Saved in:
Bibliographic Details
Main Authors: Sheth, Farhan, Girish, Akhtar, Mohd Mujtaba, Singh, Muskaan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.10793
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915616561037312
author Sheth, Farhan
Girish
Akhtar, Mohd Mujtaba
Singh, Muskaan
author_facet Sheth, Farhan
Girish
Akhtar, Mohd Mujtaba
Singh, Muskaan
contents In this work, we address the challenge of generalizable audio deepfake detection (ADD) across diverse speech synthesis paradigms-including conventional text-to-speech (TTS) systems and modern diffusion or flow-matching (FM) based generators. Prior work has mostly targeted individual synthesis families and often fails to generalize across paradigms due to overfitting to generation-specific artifacts. We hypothesize that synthetic speech, irrespective of its generative origin, leaves behind shared structural distortions in the embedding space that can be aligned through geometry-aware modeling. To this end, we propose RHYME, a unified detection framework that fuses utterance-level embeddings from diverse pretrained speech encoders using non-Euclidean projections. RHYME maps representations into hyperbolic and spherical manifolds-where hyperbolic geometry excels at modeling hierarchical generator families, and spherical projections capture angular, energy-invariant cues such as periodic vocoder artifacts. The fused representation is obtained via Riemannian barycentric averaging, enabling synthesis-invariant alignment. RHYME outperforms individual PTMs and homogeneous fusion baselines, achieving top performance and setting new state-of-the-art in cross-paradigm ADD.
format Preprint
id arxiv_https___arxiv_org_abs_2511_10793
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Curved Worlds, Clear Boundaries: Generalizing Speech Deepfake Detection using Hyperbolic and Spherical Geometry Spaces
Sheth, Farhan
Girish
Akhtar, Mohd Mujtaba
Singh, Muskaan
Audio and Speech Processing
In this work, we address the challenge of generalizable audio deepfake detection (ADD) across diverse speech synthesis paradigms-including conventional text-to-speech (TTS) systems and modern diffusion or flow-matching (FM) based generators. Prior work has mostly targeted individual synthesis families and often fails to generalize across paradigms due to overfitting to generation-specific artifacts. We hypothesize that synthetic speech, irrespective of its generative origin, leaves behind shared structural distortions in the embedding space that can be aligned through geometry-aware modeling. To this end, we propose RHYME, a unified detection framework that fuses utterance-level embeddings from diverse pretrained speech encoders using non-Euclidean projections. RHYME maps representations into hyperbolic and spherical manifolds-where hyperbolic geometry excels at modeling hierarchical generator families, and spherical projections capture angular, energy-invariant cues such as periodic vocoder artifacts. The fused representation is obtained via Riemannian barycentric averaging, enabling synthesis-invariant alignment. RHYME outperforms individual PTMs and homogeneous fusion baselines, achieving top performance and setting new state-of-the-art in cross-paradigm ADD.
title Curved Worlds, Clear Boundaries: Generalizing Speech Deepfake Detection using Hyperbolic and Spherical Geometry Spaces
topic Audio and Speech Processing
url https://arxiv.org/abs/2511.10793