Tootfinder

Data-Driven Analysis of Text-Conditioned AI-Generated Music: A Case Study with Suno and Udio
Luca Casini, Laura Cros Vila, David Dalmazzo, Anna-Kaisa Kaila, Bob L. T. Sturm
https://arxiv.org/abs/2509.11824

Data-Driven Analysis of Text-Conditioned AI-Generated Music: A Case Study with Suno and Udio
Online AI platforms for creating music from text prompts (AI music), such as Suno and Udio, are now being used by hundreds of thousands of users. Some AI music is appearing in advertising, and even charting, in multiple countries. How are these platforms being used? What subjects are inspiring their users? This article answers these questions for Suno and Udio using a large collection of songs generated by users of these platforms from May to October 2024. Using a combination of state-of-the-ar…

How AI is upending the music industry in Latin America, as artists push back against a flood of AI-generated music on Spotify, Deezer, and YouTube Music (Laura Rodríguez Salamanca/Rest of World)
https://restofworld.org/2025/ai-music-spotify-deezer-latin-america/

Latin American musicians say AI is stealing their streams
Musicians from Chile to Mexico say bots are stealing streams, siphoning income, and shortening the lifespan of songs. Even Bad Bunny isn’t safe.

How AI is upending the music industry in Latin America, as artists push back against a flood of AI-generated music on Spotify, Deezer, and YouTube Music (Laura Rodríguez Salamanca/Rest of World)
https://restofworld.org/2025/ai-music-spotify-deezer-latin-america/

Latin American musicians say AI is stealing their streams
Musicians from Chile to Mexico say bots are stealing streams, siphoning income, and shortening the lifespan of songs. Even Bad Bunny isn’t safe.

Segment Transformer: AI-Generated Music Detection via Music Structural Analysis
Yumin Kim, Seonghyeon Go
https://arxiv.org/abs/2509.08283 https://arxiv.org…

Segment Transformer: AI-Generated Music Detection via Music Structural Analysis
Audio and music generation systems have been remarkably developed in the music information retrieval (MIR) research field. The advancement of these technologies raises copyright concerns, as ownership and authorship of AI-generated music (AIGM) remain unclear. Also, it can be difficult to determine whether a piece was generated by AI or composed by humans clearly. To address these challenges, we aim to improve the accuracy of AIGM detection by analyzing the structural patterns of music segments…

TalkPlayData 2: An Agentic Synthetic Data Pipeline for Multimodal Conversational Music Recommendation
Keunwoo Choi, Seungheon Doh, Juhan Nam
https://arxiv.org/abs/2509.09685 htt…

TalkPlayData 2: An Agentic Synthetic Data Pipeline for Multimodal Conversational Music Recommendation
We present TalkPlayData 2, a synthetic dataset for multimodal conversational music recommendation generated by an agentic data pipeline. In TalkPlayData 2 pipeline, multiple large language model (LLM) agents are created under various roles with specialized prompts and access to different parts of information, and the chat data is acquired by logging the conversation between the Listener LLM and the Recsys LLM. To cover various conversation scenarios, for each conversation, the Listener LLM is c…

Interactive TV group FastStream unveils AI-generated presenters for ROXi, the TV music channel it acquired in May; ROXi airs on Nextgen TV in 31 US markets (Scott Roxborough/The Hollywood Reporter)
https://www.hollywoodreporter.com/business/digit…

Tech Company Unveils AI-Generated Music Video Hosts
FastStream, an interactive TV group backed by the likes of Simon Cowell, Robbie Williams, Kylie Minogue and U2 bassist Adam Clayton, plans to use AI images to mimic VJ presenters on its music TV channel ROXi.

RIAA: US recorded music revenue hit $5.6B across all formats in H1 2025, up 1% YoY; streaming generated $4.68B, and paid subscriptions grew 5.7% YoY to $3.2B (Marc Schneider/Billboard)
https://www.billboard.com/pro/riaa-2025-mid-year-report-recorded…

U.S. Recorded Music Revenue Hits $5.6B in First Half of 2025 as Paid Subscriptions Top 100 Million: RIAA
RIAA says U.S. recorded music revenue rose slightly to $5.6 billion in the first half of 2025, with figures now presented on a wholesale basis.

Attribution-by-design: Ensuring Inference-Time Provenance in Generative Music Systems
Fabio Morreale, Wiebke Hutiri, Joan Serr\`a, Alice Xiang, Yuki Mitsufuji
https://arxiv.org/abs/2510.08062

Attribution-by-design: Ensuring Inference-Time Provenance in Generative Music Systems
The rise of AI-generated music is diluting royalty pools and revealing structural flaws in existing remuneration frameworks, challenging the well-established artist compensation systems in the music industry. Existing compensation solutions, such as piecemeal licensing agreements, lack scalability and technical rigour, while current data attribution mechanisms provide only uncertain estimates and are rarely implemented in practice. This paper introduces a framework for a generative music infras…

As the lyricist behind AI artist Xania Monet signs a $3M record deal, experts say current copyright law may only protect the human-made expressive elements (Elissa Welle/The Verge)
https://www.theverge.com/ai-artificial-intelligence/785792/…

What happens when an AI-generated artist gets a record deal? A copyright mess
The only human-made element behind Xania Monet’s act appear to be the lyrics.

