• Publications
  • Influence
librosa: Audio and Music Signal Analysis in Python
tl;dr
This document describes version 0.4.0 of librosa: a Python pack- age for audio and music signal processing. Expand
  • 550
  • 38
  • Open Access
Metric Learning to Rank
tl;dr
We present a general metric learning algorithm, based on the structural SVM framework, to learn a metric such that rankings of data induced by distance from a query can be optimized against various ranking measures, such as AUC, Precision-at-k, MRR, MAP or NDCG. Expand
  • 294
  • 35
  • Open Access
Lasagne: First release.
  • 374
  • 31
The Natural Language of Playlists
tl;dr
We propose a simple, scalable, and objective evaluation procedure for playlist generation algorithms. Expand
  • 94
  • 13
  • Open Access
Deep Salience Representations for F0 Estimation in Polyphonic Music
tl;dr
A fully convolutional neural network for learning salience representations for multi-f0 and melody tracking in polyphonic audio, trained using a large, semi-automatically generated f0 dataset. Expand
  • 83
  • 12
  • Open Access
Robust Structural Metric Learning
tl;dr
In this paper, we present an efficient and robust structural metric learning algorithm which enforces group sparsity on the learned transformation, while optimizing for structured ranking output prediction. Expand
  • 86
  • 11
  • Open Access
MIR_EVAL: A Transparent Implementation of Common MIR Metrics
tl;dr
We present mir_eval, an open source software library which provides a transparent and easy-to-use implementation of the most common metrics used to measure the performance of MIR algorithms. Expand
  • 221
  • 9
  • Open Access
Learning Multi-modal Similarity
tl;dr
We present a novel multiple kernel learning technique for integrating heterogeneous data into a single, unified similarity space for multi-media data. Expand
  • 135
  • 9
  • Open Access
The million song dataset challenge
tl;dr
We introduce the Million Song Dataset Challenge: a large-scale, personalized music recommendation challenge where the goal is to predict the songs that a user will listen to, given both the user's listening history and full information (including meta-data and content analysis) for all songs. Expand
  • 79
  • 9
  • Open Access
Hypergraph Models of Playlist Dialects
tl;dr
We propose to build playlist models which are tuned to specific categories or dialects of playlists. Expand
  • 60
  • 7
  • Open Access