# Energy Consumption of Deep Generative Audio Models

arXiv: https://arxiv.org/abs/2107.02621 · HTML: https://mlsanity.com/paper/2107.02621/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 22 references that are in the map.
- First posted on arXiv 6 Jul 2021.

## Builds on (most cited first, 19 of 19)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [A note on the evaluation of generative models](https://mlsanity.com/paper/1511.01844/) (2015)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models](https://mlsanity.com/paper/2007.03051/) (2020)
- [GANSynth: Adversarial Neural Audio Synthesis](https://mlsanity.com/paper/1902.08710/) (2019)
- [SampleRNN: An Unconditional End-to-End Neural Audio Generation Model](https://mlsanity.com/paper/1612.07837/) (2016)
- [FloWaveNet : A Generative Flow for Raw Audio](https://mlsanity.com/paper/1811.02155/) (2018)
- [Measuring the Algorithmic Efficiency of Neural Networks](https://mlsanity.com/paper/2005.04305/) (2020)
- [WaveFlow: A Compact Flow-based Model for Raw Audio](https://mlsanity.com/paper/1912.01219/) (2019)
- [SING: Symbol-to-Instrument Neural Generator](https://mlsanity.com/paper/1810.09785/) (2018)
- [Deep generative models for musical audio synthesis](https://mlsanity.com/paper/2006.06426/) (2020)

## Built on by (most cited first, 12 of 12)

- [The Ethical Implications of Generative Audio Models: A Systematic Literature Review](https://mlsanity.com/paper/2307.05527/) (2023)
- [Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle](https://mlsanity.com/paper/2303.01980/) (2023)
- [From Computation to Consumption: Exploring the Compute-Energy Link for Training and Testing Neural Networks for SED Systems](https://mlsanity.com/paper/2409.05080/) (2024)
- [And what if two musical versions don't share melody, harmony, rhythm, or lyrics ?](https://mlsanity.com/paper/2210.01256/) (2022)
- [Sound Check: Auditing Audio Datasets](https://mlsanity.com/paper/2410.13114/) (2024)
- [Small is Sufficient: Reducing the World AI Energy Consumption Through Model Selection](https://mlsanity.com/paper/2510.01889/) (2025)
- [Energy Consumption Trends in Sound Event Detection Systems](https://mlsanity.com/paper/2409.08763/) (2024)
- [Diffused Responsibility: Analyzing the Energy Consumption of Generative Text-to-Audio Diffusion Models](https://mlsanity.com/paper/2505.07615/) (2025)
- [Normalizing Energy Consumption for Hardware-Independent Evaluation](https://mlsanity.com/paper/2409.05602/) (2024)
- [Bringing together invertible UNets with invertible attention modules for memory-efficient diffusion models](https://mlsanity.com/paper/2504.10883/) (2025)
- [Detecting Musical Deepfakes](https://mlsanity.com/paper/2505.09633/) (2025)
- [Exposing the Cost of Deep Learning Audio Development](https://mlsanity.com/paper/2610.01619/) (2026)

## Abstract (arXiv)

In most scientific domains, the deep learning community has largely focused on the quality of deep generative models, resulting in highly accurate and successful solutions. However, this race for quality comes at a tremendous computational cost, which incurs vast energy consumption and greenhouse gas emissions. At the heart of this problem are the measures that we use as a scientific community to evaluate our work. In this paper, we suggest relying on a multi-objective measure based on Pareto optimality, which takes into account both the quality of the model and its energy consumption. By applying our measure on the current state-of-the-art in generative audio models, we show that it can drastically change the significance of the results. We believe that this type of metric can be widely used by the community to evaluate their work, while putting computational cost -- and in fine energy consumption -- in the spotlight of deep learning research.