Wearable Music2Emotion : Assessing Emotions Induced by AI-Generated Music through Portable EEG-fNIRS Fusion
Sha Zhao, Song Yi, Yangxuan Zhou, Jiadong Pan, Jiquan Wang, Jie Xia, Shijian Li, Shurong Dong, Gang Pan
https://arxiv.org/abs/2508.04723

Wearable Music2Emotion : Assessing Emotions Induced by AI-Generated Music through Portable EEG-fNIRS Fusion
Emotions critically influence mental health, driving interest in music-based affective computing via neurophysiological signals with Brain-computer Interface techniques. While prior studies leverage music's accessibility for emotion induction, three key limitations persist: \textbf{(1) Stimulus Constraints}: Music stimuli are confined to small corpora due to copyright and curation costs, with selection biases from heuristic emotion-music mappings that ignore individual affective profiles. \text…

Just learned that my little visual cosine gradient generator tool (from 2015) is featured in this popular video tutorial (1.1M views) about artistic shader programming:
https://youtu.be/f4s1h2YETNY?t=971
The tool is still here:

Singing Syllabi with Virtual Avatars: Enhancing Student Engagement Through AI-Generated Music and Digital Embodiment
Xinxing Wu
https://arxiv.org/abs/2508.11872 https://

Singing Syllabi with Virtual Avatars: Enhancing Student Engagement Through AI-Generated Music and Digital Embodiment
In practical teaching, we observe that few students thoroughly read or fully comprehend the information provided in traditional, text-based course syllabi. As a result, essential details, such as course policies and learning outcomes, are frequently overlooked. To address this challenge, in this paper, we propose a novel approach leveraging AI-generated singing and virtual avatars to present syllabi in a format that is more visually appealing, engaging, and memorable. Especially, we leveraged t…

Training chord recognition models on artificially generated audio
Martyna Majchrzak, Jacek Ma\'ndziuk
https://arxiv.org/abs/2508.05878 https://arxiv.or…

Training chord recognition models on artificially generated audio
One of the challenging problems in Music Information Retrieval is the acquisition of enough non-copyrighted audio recordings for model training and evaluation. This study compares two Transformer-based neural network models for chord sequence recognition in audio recordings and examines the effectiveness of using an artificially generated dataset for this purpose. The models are trained on various combinations of Artificial Audio Multitracks (AAM), Schubert's Winterreise Dataset, and the McGill…

Assessing Data Replication in Symbolic Music via Adapted Structural Similarity Index Measure
Shulei Ji, Zihao Wang, Le Ma, Jiaxing Yu, Kejun Zhang
https://arxiv.org/abs/2509.13658

Assessing Data Replication in Symbolic Music via Adapted Structural Similarity Index Measure
AI-generated music may inadvertently replicate samples from the training data, raising concerns of plagiarism. Similarity measures can quantify such replication, thereby offering supervision and guidance for music generation models. Existing similarity measure methods for symbolic music mainly target melody repetition, leaving a gap in assessing complex music with rich textures and expressive performance characteristics. To address this gap, we introduce SSIMuse, the first adaptation of the Str…

Bias beyond Borders: Global Inequalities in AI-Generated Music
Ahmet Solak, Florian Gr\"otschla, Luca A. Lanzend\"orfer, Roger Wattenhofer
https://arxiv.org/abs/2510.01963

Bias beyond Borders: Global Inequalities in AI-Generated Music
While recent years have seen remarkable progress in music generation models, research on their biases across countries, languages, cultures, and musical genres remains underexplored. This gap is compounded by the lack of datasets and benchmarks that capture the global diversity of music. To address these challenges, we introduce GlobalDISCO, a large-scale dataset consisting of 73k music tracks generated by state-of-the-art commercial generative music models, along with paired links to 93k refer…

As the lyricist behind AI artist Xania Monet signs a $3M record deal, experts say current copyright law may only protect the human-made expressive elements (Elissa Welle/The Verge)
https://www.theverge.com/ai-artificial-intelligence/785792/…

What happens when an AI-generated artist gets a record deal? A copyright mess
The only human-made element behind Xania Monet’s act appear to be the lyrics.

