Robust Spoofed Speech Detection via Temporal Pyramid Modeling

Authors: Mahtab Masoudi Nezhad, Nima Karimian

Published: 2026-06-15 15:16:10+00:00

AI Summary

This work introduces a Temporal Pyramid Adapter to enhance spoofed speech detection, addressing challenges in cross-dataset generalization and multilingual robustness. It leverages parallel temporal convolutions with varying receptive fields to capture multi-scale spoofing cues, integrated with self-supervised XLS-R representations. The proposed model significantly outperforms existing baselines on benchmarks like PartialSpoof, achieving superior AUC and EER, while highlighting the need for better adaptation strategies under domain and language shifts.

Abstract

Spoofed speech detection is increasingly challenged by realistic synthesis, voice conversion, and replay attacks, with cross-dataset generalization remaining a major limitation. This work we propose a Temporal Pyramid Adapter that utilize parallel temporal convolutions with varying receptive fields to capture multi-scale spoofing cues, ranging from local artifacts to global prosodic irregularities. We also integrated self-supervised XLS-R representations combined with front-end adapters, including Mel, Sinc, and a Temporal Pyramid design for multi-scale temporal modeling. The proposed model is evaluated cross multiple benchmark including ASVspoof 2017, ASVspoof 2021 (DF/LA), PartialSpoof, DiffSSD, and multilingual HQ-MPSD datasets. Experimental results demonstrate that Temporal Pyramid model obtained AUC of 99.24% and a EER of 3.87% on the PartialSpoof database, which is significantly outperforming the base model and several SOTA baseline such as LCNN-BLSTM (9.87% EER) and TRACE (8.08% EER). Additionally, multilingual evaluations confirm that while spoofing artifact are independent from language. While self-supervised representations improve robustness, performance degrades under domain and language shifts, highlighting the need for better adaptation and calibration strategies.