paper-with-me

홈 › Papers

Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice

2024-06-14 · Shubham Gupta, Mirco Ravanelli, Pascal Germain, Cem Subakan

In this paper, we propose Phoneme Discretized Saliency Maps (PDSM), a discretization algorithm for saliency maps that takes advantage of phoneme boundaries for explainable detection of AI-generated voice. We experimentally show with two different Text-to-Speech systems (i.e., Tacotron2 and Fastspeech2) that the proposed algorithm produces saliency maps that result in more faithful explanations compared to standard posthoc explanation methods. Moreover, by associating the saliency maps to the phoneme representations, this methodology generates explanations that tend to be more understandable than standard saliency maps on magnitude spectrograms.

📄 PDF Abstract BibTeX arXiv:2406.10422

Code (0)

등록된 구현이 없습니다.

Tasks

text-to-speechText to Speech

Similar Papers 제목 키워드 기반

SESS: Saliency Enhancing with Scaling and Sliding

2022-07-05 · Osman Tursun, Simon Denman, Sridha Sridharan, Clinton Fookes

High-quality saliency maps are essential in several machine learning application areas including explainable AI and weakly supervised object detection and segmentation. Many techniques have been developed to generate bet…

Explainable artificial intelligenceObject DetectionObject RecognitionWeakly Supervised Object Detection+1

Explainable Deep Neural Network for Multimodal ECG Signals: Intermediate vs Late Fusion

2025-08-06 · Timothy Oladunni, Ehimen Aneni arxiv

The limitations of unimodal deep learning models, particularly their tendency to overfit and limited generalizability, have renewed interest in multimodal fusion strategies. Multimodal deep neural networks (MDNN) have th…

Explainable Image Quality Assessment for Medical Imaging

2023-03-25 · Caner Ozer, Arda Guler, Aysel Turkvatan Cansever, Ilkay Oksuz

Medical image quality assessment is an important aspect of image acquisition, as poor-quality images may lead to misdiagnosis. Manual labelling of image quality is a tedious task for population studies and can lead to mi…

Image Quality AssessmentObjectobject-detectionObject Detection+1

Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models

2023-05-05 · Guoyang Liu, Jindi Zhang, Antoni B. Chan, Janet H. Hsiao

We examined whether embedding human attention knowledge into saliency-based explainable AI (XAI) methods for computer vision models could enhance their plausibility and faithfulness. We first developed new gradient-based…

ClassificationExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)image-classification+4

Deriving Explanation of Deep Visual Saliency Models

2021-09-08 · Sai Phani Kumar Malladi, Jayanta Mukhopadhyay, Chaker Larabi, Santanu Chaudhury

Deep neural networks have shown their profound impact on achieving human level performance in visual saliency prediction. However, it is still unclear how they learn the task and what it means in terms of understanding h…

Explainable ModelsSaliency Prediction