# ANIRA: An Architecture for Neural Network Inference in Real-Time Audio Applications

arXiv: https://arxiv.org/abs/2506.12665 · HTML: https://mlsanity.com/paper/2506.12665/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [RAVE: A variational autoencoder for fast and high-quality neural audio synthesis](https://mlsanity.com/paper/2111.05011/) (2021)
- [A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation](https://mlsanity.com/paper/2203.09893/) (2022)
- [Efficient neural networks for real-time modeling of analog dynamic range compression](https://mlsanity.com/paper/2102.06200/) (2021)
- [Sample Rate Independent Recurrent Neural Networks for Audio Effects Processing](https://mlsanity.com/paper/2406.06293/) (2024)
- [RTNeural: Fast Neural Inferencing for Real-Time Systems](https://mlsanity.com/paper/2106.03037/) (2021)
- [Pipeline for recording datasets and running neural networks on the Bela embedded hardware platform](https://mlsanity.com/paper/2306.11389/) (2023)

## Abstract (arXiv)

Numerous tools for neural network inference are currently available, yet many do not meet the requirements of real-time audio applications. In response, we introduce anira, an efficient cross-platform library. To ensure compatibility with a broad range of neural network architectures and frameworks, anira supports ONNX Runtime, LibTorch, and TensorFlow Lite as backends. Each inference engine exhibits real-time violations, which anira mitigates by decoupling the inference from the audio callback to a static thread pool. The library incorporates built-in latency management and extensive benchmarking capabilities, both crucial to ensure a continuous signal flow. Three different neural network architectures for audio effect emulation are then subjected to benchmarking across various configurations. Statistical modeling is employed to identify the influence of various factors on performance. The findings indicate that for stateless models, ONNX Runtime exhibits the lowest runtimes. For stateful models, LibTorch demonstrates the fastest performance. Our results also indicate that for certain model-engine combinations, the initial inferences take longer, particularly when these inferences exhibit a higher incidence of real-time violations.