# CAT: Causal Audio Transformer for Audio Classification

arXiv: https://arxiv.org/abs/2303.07626 · HTML: https://mlsanity.com/paper/2303.07626/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2023.

## Built on by (most cited first, 10 of 10)

- [Explore Spurious Correlations at the Concept Level in Language Models for Text Classification](https://mlsanity.com/paper/2311.08648/) (2023)
- [TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining](https://mlsanity.com/paper/2505.07609/) (2025)
- [C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder](https://mlsanity.com/paper/2310.17325/) (2023)
- [Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/2406.13114/) (2024)
- [CSRec: Rethinking Sequential Recommendation from A Causal Perspective](https://mlsanity.com/paper/2409.05872/) (2024)
- [Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning](https://mlsanity.com/paper/2508.06382/) (2025)
- [EAViT: External Attention Vision Transformer for Audio Classification](https://mlsanity.com/paper/2408.13201/) (2024)
- [Transformer-based Sequence Labeling for Audio Classification based on MFCCs](https://mlsanity.com/paper/2305.00417/) (2023)
- [Abjad-Kids: An Arabic Speech Classification Dataset for Primary Education](https://mlsanity.com/paper/2603.20255/) (2026)
- [Quantum Vision Theory Applied to Audio Classification for Deepfake Speech Detection](https://mlsanity.com/paper/2604.08104/) (2026)

## Abstract (arXiv)

The attention-based Transformers have been increasingly applied to audio classification because of their global receptive field and ability to handle long-term dependency. However, the existing frameworks which are mainly extended from the Vision Transformers are not perfectly compatible with audio signals. In this paper, we introduce a Causal Audio Transformer (CAT) consisting of a Multi-Resolution Multi-Feature (MRMF) feature extraction with an acoustic attention block for more optimized audio modeling. In addition, we propose a causal module that alleviates over-fitting, helps with knowledge transfer, and improves interpretability. CAT obtains higher or comparable state-of-the-art classification performance on ESC50, AudioSet and UrbanSound8K datasets, and can be easily generalized to other Transformer-based models.