• Publications
  • Influence
Essentia: An Audio Analysis Library for Music Information Retrieval
Comunicacio presentada a la 14th International Society for Music Information Retrieval Conference, celebrada a Curitiba (Brasil) els dies 4 a 8 de novembre de 2013.
An industrial-strength content-based music recommendation system
TLDR
MusicSurfer automatically extracts descriptions related to instrumentation, rhythm and harmony from music audio signals to allow navigation of multimillion track music collections in a flexible and efficient way without the need of metadata or human ratings.
Content-based music audio recommendation
TLDR
The MusicSurfer automatically extracts descriptions related to instrumentation, rhythm and harmony from music audio signals to allow navigation of multimillion track music collections in a flexible and efficient way without the need for metadata nor human ratings.
ESSENTIA: an open-source library for sound and music analysis
TLDR
Essentia 2.0, an open-source C++ library for audio analysis and audio-based music information retrieval, is presented, which contains an extensive collection of reusable algorithms which implement audio input/output functionality, standard digital signal processing blocks, statistical characterization of data, and a large set of spectral, temporal, tonal and high-level music descriptors.
ISMIR 2004 Audio Description Contest
TLDR
The ISMIR 2004 Audio Description Contest is reported on, which details the contest organization, evaluation metrics, data and infrastructure, and proposes ways to organize future, improved, audio description contests.
Unifying Low-Level and High-Level Music Similarity Measures
TLDR
This paper proposes three of such distance measures based on the audio content: first, a low-level measure based on tempo-related description; second, a high-level semantic measurebased on the inference of different musical dimensions by support vector machines; and third, a hybrid measure which combines the above-mentioned distance measures.
Nearest-Neighbor Automatic Sound Annotation with a WordNet Taxonomy
TLDR
A nearest-neighbor classifier with a database of isolated sounds unambiguously linked to WordNet concepts, a semantic network that organizes real world knowledge, is used to overcome the need of a huge number of classifiers to distinguish many different sound classes.
BEAT DETECTION USING PLP
We report here about our submission to both the Beat Tracking and the Tempo Estimation tasks for the MIREX 2010 evaluations. Our submission consists of an adaptation of the technique presented at
MTG-DB: a repository for music audio processing
TLDR
This work presents a common repository of audio, metadata, ontologies and algorithms, in the form of massive storage and computation cluster, the software and databases design and the ontology management of the current system.
Nearest-neighbor Generic Sound Classification with a WordNet-based Taxonomy
TLDR
This work uses WordNet, a semantic network that organizes real world knowledge, to tackle the taxonomy definition problem and uses a nearest-neighbor classifier with a database of isolated sounds unambiguously linked to WordNet concepts to overcome the need of a huge number of classifiers.
...
...