Gæðastjórnunarkerfi : grunnatriði og íðorðasafn = Quality Management Systems : fundamentals and vocabulary.

The power of sound.

Reflecting on a decade of Automatic Mixing systems for multitrack music processing, this paper positions the topic in the wider field of Intelligent Music Production, and seeks to motivate the existing and continued work in this area. Tendencies such as the introduction of machine learning and the increasing complexity of automated systems become apparent from examining a short history of relevant work, and several categories of applications are identified. Based on this systematic review, we highlight some promising directions for future research for the next ten years of Automatic Mixing.

Ten Years of Automatic Mixing

Music production technology has made few advancements over the past few decades. State-of-the-art approaches are based on traditional studio paradigms with new developments primarily focusing on digital modelling of analog equipment. Intelligent music production (IMP) is the approach of introducing some level of artificial intelligence into the space of music production, which has the ability to change the field considerably. There are a multitude of methods that intelligent systems can employ to analyse, interact with, and modify audio. Some systems interact and collaborate with human mix engineers, while others are purely black box autonomous systems, which are uninterpretable and challenging to work with. This article outlines a number of key decisions that need to be considered while producing an intelligent music production system, and identifies some of the assumptions and constraints of each of the various approaches. One of the key aspects to consider in any IMP system is how an individual will interact with the system, and to what extent they can consistently use any IMP tools. The other key aspects are how the target or goal of the system is created and defined, and the manner in which the system directly interacts with audio. The potential for IMP systems to produce new and interesting approaches for analysing and manipulating audio, both for the intended application and creative misappropriation, is considerable.

https://www.mdpi.com/2076-0752/8/4/125/pdf

Approaches in Intelligent Music Production

Mixing music is the process of combining tracks of recorded audio to an overall piece. This is a complicated process and, hence, automatic mixing or metering tools would be useful. The aim of the current research project was to work towards measuring the perceived quality of music mixes by establishing predictors for one important perceptual attribute of high- quality mixes (spectral clarity).

A review of academic and non-academic literature revealed that the high-level parameters that are responsible for determining the perceived quality of a music mix are ‘clarity and separation’, ‘balance’, ‘impact and interest’ and ‘freedom from technical faults’, alongside context-specific parameters. A further in-depth literature review established that clarity and separation—the chosen focus for this research—depend on spectral, spatial and intensity factors, and temporal changes in these factors. Spectral factors play an important role across all areas of literature consulted (namely timbral clarity, clarity in concert halls, masking, loudness, auditory scene analysis and speech intelligibility), and so the impact of mix EQ on spectral clarity was investigated in a series of experiments.

These experiments determined that two important factors contribute to the spectral clarity of single sounds. These are the harmonic centroid (spectral centroid divided by the sound’s average fundamental frequency) and mid-range spectral peakiness (related to sharp peaks in the frequency spectrum). For sounds modified by simple spectral filtering, these two factors are sufficient to model clarity changes with a Spearman correlation ranging from 0.631 (bass and vocal stimuli) to 0.848 (string stimuli). For sounds in a mix, however, other factors become important. Adding a peak audibility measure proved useful. This measure determined whether the audibility of peaks in the spectra of the target sounds was increased or decreased through EQ. Target and overall mix harmonic centroids and mid- range spectral peakiness, combined with peak audibility, correlated positively with target spectral clarity (r=0.568).

Findings could contribute to the development of marketable products such as a piece of software able to judge the overall sound quality of a mix, automatic mixers or sonically improved music production software. Further work will allow a more comprehensive and generalizable model to be developed.

Towards measuring music mix quality : the factors contributing to the spectral clarity of single sounds.

