Listening without ears: Artificial intelligence in audio mastering

Abstract

Since the inception of recorded music there has been a need for standards and reliability across sound formats and listening environments. The role of the audio mastering engineer is prestigious and akin to a craft expert combining scientific knowledge, musical learning, manual precision and skill, and an awareness of cultural fashions and creative labour. With the advent of algorithms, big data and machine learning, loosely termed artificial intelligence in this creative sector, there is now the possibility of automating human audio mastering processes and radically disrupting mastering careers. The emergence of dedicated products and services in artificial intelligence-driven audio mastering poses profound questions for the future of the music industry, already having faced significant challenges due to the digitalization of music over the past decades. The research reports on qualitative and ethnographic inquiry with audio mastering engineers on the automation of their expertise and the potential for artificial intelligence to augment or replace aspects of their workflows. Investigating audio mastering engineers' awareness of artificial intelligence, the research probes the importance of criticality in their labour. The research identifies intuitive performance and critical listening as areas where human ingenuity and communication pose problems for simulation. Affective labour disrupts speculation of algorithmic domination by highlighting the pragmatic strategies available for humans to adapt and augment digital technologies.

Sensing defects: Collaborative seeing in engineering work

“…More ethnographic studies demonstrate that automation does not simply substitute human for machine labor but rather shifts the distribution of tasks that human and nonhuman actors undertake at work (Hutchins, 1995; Johnson, 1988; Shestakofsky, 2017; Stacey and Suchman, 2012). As Shestakofsky (2017) argues, automation must be approached as a project whose effects depend on the diverse contexts in which it is undertaken (see also Birtchnell, 2018; Bissell, 2018). His study of automation in a computing startup firm stresses the temporal dimension as the company’s efforts at automation create successive forms of human and machine collaboration.…”

“…Our approach contributes to these studies by shifting focus from the politics of whose jobs are lost (Benjamin, 2019; Brussevich et al, 2019) to also consider the politics of work with increasingly automated systems. Other ethnographic analyses have urged us to focus on projects of automation as they unfold in particular industrial and organizational contexts (Birtchnell, 2018; Bissell, 2018; Shestakofsky, 2017; Zuboff, 1988). This work finds that corporate efforts at automation often overstate the human labor replaced by technical apparatus and find instead that human labor is displaced, transformed or reorganized rather than eliminated in the name of automation (Ekbia and Nardi, 2017; Hamid et al, 2017; Irani, 2015; Johnson, 1988).…”

I Keep Counting: An Experiment in Human/AI Co-creative Songwriting

“…Music arrangement, orchestration, and mixing form a crucial part in the composition of a piece of popular music. Automatic mixing and production form a growing research area (Deruty, 2016;Man et al, 2017;Birtchnell, 2018). Although the team decided not to use any AI method for this layer, human interventions were intended to be as discreet as possible to avoid the AI-generated content being pushed into the background.…”

Music Generation and Song Popularity Prediction using Artificial Intelligence - An Overview

“…Mastering is really an intuitive process, so automating it is a bit of a challenge. But according to [20], "LANDR" is an online platform which has been successful in automating this process.…”