This paper describes an approach to algorithmic music composition that takes narrative structures as input, allowing composers to create music directly from narrative elements. Creating narrative development in music remains a challenging task in algorithmic composition. Our system addresses this by combining leitmotifs to represent characters, generative grammars for harmonic coherence, and evolutionary algorithms to align musical tension with narrative progression. The system operates at different scales, from overall plot structure to individual motifs, enabling both autonomous composition and co-creation with varying degrees of user control. Evaluation with compositions based on tales demonstrated the system's ability to compose music that supports narrative listening and aligns with its source narratives, while being perceived as familiar and enjoyable.

Abstract We advance Mixmash-AIS, a multimodal optimization music mashup creation model for loop recombination at scale. Our motivation is to (1) tackle current scalability limitations in state-of-the-art (brute force) computational mashup models while enforcing the (2) compatibility of audio loops and (3) a pool of diverse mashups that can accommodate user preferences. To this end, we adopt the artificial immune system (AIS) opt-aiNet algorithm to efficiently compute a population of compatible and diverse music mashups from loop recombinations. Optimal mashups result from local minima in a feature space representing harmonic, rhythmic, and spectral musical audio compatibility. We objectively assess the compatibility, diversity, and computational performance of Mixmash-AIS generated mashups compared to a standard genetic algorithm (GA) and a brute force (BF) approach. Furthermore, we conducted a perceptual test to validate the objective evaluation function within Mixmash-AIS in capturing user enjoyment of the computer-generated loop mashups. Our results show that while the GA stands as the most efficient algorithm, the AIS opt-aiNet outperforms both the GA and BF approaches in terms of compatibility and diversity. Our listening test has shown that Mixmash-AIS objective evaluation function significantly captures the perceptual compatibility of loop mashups (p < .001).

Emotional Machines is an interactive installation that builds affective virtual environments through spoken language. In response to the existing limitations of emotion recognition models incorporating computer vision and electrophysiological activity, whose sources are hindered by a head-mounted display, we propose the adoption of speech emotion recognition (from the audio signal) and semantic sentiment analysis. In detail, we use two machine learning models to predict three main emotional categories from high-level semantic and low-level speech features. Output emotions are mapped to audiovisual representation by an end-to-end process. We use a generative model of chord progressions to transfer speech emotion into music and a synthesized image from the text (transcribed from the user's speech). The generated image is used as the style source in the style-transfer process onto an equirectangular projection image target selected for each emotional category. The installation is an immersive virtual space encapsulating emotions in spheres disposed into a 3D environment. Thus, users can create new affective representations or interact with other previous encoded instances using joysticks.

Professional theatre actors are highly specialized in controlling their own expressive behaviour and non-verbal emotional expressiveness, so they are of particular interest in fields of study such as affective computing. We present Acting Emotions, an experimental protocol to investigate the physiological correlates of emotional valence and arousal within professional theatre actors. Ultimately, our protocol examines the physiological agreement of valence and arousal amongst several actors. Our main contribution lies in the open selection of the emotional set by the participants, based on a set of four categorical emotions, which are self-assessed at the end of each experiment. The experiment protocol was validated by analyzing the inter-rater agreement (> 0.261 arousal, > 0.560 valence), the continuous annotation trajectories, and comparing the box plots for different emotion categories. Results show that the participants successfully induced the expected emotion set to a significant statistical level of distinct valence and arousal distributions.

We present MixMash, an interactive tool to assist users in the creation of music mashups based on cross-modal associations between musical content analysis and information visualisation. Our point of departure is a harmonic mixing method for musical mashups by Bernardes et al. [1]. To surpass design limitations identified in the previous method, we propose a new interactive visualisation of multidimensional musical attributes-hierarchical harmonic compatibility, onset density, spectral region, and timbral similarity-extracted from a large collection of audio tracks. All tracks are represented as nodes whose distances and edge connections indicate their harmonic compatibility as a result of a force-directed graph. In addition, we provide a visual language that aims to enhance the tool usability and foster creative endeavour in the search for meaningful music mixes.

In this paper we present the INESC Key Detection (IKD) system which incorporates a novel method for dynamically biasing key mode estimation using the spatial displacement of beat-synchronous Tonal Interval Vectors (TIVs). We evaluate the performance of the IKD system at finding the global key on three annotated audio datasets and using three key-defining profiles. Results demonstrate the effectiveness of the mode bias in favoring either the major or minor mode, thus allowing users to fine tune this variable to improve correct key estimates on style-specific music datasets or to balance predictions across key modes on unknown input sources.