To further the development of intelligent music production tools, towards generating mixes
that would realistically be created by a human mix-engineer, it is important to understand what
kind of mixes can be created, and are typically created, by human mix-engineers. This paper
presents an analysis of 1501 mixes, over 10 different songs, created by mix-engineers. The
primary dimensions of variation in the full dataset of mixes were ‘amplitude’, ‘brightness’,
‘bass’ and ‘width’, as determined by feature-extraction and subsequent principal component
analysis. The distribution of representative features approximated a normal distribution and
this is then used to obtain general trends and tolerance bounds for these features. The results
presented here are useful as parametric guidance for intelligent music production systems.

/pdf/variation-in-multitrack-mixes-analysis-of-low-level-audio-essi7sxq4k.pdf

Variation in Multitrack Mixes: Analysis of Low-level Audio Signal Features

The quality of recorded music is often highly disputed. To gain insight into the dimensions
of quality perception, subjective and objective evaluation of musical programme material,
extracted from commercial CDs, was undertaken. It was observed that perception of audio
quality and liking of the music can be affected by separate factors. Familiarity with stimuli
affected like ratings while quality ratings were most associated with signal features related
to perceived loudness and dynamic range compression. The effect of listener expertise was
small. Additionally, the sonic attributes describing quality ratings were gathered and indicate
a diverse lexicon relating to timbre, space, defects and other concepts. The results also suggest
that, while the perceived quality of popular music may have decreased over recent years, like
ratings were unaffected.

Perception of Audio Quality in Productions of Popular Music

The act of mix-engineering is a complex combination of creative and technical processes; analysis is often performed by studying the techniques of a few expert practitioners, qualitatively. We propose to study the actions of a large group of mix-engineers of varying experience, introducing quantitative methodology to investigate mix-variation and the perception of quality. This paper describes the analysis of a dataset containing 101 alternate mixes generated by human mixers as part of an on-line mix competition. A varied selection of audio signal features is obtained from each mix and subsequent principal component analysis reveals four prominent dimensions of variation - `dynamics', `treble', `width' and `bass'. An ordinal logistic regression model suggests that the ranking of each mix in the competition was significantly influenced by these four dimensions. The implications for the design of intelligent music production systems are discussed.

101 Mixes: A Statistical Analysis of Mix-Variation in a Dataset of Multi-Track Music Mixes

The mixing of audio signals has been at the foundation of
audio production since the advent of electrical recording in the 1920’s, yet the mathematical and psychological bases for this activity are relatively under-studied. This paper investigates how the process of mixing music is conducted. We introduce a method of transformation from a “gain-space” to a “mix-space”, using a novel representation of the individual track gains. An experiment is conducted in order to obtain time-series data of mix engineers exploration of this space as they adjust levels within a multitrack session to create their desired mixture. It is observed that, while the exploration of the space is influenced by the initial configuration of track gains, there is agreement between
individuals on the appropriate gain settings required
to create a balanced mixture. Implications for the design
of intelligent music production systems are discussed.

https://usir.salford.ac.uk/36950/1/SMC2015_MixSpace_Final.pdf

Navigating the mix-space : theoretical and practical level-balancing technique in multitrack music mixtures

A dataset of audio clips was prepared and audio quality assessed by subjective testing. Encoded as digital signals, a large amount of feature-extraction was possible. A new objective metric is proposed, describing the Gaussian nature of a signal’s amplitude distribution. Correlations between objective measurements of the music signals and the subjective perception of their quality were found. Existing metrics were adjusted to match quality perception. A number of timbral, spatial, rhythmic and amplitude measures, in
addition to predictions of emotional response, were found to be related to the perception of quality. The emotional features were found to have most importance, indicating a connection between quality and a uniﬁed set of subjective and objective parameters.

/pdf/perception-evaluation-of-audio-quality-in-music-production-dn5fkk21b0.pdf

Alex Wilson

Papers

Variation in Multitrack Mixes: Analysis of Low-level Audio Signal Features

Perception of Audio Quality in Productions of Popular Music

101 Mixes: A Statistical Analysis of Mix-Variation in a Dataset of Multi-Track Music Mixes

Navigating the mix-space : theoretical and practical level-balancing technique in multitrack music mixtures

Perception & evaluation of audio quality in music production