Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2407.04333

PAGURI: a user experience study of creative interaction with text-to-music models

Francesca Ronchini·Luca Comanducci·Gabriele Perego·Fabio Antonacci
View original source ↗Read source document ↗Export metadata ↓

Abstract

In recent years, text-to-music models have been the biggest breakthrough in automatic music generation. While they are unquestionably a showcase of technological progress, it is not clear yet how they can be realistically integrated into the artistic practice of musicians and music practitioners. This paper aims to address this question via Prompt Audio Generation User Research Investigation (PAGURI), a user experience study where we leverage recent text-to-music developments to study how musicians and practitioners interact with these systems, evaluating their satisfaction levels. We developed an online tool through which users can generate music samples and/or apply recently proposed personalization techniques based on fine-tuning to allow the text-to-music model to generate sounds closer to their needs and preferences. Using semi-structured interviews, we analyzed different aspects related to how participants interacted with the proposed tool to understand the current effectiveness and limitations of text-to-music models in enhancing users' creativity. Our research centers on user experiences to uncover insights that can guide the future development of TTM models and their role in AI-driven music creation. Additionally, they offered insightful perspectives on potential system improvements and their integration into their music practices. The results obtained through the study reveal the pros and cons of the use of TTMs for creative endeavors. Participants recognized the system's creative potential and appreciated the usefulness of its personalization features. However, they also identified several challenges that must be addressed before TTMs are ready for real-world music creation, particularly issues of prompt ambiguity, limited controllability, and integration into existing workflows.

Explore related subjects

cs.SDeess.AS

Keep this discovery

BibTeXRIS

Francesca Ronchini, Luca Comanducci, Gabriele Perego, Fabio Antonacci. 2024-07-05. PAGURI: a user experience study of creative interaction with text-to-music models. https://doi.org/10.3390/electronics14173379

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Xiaomi-CocktailASR-1 Technical Report

Recently, large language model (LLM) based ASR models have achieved significant progress, yet they generally lack support for multi-speaker scenarios, where the cocktail party problem remains a critical bottleneck for further advancing ASR. Existing TS-ASR methods, including end-to-end architectures with speaker embeddings and latest LLM-based explorations suffer from degraded single-speaker performance and the inability to reject when the target speaker is absent. In this paper, we propose Xiaomi-CocktailASR-1, an LLM-based end-to-end TS-ASR architecture. By utilizing reference speech as voiceprint prompts, it directly transcribes the target speaker's speech without requiring speech separation. Xiaomi-CocktailASR-1 maintains competitive performance in single-speaker scenarios, comparable to mainstream ASR models. It also features a negative sample rejection capability, outputting empty text when the target speaker is absent from the mixed speech. Additionally, Xiaomi-CocktailASR-1 supports a Chain-of-Thought (CoT) reasoning mode to provide explicit reasoning steps. Extensive experiments on various synthetic and real-world multispeaker benchmarks demonstrate that Xiaomi-CocktailASR-1 achieves state-of-the-art performance, effectively addressing the cocktail party problem through a unified architecture that balances multispeaker and single-speaker recognition accuracy, along with rejection capability.

cs.SD↗
arXiv2026

EConv-TasNet: Efficient Conv-TasNet for Effective Speech Separation

Conv-TasNet has served as a strong baseline for time-domain speech separation, and many studies have extended it with advanced architectures such as dual-path networks, U-Nets, and attention mechanisms. However, these methods often introduce high computational cost and complexity, limiting their deployment in resource-constrained scenarios. To address this issue, we propose eConv-TasNet, an efficient variant of Conv-TasNet that improves both effectiveness and efficiency without relying on resource-intensive modules. The proposed model consists of a group-wise early-splitting (GES) module and a multi-group feature aggregation (MGFA) module. GES generates discriminative speaker embeddings at intermediate stages, while MGFA progressively aggregates these group-level representations for refined mask estimation. Experimental results show that eConv-TasNet reduces model size by 22.4%, accelerates inference by 18.9%, and improves SI-SNRi by 14.0%-28.0% across three public benchmarks. Moreover, it achieves competitive performance compared with state-of-the-art methods while requiring significantly fewer parameters and lower inference cost. These results demonstrate a favorable efficiency-effectiveness trade-off for edge deployment.

cs.SD↗