Towards Explainable Spoofed Speech Attribution and Detection:a Probabilistic Approach for Characterizing Speech Synthesizer Components

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mishra, Jagabandhu, Chhibber, Manasi, Shim, Hye-jin, Kinnunen, Tomi H.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912407666819072
author Mishra, Jagabandhu
Chhibber, Manasi
Shim, Hye-jin
Kinnunen, Tomi H.
author_facet Mishra, Jagabandhu
Chhibber, Manasi
Shim, Hye-jin
Kinnunen, Tomi H.
contents We propose an explainable probabilistic framework for characterizing spoofed speech by decomposing it into probabilistic attribute embeddings. Unlike raw high-dimensional countermeasure embeddings, which lack interpretability, the proposed probabilistic attribute embeddings aim to detect specific speech synthesizer components, represented through high-level attributes and their corresponding values. We use these probabilistic embeddings with four classifier back-ends to address two downstream tasks: spoofing detection and spoofing attack attribution. The former is the well-known bonafide-spoof detection task, whereas the latter seeks to identify the source method (generator) of a spoofed utterance. We additionally use Shapley values, a widely used technique in machine learning, to quantify the relative contribution of each attribute value to the decision-making process in each task. Results on the ASVspoof2019 dataset demonstrate the substantial role of duration and conversion modeling in spoofing detection; and waveform generation and speaker modeling in spoofing attack attribution. In the detection task, the probabilistic attribute embeddings achieve $99.7\%$ balanced accuracy and $0.22\%$ equal error rate (EER), closely matching the performance of raw embeddings ($99.9\%$ balanced accuracy and $0.22\%$ EER). Similarly, in the attribution task, our embeddings achieve $90.23\%$ balanced accuracy and $2.07\%$ EER, compared to $90.16\%$ and $2.11\%$ with raw embeddings. These results demonstrate that the proposed framework is both inherently explainable by design and capable of achieving performance comparable to raw CM embeddings.
format Preprint
id arxiv_https___arxiv_org_abs_2502_04049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Explainable Spoofed Speech Attribution and Detection:a Probabilistic Approach for Characterizing Speech Synthesizer Components
Mishra, Jagabandhu
Chhibber, Manasi
Shim, Hye-jin
Kinnunen, Tomi H.
Audio and Speech Processing
We propose an explainable probabilistic framework for characterizing spoofed speech by decomposing it into probabilistic attribute embeddings. Unlike raw high-dimensional countermeasure embeddings, which lack interpretability, the proposed probabilistic attribute embeddings aim to detect specific speech synthesizer components, represented through high-level attributes and their corresponding values. We use these probabilistic embeddings with four classifier back-ends to address two downstream tasks: spoofing detection and spoofing attack attribution. The former is the well-known bonafide-spoof detection task, whereas the latter seeks to identify the source method (generator) of a spoofed utterance. We additionally use Shapley values, a widely used technique in machine learning, to quantify the relative contribution of each attribute value to the decision-making process in each task. Results on the ASVspoof2019 dataset demonstrate the substantial role of duration and conversion modeling in spoofing detection; and waveform generation and speaker modeling in spoofing attack attribution. In the detection task, the probabilistic attribute embeddings achieve $99.7\%$ balanced accuracy and $0.22\%$ equal error rate (EER), closely matching the performance of raw embeddings ($99.9\%$ balanced accuracy and $0.22\%$ EER). Similarly, in the attribution task, our embeddings achieve $90.23\%$ balanced accuracy and $2.07\%$ EER, compared to $90.16\%$ and $2.11\%$ with raw embeddings. These results demonstrate that the proposed framework is both inherently explainable by design and capable of achieving performance comparable to raw CM embeddings.
title Towards Explainable Spoofed Speech Attribution and Detection:a Probabilistic Approach for Characterizing Speech Synthesizer Components
topic Audio and Speech Processing
url https://arxiv.org/abs/2502.04049