• Publications
  • Influence
librosa: Audio and Music Signal Analysis in Python
TLDR
This document describes version 0.4.0 of librosa: a Python pack- age for audio and music signal processing. Expand
  • 646
  • 40
  • PDF
MIR_EVAL: A Transparent Implementation of Common MIR Metrics
TLDR
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
  • 239
  • 10
  • PDF
End-to-end Learning for Music Audio Tagging at Scale
TLDR
The lack of data tends to limit the outcomes of deep learning research, particularly when dealing with end-to-end learning for music auto-tagging. Expand
  • 76
  • 6
  • PDF
A Deep Multimodal Approach for Cold-start Music Recommendation
TLDR
We address the cold-start problem of music recommendation by combining text and audio information with user feedback data using deep network architectures. Expand
  • 26
  • 6
  • PDF
Data Driven and Discriminative Projections for Large-Scale Cover Song Identification
TLDR
We improve upon previous work in large-scale cover song identification by using data-driven projections at different time-scales to capture local features and embed summary vectors into a semantically organized space. Expand
  • 43
  • 4
  • PDF
JAMS: A JSON Annotated Music Specification for Reproducible MIR Research
TLDR
We propose JAMS, a JSON-based music annotation format capable of addressing the evolving research requirements of the community, based on the three core principles of simplicity, structure and sustainability. Expand
  • 41
  • 4
  • PDF
Systematic Exploration of Computational Music Structure Research
TLDR
In this work we present a framework containing open source implementations of multiple music structural segmentation algorithms and employ it to explore the hyper parameters of features, algorithms, evaluation metrics, datasets, and annotations of this MIR task. Expand
  • 22
  • 4
  • PDF
Convex non-negative matrix factorization for automatic music structure identification
  • O. Nieto, T. Jehan
  • Mathematics, Computer Science
  • IEEE International Conference on Acoustics…
  • 26 May 2013
TLDR
We propose a novel and fast approach to discover structure in western popular music by using a specific type of matrix factorization that adds a convex constrain to obtain a decomposition that can be interpreted as a set of weighted cluster centroids. Expand
  • 28
  • 3
  • PDF
IDENTIFYING POLYPHONIC PATTERNS FROM AUDIO RECORDINGS USING MUSIC SEGMENTATION TECHNIQUES
This paper presents a method for discovering patterns of note collections that repeatedly occur in a piece of music. We assume occurrences of these patterns must appear at least twice across aExpand
  • 19
  • 3
  • PDF
Identifying Polyphonic Musical Patterns From Audio Recordings Using Music Segmentation Techniques
TLDR
We describe an algorithm that makes use of techniques from the music information retrieval task of music segmentation, which exploits repetitive features in order to automatically identify polyphonic musical patterns from audio recordings. Expand
  • 16
  • 3
  • PDF