Audio steganography—the practice of concealing information within sound—has emerged as a creative tool in electronic music production, with artists embedding visual data in the time-frequency domain that is audible as texture but reveals itself clearly only when rendered as a spectrogram. Artists are increasingly adopting steganographic techniques, known as data poisoning, to prevent their works being used to train AI without their consent. By embedding imperceptible adversarial noise directly into their work, artists can corrupt the feature-extraction process of unauthorised AI model development, while the data remains perceptually unchanged to humans. This work, through the medium of two audio-visual artworks incorporating steganographic processes, places a critical lens on the socio-cultural impacts of technological development and its historically undulating relationship with electronic music. Through this, we hope to promote discussions on responsible technology development that recognises the value of human creativity, an imperative dialogue as data-driven AI continues its rapid expansion.

We suggest that more attention should be given to how musicians collaborate in the studio when designing Digital Audio Workstations (DAWs). We conducted an ethnography in a home studio, gathering three hours of video recordings over four consecutive days of a pro-amateur performer-producer duo during the writing of their debut album. Focusing on how performers and producers structure their interactions around the audio playback of the DAW whilst composing, this paper analyses how their relationship to the software might change their interactions, towards establishing common ground in conversation. Field notes are analysed, and a design brief is suggested where control of the playhead is given to the performer, potentially allowing them to use the audio playback within their utterances to help reference specific audio sections, even when they are not near to the DAW.

This paper describes the design and evaluation of Netz, a novel mixed reality musical instrument that leverages artificial intelligence for reducing errors in gesture interpretation by the system. We followed a participatory design approach over three months through regular sessions with a professional musician. We explain our design process and discuss technological sensing errors in mixed reality devices, which emerged during the design sessions. We investigate the use of interactive machine learning techniques to mitigate such errors. Results from statistical analyses indicate that a deep learning model based on interactive machine learning can significantly reduce the number of technological errors in a set of musical performance tasks with the mixed reality musical instrument. Based on our findings, we argue that the application of interactive machine learning techniques can be beneficial for embodied, hand-controlled musical instruments in the mixed reality domain.

Working from vague client instructions, how do audio producers collaborate to diagnose what specifically is wrong with a piece of music, where the problem is and what to do about it? This paper presents a design ethnography that uncovers some of the ways in which two music producers co-ordinate their understanding of complex representations of pieces of music while working together in a studio. Our analysis shows that audio producers constantly make judgements based on audio and visual evidence while working with complex digital tools, which can lead to ambiguity in assessments of issues. We show how multimodal conduct guides the process of work and that complex media objects are integrated as elements of interaction by the music producers. The findings provide an understanding how people currently collaborate when producing audio, to support the design of better tools and systems for collaborative audio production in the future.

Current music emotion recognition (MER) systems rely on emotion data averaged across listeners and over time to infer the emotion expressed by a musical piece, often neglecting time- and listener-dependent factors. These limitations can restrict the efficacy of MER systems and cause misjudgements. We present two exploratory studies on music emotion perception. First, in a live music concert setting, fifteen audience members annotated perceived emotion in the valence-arousal space over time using a mobile application. Analyses of inter-rater reliability yielded widely varying levels of agreement in the perceived emotions. A follow-up lab-based study to uncover the reasons for such variability was conducted, where twenty-one participants annotated their perceived emotions whilst viewing and listening to a video recording of the original performance and offered open-ended explanations. Thematic analysis revealed salient features and interpretations that help describe the cognitive processes underlying music emotion perception. Some of the results confirm known findings of music perception and MER studies. Novel findings highlight the importance of less frequently discussed musical attributes, such as musical structure, performer expression, and stage setting, as perceived across audio and visual modalities. Musicians are found to attribute emotion change to musical harmony, structure, and performance technique more than non-musicians. We suggest that accounting for such listener-informed music features can benefit MER in helping to address variability in emotion perception by providing reasons for listener similarities and idiosyncrasies.

This paper presents an observational study of collaborative spatial music composition. We uncover the practical methods two experienced music producers use to coordinate their understanding of multi-modal and spatial representations of music as part of their workflow. We show embodied spatial referencing as a significant feature of the music producers' interactions. Our analysis suggests that gesture is used to understand, communicate and form action through a process of shaping sounds in space. This metaphor highlights how aesthetic assessments are collaboratively produced and developed through coordinated spatial activity. Our implications establish sensitivity to embodied action in the development of collaborative workspaces for creative, spatial-media production of music.

