A Parameter-Efficient Multi-Scale Convolutional Adapter for Synthetic Speech Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kheir, Yassine El, Ritter-Guttierez, Fabian, Das, Arnab, Polzehl, Tim, Möller, Sebastian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915584948568064
author Kheir, Yassine El
Ritter-Guttierez, Fabian
Das, Arnab
Polzehl, Tim
Möller, Sebastian
author_facet Kheir, Yassine El
Ritter-Guttierez, Fabian
Das, Arnab
Polzehl, Tim
Möller, Sebastian
contents Recent synthetic speech detection models typically adapt a pre-trained SSL model via finetuning, which is computationally demanding. Parameter-Efficient Fine-Tuning (PEFT) offers an alternative. However, existing methods lack the specific inductive biases required to model the multi-scale temporal artifacts characteristic of spoofed audio. This paper introduces the Multi-Scale Convolutional Adapter (MultiConvAdapter), a parameter-efficient architecture designed to address this limitation. MultiConvAdapter integrates parallel convolutional modules within the SSL encoder, facilitating the simultaneous learning of discriminative features across multiple temporal resolutions, capturing both short-term artifacts and long-term distortions. With only $3.17$M trainable parameters ($1\%$ of the SSL backbone), MultiConvAdapter substantially reduces the computational burden of adaptation. Evaluations on five public datasets, demonstrate that MultiConvAdapter achieves superior performance compared to full fine-tuning and established PEFT methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24852
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Parameter-Efficient Multi-Scale Convolutional Adapter for Synthetic Speech Detection
Kheir, Yassine El
Ritter-Guttierez, Fabian
Das, Arnab
Polzehl, Tim
Möller, Sebastian
Sound
Recent synthetic speech detection models typically adapt a pre-trained SSL model via finetuning, which is computationally demanding. Parameter-Efficient Fine-Tuning (PEFT) offers an alternative. However, existing methods lack the specific inductive biases required to model the multi-scale temporal artifacts characteristic of spoofed audio. This paper introduces the Multi-Scale Convolutional Adapter (MultiConvAdapter), a parameter-efficient architecture designed to address this limitation. MultiConvAdapter integrates parallel convolutional modules within the SSL encoder, facilitating the simultaneous learning of discriminative features across multiple temporal resolutions, capturing both short-term artifacts and long-term distortions. With only $3.17$M trainable parameters ($1\%$ of the SSL backbone), MultiConvAdapter substantially reduces the computational burden of adaptation. Evaluations on five public datasets, demonstrate that MultiConvAdapter achieves superior performance compared to full fine-tuning and established PEFT methods.
title A Parameter-Efficient Multi-Scale Convolutional Adapter for Synthetic Speech Detection
topic Sound
url https://arxiv.org/abs/2510.24852