AUFX-O: Novel Methods for the Representation of Audio Processing Workflows

Wilmering, Thomas; Fazekas, György; Sandler, Mark

doi:10.1007/978-3-319-46547-0_24

Cited by 12 publications

(15 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several experiences of building Knowledge Graphs about music have been proposed in the literature. Ontologies have been designed to represent music metadata about works, performances and tracks; some notable examples are the Music Ontology [44] -further extended with other modules such as the Audio Effects Ontology (AUFX-O) [63] and the Audio Features Ontology [3] -, DOREMUS [2], the Performed Music Ontology (PMO) [52], CoMus [55]. Researching strategies for publishing and exploiting the music knowledge is the main focus of several projects such as TROMPA [60] and Polifonia, 2 both using Knowledge Graphs and Linked Data technologies.…”

Section: Related Workmentioning

confidence: 99%

MIDI2vec: Learning MIDI embeddings for reliable prediction of symbolic music metadata

Lisena

Meroño‐Peñuela

Troncy

2022

View full text Add to dashboard Cite

An important problem in large symbolic music collections is the low availability of high-quality metadata, which is essential for various information retrieval tasks. Traditionally, systems have addressed this by relying either on costly human annotations or on rule-based systems at a limited scale. Recently, embedding strategies have been exploited for representing latent factors in graphs of connected nodes. In this work, we propose MIDI2vec, a new approach for representing MIDI files as vectors based on graph embedding techniques. Our strategy consists of representing the MIDI data as a graph, including the information about tempo, time signature, programs and notes. Next, we run and optimise node2vec for generating embeddings using random walks in the graph. We demonstrate that the resulting vectors can successfully be employed for predicting the musical genre and other metadata such as the composer, the instrument or the movement. In particular, we conduct experiments using those vectors as input to a Feed-Forward Neural Network and we report good comparable accuracy scores in the prediction with respect to other approaches relying purely on symbolic music, avoiding feature engineering and producing highly scalable and reusable models with low dimensionality. Our proposal has real-world applications in automated metadata tagging for symbolic music, for example in digital libraries for musicology, datasets for machine learning, and knowledge graph completion.

show abstract

Section: Related Workmentioning

confidence: 99%

MIDI2vec: Learning MIDI embeddings for reliable prediction of symbolic music metadata

Lisena

Meroño‐Peñuela

Troncy

2022

View full text Add to dashboard Cite

show abstract

“…High-level extensions include domain ontologies for microphones, mixing, basic audio effects, and audio editing. The framework also provides hooks for domain-specific extensions such as detailed models of audio effects described in the Audio Effects Ontology [62] using a conceptual layering system originally proposed for intellectual works [63].…”

Section: Context In Semantic Audio and Music Information Retrievalmentioning

confidence: 99%

Context-Aware Intelligent Mixing Systems

Lefford¹,

Bromham²,

Fazekas³

et al. 2021

J. Audio Eng. Soc.

Self Cite

View full text Add to dashboard Cite

Intelligent Mixing Systems (IMS) are rapidly becoming integrated into music mixing and production workflows. The intelligences of a human mixer and IMS can be distinguished by their abilities to comprehend, assess, and appreciate context. Humans will factor context into decisions, particularly concerning the use and application of technologies. The utility of an IMS depends on both its affordances and the situation in which it is to be used. The appropriate use for conventional purposes, or its utility for misappropriation, is determined by the context. This study considers how context impacts mixing decisions and the use of technology, focusing on how the mixer's understanding of context can inform the use of IMS, and how the use of IMS can aid in informing a mixer of different contexts.

show abstract

“…This requires a shared conceptualization of low to high level acoustic features, as well as meaningful labels across different audio related domains. Several ontologies have been proposed for these purposes, including those for audio features [108], effects and transformations [109], mobile sensing in the audio context [110], as well as ontologies that bind complex workflows and signal routing in audio processing environments [111] and ontologies that bind distributed content repositories together [104].…”

Section: E Semantic Audiomentioning

confidence: 99%

The Internet of Audio Things: State of the Art, Vision, and Challenges

Turchet

Fazekas

Lagrange

et al. 2020

IEEE Internet Things J.

View full text Add to dashboard Cite

The Internet of Audio Things (IoAuT) is an emerging research field positioned at the intersection of the Internet of Things, sound and music computing, artificial intelligence, and human-computer interaction. The IoAuT refers to the networks of computing devices embedded in physical objects (Audio Things) dedicated to the production, reception, analysis and understanding of audio in distributed environments. Audio Things, such as nodes of wireless acoustic sensor networks, are connected by an infrastructure that enables multidirectional communication, both locally and remotely. In this paper, we first review the state of the art of this field, then we present a vision for the IoAuT and its motivations. In the proposed vision, the IoAuT enables the connection of digital and physical domains by means of appropriate information and communication technologies, fostering novel applications and services based on auditory information. The ecosystems associated with the IoAuT include interoperable devices and services that connect humans and machines to support human-human and human-machines interactions. We discuss challenges and implications of this field, which lead to future research directions on the topics of privacy, security, design of Audio Things, and methods for the analysis and representation of audio-related information.

show abstract

AUFX-O: Novel Methods for the Representation of Audio Processing Workflows

Cited by 12 publications

References 1 publication

MIDI2vec: Learning MIDI embeddings for reliable prediction of symbolic music metadata

MIDI2vec: Learning MIDI embeddings for reliable prediction of symbolic music metadata

Context-Aware Intelligent Mixing Systems

The Internet of Audio Things: State of the Art, Vision, and Challenges

Contact Info

Product

Resources

About