Communication among performers is a fundamental aspect in music performance. A large number of electronic music instruments based on tangible and screen-based interfaces require a focused visual attention from performers while they are controlled. In certain stage and artistic configurations, this may be an obstacle to face-to-face creative interactions between coperformers and their collaborators. To address these issues, we adopted a user-centered design methodology to develop a novel class of IoT devices that we term musical haptic wearables for performers. We conducted a co-design workshop with 10 electronic musicians using focus-group discussions and the bootlegging technique. This workshop identified numerous creative communication issues among performers in electronic music practice and resulted in mock-up prototypes. We then developed three chest-, foot-, and arm-worn haptic wearables respectively for coperformer, performer-conductor, and performer-sound-engineer interactions. The wearables were assessed with 25 participants using a mixed-methods approach. High accuracies (70%-100%) were obtained for musical actions expected after instructions wirelessly communicated via tactile signals. The results provide evidence that musical haptic wearables can be an effective medium of communication in the context of electronic music performances. More challenges were identified regarding size and placement of the devices on the body, interferences with concurrent vibrations generated by music signals, limitations on the range of creative controls, and a required training curve.

This paper presents initial steps towards the design of an embedded system for body-centric sonic performance. The proposed prototyping system allows performers to manipulate sounds through gestural interactions captured by textile wearable sensors. The e-textile sensor data control, in real-time, audio synthesis algorithms working with content from Audio Commons, a novel web-based ecosystem for re-purposing crowd-sourced audio. The system enables creative embodied music interactions by combining seamless physical e-textiles with web-based digital audio technologies.

This study investigates whether taking genre into account is beneficial for automatic music mood annotation in terms of core affects valence, arousal, and tension, as well as several other mood scales. Novel techniques employing genre-adaptive semantic computing and audio-based modelling are proposed. A technique called the ACTwg employs genre-adaptive semantic computing of mood-related social tags, whereas ACTwg-SLPwg combines semantic computing and audio-based modelling, both in a genre-adaptive manner. The proposed techniques are experimentally evaluated at predicting listener ratings related to a set of 600 popular music tracks spanning multiple genres. The results show that ACTwg outperforms a semantic computing technique that does not exploit genre information, and ACTwg-SLPwg outperforms conventional techniques and other genre-adaptive alternatives. In particular, improvements in the prediction rates are obtained for the valence dimension which is typically the most challenging core affect dimension for audio-based annotation. The specificity of genre categories is not crucial for the performance of ACTwg-SLPwg. The study also presents analytical insights into inferring a concise tag-based genre representation for genre-adaptive music mood analysis.

Mood Conductor is a system that allows the audience to interact with stage performers to create directed improvisations. The term "conductor" is used metaphorically. Rather than directing a musical performance by way of visible gestures, spectators act as conductors by communicating emotional intentions to the performers through our web-based smartphone-friendly Mood Conductor app. Performers receive the audience's directions via a visual feedback system operating in real-time. Emotions are represented by coloured blobs in a two-dimensional space (vertical dimension: arousal or excitation; horizontal dimension: valence or pleasantness). The size of the "emotion blobs" indicates the number of spectators that have selected the corresponding emotions at a given time.

In this paper we present a novel hybrid system that involves a formal method of automatic ontology generation for web-based audio signal processing applications. An ontology is seen as a knowledge management structure that represents domain knowledge in a machine interpretable format. It describes concepts and relationships within a particular domain, in our case, the domain of musical instruments. However, the different tasks of ontology engineering including manual annotation, hierarchical structuring and organization of data can be laborious and challenging. For these reasons, we investigate how the process of creating ontologies can be made less dependent on human supervision by exploring concept analysis techniques in a Semantic Web environment. In this study, various musical instruments, from wind to string families, are classified using timbre features extracted from audio. To obtain models of the analysed instrument recordings, we use K-means clustering to determine an optimised codebook of Line Spectral Frequencies (LSFs), or Mel-frequency Cepstral Coefficients (MFCCs). Two classification techniques based on Multi-Layer Perceptron (MLP) neural network and Support Vector Machines (SVM) were tested. Then, Formal Concept Analysis (FCA) is used to automatically build the hierarchical structure of musical instrument ontologies. Finally, the generated ontologies are expressed using the Ontology Web Language (OWL). System performance was evaluated under natural recording conditions using databases of isolated notes and melodic phrases. Analysis of Variance (ANOVA) were conducted with the feature and classifier attributes as independent variables and the musical instrument recognition F-measure as dependent variable. Based on these statistical analyses, a detailed comparison between musical instrument recognition models is made to investigate their effects on the automatic ontology generation system. The proposed system is general and also applicable to other research fields that are related to ontologies and the Semantic Web.