Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911060092518400 |
|---|---|
| author | Passoni, Riccardo Ronchini, Francesca Comanducci, Luca Serizel, Romain Antonacci, Fabio |
| author_facet | Passoni, Riccardo Ronchini, Francesca Comanducci, Luca Serizel, Romain Antonacci, Fabio |
| contents | Text-to-audio models have recently emerged as a powerful technology for generating sound from textual descriptions. However, their high computational demands raise concerns about energy consumption and environmental impact. In this paper, we conduct an analysis of the energy usage of 7 state-of-the-art text-to-audio diffusion-based generative models, evaluating to what extent variations in generation parameters affect energy consumption at inference time. We also aim to identify an optimal balance between audio quality and energy consumption by considering Pareto-optimal solutions across all selected models. Our findings provide insights into the trade-offs between performance and environmental impact, contributing to the development of more efficient generative audio models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07615 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models Passoni, Riccardo Ronchini, Francesca Comanducci, Luca Serizel, Romain Antonacci, Fabio Audio and Speech Processing Artificial Intelligence Machine Learning Sound Text-to-audio models have recently emerged as a powerful technology for generating sound from textual descriptions. However, their high computational demands raise concerns about energy consumption and environmental impact. In this paper, we conduct an analysis of the energy usage of 7 state-of-the-art text-to-audio diffusion-based generative models, evaluating to what extent variations in generation parameters affect energy consumption at inference time. We also aim to identify an optimal balance between audio quality and energy consumption by considering Pareto-optimal solutions across all selected models. Our findings provide insights into the trade-offs between performance and environmental impact, contributing to the development of more efficient generative audio models. |
| title | Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models |
| topic | Audio and Speech Processing Artificial Intelligence Machine Learning Sound |
| url | https://arxiv.org/abs/2505.07615 |