# A Model You Can Hear: Audio Identification with Playable Prototypes

arXiv: https://arxiv.org/abs/2208.03311 · HTML: https://mlsanity.com/paper/2208.03311/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Aug 2022.

## Built on by (most cited first, 6 of 6)

- [Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach](https://mlsanity.com/paper/2303.12533/) (2023)
- [Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio](https://mlsanity.com/paper/2402.09318/) (2024)
- [LMAC-TD: Producing Time Domain Explanations for Audio Classifiers](https://mlsanity.com/paper/2409.08655/) (2024)
- [MusicLIME: Explainable Multimodal Music Understanding](https://mlsanity.com/paper/2409.10496/) (2024)
- [Semantic-Aware Interpretable Multimodal Music Auto-Tagging](https://mlsanity.com/paper/2505.17233/) (2025)
- [Are Inherently Interpretable Models More Robust? A Study In Music Emotion Recognition](https://mlsanity.com/paper/2508.03780/) (2025)

## Abstract (arXiv)

Machine learning techniques have proved useful for classifying and analyzing audio content. However, recent methods typically rely on abstract and high-dimensional representations that are difficult to interpret. Inspired by transformation-invariant approaches developed for image and 3D data, we propose an audio identification model based on learnable spectral prototypes. Equipped with dedicated transformation networks, these prototypes can be used to cluster and classify input audio samples from large collections of sounds. Our model can be trained with or without supervision and reaches state-of-the-art results for speaker and instrument identification, while remaining easily interpretable. The code is available at: https://github.com/romainloiseau/a-model-you-can-hear