Quantum Vision Theory Applied to Audio Classification for Deepfake Speech Detection
2026-04-09 • Computation and Language
Computation and Language
AI summaryⓘ
The authors introduce Quantum Vision (QV) theory, inspired by quantum physics ideas, to improve deep learning models for detecting fake speech. Instead of using usual audio features directly, they first turn these features into 'information waves' with a QV block before training models. Experiments on a deepfake speech dataset show that QV-based models perform better than regular ones in telling real from fake speech. Their results suggest that QV theory can help make audio detection tasks more accurate and reliable.
Quantum Vision (QV) theorydeepfake speech detectionShort-Time Fourier Transform (STFT)Mel-spectrogramMel-Frequency Cepstral Coefficients (MFCC)Convolutional Neural Networks (CNN)Vision Transformers (ViT)audio classificationinformation wavesASVspoof dataset
Authors
Khalid Zaman, Melike Sah, Anuwat Chaiwongyenc, Cem Direkoglu
Abstract
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.