Luca Marinelli

My PhD project sits at the intersection of music data science, gender and media studies, with the aim of implementing semi-automated systems for a critical analysis of gendered markers in large corpora of television adverts. Theorising music as a multimodal discourse enables us to account for the influence of gender-based market segmentation strategies on the selection and composition of sound and music for advertising.

My research combines technical and critical approaches. I developed deep learning models and statistical methods for analyzing multimodal data, including recent work with large language models and retrieval-augmented generation systems. I worked with explainable AI techniques to make model decisions interpretable, and I have strong foundations in audio signal processing, NLP, and time series analysis.

I welcome conversations with researchers, industry professionals, and anyone interested in the intersection of music, gender, and media. Get in touch at marinelli.luca [at] proton.me.

news

Jan 05, 2026	I submitted the thesis! The discussion will be sometime in March.
Nov 20, 2025	Invited lecture on “Gender‑Coded Sound: Computational Insights into Toy Advertising Music” at the Hochschule für Musik, Theater und Medien Hannover, Germany.

selected publications

Leveraging RAG for a Low-Resource Audio-Aware Diachronic Analysis of Gendered Toy Marketing

Luca Marinelli, Iacopo Ghinassi, and Charalampos Saitis

In Proceedings of the First Workshop on Natural Language Processing and Language Models for Digital Humanities @ RANLP 2025, 2025
Explainable Modeling of Gender-Targeting Practices in Toy Advertising Sound and Music

Luca Marinelli and Charalampos Saitis

In 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), 2024
Gender-Coded Sound: Analysing the Gendering of Music in Toy Commercials via Multi-Task Learning

Luca Marinelli, György Fazekas, and Charis Saitis

24th International Society for Music Information Retrieval Conference (ISMIR 2023), 2023
A multimodal understanding of the role of sound and music in gendered toy marketing

Luca Marinelli, Petra Lucht, and Charalampos Saitis

PLOS ONE, Nov 2024

Abs DOI

Literature in music theory and psychology shows that, even in isolation, musical sounds can reliably encode gender-loaded messages. Musical material can be imbued with many ideological dimensions and gender is just one of them. Nonetheless, studies of the gendering of music within multimodal communicative events are sparse and lack an encompassing theoretical framework. The present study attempts to address this literature gap by employing a critical quantitative analysis of music in gendered toy marketing, which integrated a content analytical approach with multimodal affective and music-focused perceptual responses. Ratings were collected on a set of 606 commercials spanning a ten-year time frame and strong gender polarization was observed in nearly all of the collected variables. Gendered music styles in toy commercials exhibit synergistic design choices, as music in masculine-targeted adverts was substantially more abrasive—louder, more inharmonious, and more distorted—than in feminine-targeted ones. Thus, toy advertising music appeared deliberately and consistently in line with traditional gender norms. In addition, music perceptual scales and voice-related content analytical variables explain quite well the heavily polarized affective ratings. This study presents a empirical understanding of the gendering of music as constructed within multimodal discourse, reiterating the importance of the sociocultural underpinnings of music cognition. We provided a public repository with all code and data necessary to reproduce the results of this study on github.com/marinelliluca/music-role-gender-marketing.
Musical Dynamics Classification with CNN and Modulation Spectra

Luca Marinelli, Athanasios Lykartsis, Stefan Weinzierl, and 1 more author

In Proceedings of the 17th Sound and Music Computing Conference, Torino, Italy, 2020