Tootfinder

I remember a time when I called a business and someone answered. Now when the phone is answered, I am immediately put on hold to listen to annoying computer generated music, then an announcement about how much they value my business, then a land acknowledgement, then a warning about abusive language or behaviour, then a number select menu, which does not include “talk to the receptionist”, then I pick a number and have to leave a message! 🤷😠

Improving AI-generated music with user-guided training
Vishwa Mohan Singh, Sai Anirudh Aryasomayajula, Ahan Chatterjee, Beste Aydemir, Rifat Mehreen Amin
https://arxiv.org/abs/2506.04852

Improving AI-generated music with user-guided training
AI music generation has advanced rapidly, with models like diffusion and autoregressive algorithms enabling high-fidelity outputs. These tools can alter styles, mix instruments, or isolate them. Since sound can be visualized as spectrograms, image-generation algorithms can be applied to generate novel music. However, these algorithms are typically trained on fixed datasets, which makes it challenging for them to interpret and respond to user input accurately. This is especially problematic beca…

Exploring listeners' perceptions of AI-generated and human-composed music for functional emotional applications
Kimaya Lecamwasam, Tishya Ray Chaudhuri
https://arxiv.org/abs/2506.02856

Exploring listeners' perceptions of AI-generated and human-composed music for functional emotional applications
This work investigates how listeners perceive and evaluate AI-generated as compared to human-composed music in the context of emotional resonance and regulation. Across a mixed-methods design, participants were exposed to both AI and human music under various labeling conditions (music correctly labeled as AI- or human-origin, music incorrectly labeled as AI- or human-origin, and unlabeled music) and emotion cases (Calm and Upbeat), and were asked to rate preference, efficacy of target emotion …

This https://arxiv.org/abs/2505.22238 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Yambda-5B -- A Large-Scale Multi-modal Dataset for Ranking And Retrieval
We present Yambda-5B, a large-scale open dataset sourced from the Yandex.Music streaming platform. Yambda-5B contains 4.79 billion user-item interactions from 1 million users across 9.39 million tracks. The dataset includes two primary types of interactions: implicit feedback (listening events) and explicit feedback (likes, dislikes, unlikes and undislikes). In addition, we provide audio embeddings for most tracks, generated by a convolutional neural network trained on audio spectrograms. A key…