive learning and music metadata as a weak source of supervision to train music representation models. Recent studies show that contrastive learning can be ...

Search DSpace


Advanced Search

Browse

My Account

In collaboration with Compliant to Partaking