# Quantum Vision Theory Applied to Audio Classification for Deepfake Speech Detection

arXiv: https://arxiv.org/abs/2604.08104 · HTML: https://mlsanity.com/paper/2604.08104/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 41 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection](https://mlsanity.com/paper/1904.05441/) (2019)
- [HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection](https://mlsanity.com/paper/2202.00874/) (2022)
- [SSAST: Self-Supervised Audio Spectrogram Transformer](https://mlsanity.com/paper/2110.09784/) (2021)
- [ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech](https://mlsanity.com/paper/2102.05889/) (2021)
- [StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion](https://mlsanity.com/paper/2107.10394/) (2021)
- [Deep Residual Neural Networks for Audio Spoofing Detection](https://mlsanity.com/paper/1907.00501/) (2019)
- [ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks](https://mlsanity.com/paper/1904.01120/) (2019)
- [SpoofCeleb: Speech Deepfake Detection and SASV In The Wild](https://mlsanity.com/paper/2409.17285/) (2024)
- [Multiscale Audio Spectrogram Transformer for Efficient Audio Classification](https://mlsanity.com/paper/2303.10757/) (2023)
- [ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification](https://mlsanity.com/paper/2211.13189/) (2022)
- [CAT: Causal Audio Transformer for Audio Classification](https://mlsanity.com/paper/2303.07626/) (2023)
- [S3T: Self-Supervised Pre-training with Swin Transformer for Music Classification](https://mlsanity.com/paper/2202.10139/) (2022)
- [Synthesized Speech Detection Using Convolutional Transformer-Based Spectrogram Analysis](https://mlsanity.com/paper/2205.01800/) (2022)
- [Frequency Domain-Based Detection of Generated Audio](https://mlsanity.com/paper/2205.01806/) (2022)

## Abstract (arXiv)

We propose Quantum Vision (QV) theory as a new perspective for deep learning-based audio classification, applied to deepfake speech detection. Inspired by particle-wave duality in quantum physics, QV theory is based on the idea that data can be represented not only in its observable, collapsed form, but also as information waves. In conventional deep learning, models are trained directly on these collapsed representations, such as images. In QV theory, inputs are first transformed into information waves using a QV block, and then fed into deep learning models for classification. QV-based models improve performance in image classification compared to their non-QV counterparts. What if QV theory is applied speech spectrograms for audio classification tasks? This is the motivation and novelty of the proposed approach. In this work, Short-Time Fourier Transform (STFT), Mel-spectrograms, and Mel-Frequency Cepstral Coefficients (MFCC) of speech signals are converted into information waves using the proposed QV block and used to train QV-based Convolutional Neural Networks (QV-CNN) and QV-based Vision Transformers (QV-ViT). Extensive experiments are conducted on the ASVSpoof dataset for deepfake speech classification. The results show that QV-CNN and QV-ViT consistently outperform standard CNN and ViT models, achieving higher classification accuracy and improved robustness in distinguishing genuine and spoofed speech. Moreover, the QV-CNN model using MFCC features achieves the best overall performance on the ASVspoof dataset, with an accuracy of 94.20% and an EER of 9.04%, while the QV-CNN with Mel-spectrograms attains the highest accuracy of 94.57%. These findings demonstrate that QV theory is an effective and promising approach for audio deepfake detection and opens new directions for quantum-inspired learning in audio perception tasks.