I found a musician that's right up my alley: Dante Zimmerman, aka "Dysmn".
https://www.youtube.com/watch?v=LTnMKRAnxU4
What's interesting about this is that he apparently uses AI as a tool for digital audio processing. The music is not generated or written by AI. It…

EEG Brain mapping based on the Duffing oscillator
Mahmut Akilli, Nazmi Yilmaz
https://arxiv.org/abs/2509.00618 https://arxiv.org/pdf/2509.00618

EEG Brain mapping based on the Duffing oscillator
In this study, we introduce the EEG brain mapping technique based on the Duffing oscillator. For this purpose, we used EEG signals recorded from two musicians and two audience members in a music experiment. The Duffing oscillator was used to detect weak signals in the EEG signals. The frequency values of the weak signal were searched between 12 Hz and 37 Hz in all EEG channels of the participants. Then, topographical maps of the brain were generated according to the numbers of these weak signal…

ACMID: Automatic Curation of Musical Instrument Dataset for 7-Stem Music Source Separation
Ji Yu, Yang shuo, Xu Yuetonghui, Liu Mengmei, Ji Qiang, Han Zerui
https://arxiv.org/abs/2510.07840

ACMID: Automatic Curation of Musical Instrument Dataset for 7-Stem Music Source Separation
Most current music source separation (MSS) methods rely on supervised learning, limited by training data quan- tity and quality. Though web-crawling can bring abundant data, platform-level track labeling often causes metadata mismatches, impeding accurate "audio-label" pair acquisi- tion. To address this, we present ACMID: a dataset for MSS generated through web crawling of extensive raw data, fol- lowed by automatic cleaning via an instrument classifier built on a pre-trained audio encoder tha…

A Survey on Evaluation Metrics for Music Generation
Faria Binte Kader, Santu Karmaker
https://arxiv.org/abs/2509.00051 https://arxiv.org/pdf/2509.00051

A Survey on Evaluation Metrics for Music Generation
Despite significant advancements in music generation systems, the methodologies for evaluating generated music have not progressed as expected due to the complex nature of music, with aspects such as structure, coherence, creativity, and emotional expressiveness. In this paper, we shed light on this research gap, introducing a detailed taxonomy for evaluation metrics for both audio and symbolic music representations. We include a critical review identifying major limitations in current evaluati…

Wavelet-Based Time-Frequency Fingerprinting for Feature Extraction of Traditional Irish Music
Noah Shore
https://arxiv.org/abs/2508.00479 https://arxiv.org…

Wavelet-Based Time-Frequency Fingerprinting for Feature Extraction of Traditional Irish Music
This work presents a wavelet-based approach to time-frequency fingerprinting for time series feature extraction, with a focus on audio identification from live recordings of traditional Irish tunes. The challenges of identifying features in time-series data are addressed by employing a continuous wavelet transform to extract spectral features and wavelet coherence analysis is used to compare recorded audio spectrograms to synthetically generated tunes. The synthetic tunes are derived from ABC n…

Charm quark evolution in the early stages of heavy-ion collisions
Mayank Singh, Manu Kurian, Bj\"orn Schenke, Sangyong Jeon, Charles Gale
https://arxiv.org/abs/2509.18647 h…

MusicWeaver: Coherent Long-Range and Editable Music Generation from a Beat-Aligned Structural Plan
Xuanchen Wang, Heng Wang, Weidong Cai
https://arxiv.org/abs/2509.21714 https:/…

MusicWeaver: Coherent Long-Range and Editable Music Generation from a Beat-Aligned Structural Plan
Current music generators capture local textures but often fail to model long-range structure, leading to off-beat outputs, weak section transitions, and limited editing capability. We present MusicWeaver, a music generation model conditioned on a beat-aligned structural plan. This plan serves as an editable intermediate between the input prompt and the generated music, preserving global form and enabling professional, localized edits. MusicWeaver consists of a planner, which translates prompts …

TART: A Comprehensive Tool for Technique-Aware Audio-to-Tab Guitar Transcription
Akshaj Gupta, Andrea Guzman, Anagha Badriprasad, Hwi Joo Park, Upasana Puranik, Robin Netzorg, Jiachen Lian, Gopala Krishna Anumanchipalli
https://arxiv.org/abs/2510.02597

TART: A Comprehensive Tool for Technique-Aware Audio-to-Tab Guitar Transcription
Automatic Music Transcription (AMT) has advanced significantly for the piano, but transcription for the guitar remains limited due to several key challenges. Existing systems fail to detect and annotate expressive techniques (e.g., slides, bends, percussive hits) and incorrectly map notes to the wrong string and fret combination in the generated tablature. Furthermore, prior models are typically trained on small, isolated datasets, limiting their generalizability to real-world guitar recordings…

Scalable Evaluation for Audio Identification via Synthetic Latent Fingerprint Generation
Aditya Bhattacharjee, Marco Pasini, Emmanouil Benetos
https://arxiv.org/abs/2509.18620 h…

Scalable Evaluation for Audio Identification via Synthetic Latent Fingerprint Generation
The evaluation of audio fingerprinting at a realistic scale is limited by the scarcity of large public music databases. We present an audio-free approach that synthesises latent fingerprints which approximate the distribution of real fingerprints. Our method trains a Rectified Flow model on embeddings extracted by pre-trained neural audio fingerprinting systems. The synthetic fingerprints generated using our system act as realistic distractors and enable the simulation of retrieval performance …