Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Phukan, Orchid Chetia, Jain, Sarthak, Behera, Swarup Ranjan, Buduru, Arun Balaji, Sharma, Rajesh, Prasanna, S. R Mahadeva
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914954545725440
author Phukan, Orchid Chetia
Jain, Sarthak
Behera, Swarup Ranjan
Buduru, Arun Balaji
Sharma, Rajesh
Prasanna, S. R Mahadeva
author_facet Phukan, Orchid Chetia
Jain, Sarthak
Behera, Swarup Ranjan
Buduru, Arun Balaji
Sharma, Rajesh
Prasanna, S. R Mahadeva
contents In this study, for the first time, we extensively investigate whether music foundation models (MFMs) or speech foundation models (SFMs) work better for singing voice deepfake detection (SVDD), which has recently attracted attention in the research community. For this, we perform a comprehensive comparative study of state-of-the-art (SOTA) MFMs (MERT variants and music2vec) and SFMs (pre-trained for general speech representation learning as well as speaker recognition). We show that speaker recognition SFM representations perform the best amongst all the foundation models (FMs), and this performance can be attributed to its higher efficacy in capturing the pitch, tone, intensity, etc, characteristics present in singing voices. To our end, we also explore the fusion of FMs for exploiting their complementary behavior for improved SVDD, and we propose a novel framework, FIONA for the same. With FIONA, through the synchronization of x-vector (speaker recognition SFM) and MERT-v1-330M (MFM), we report the best performance with the lowest Equal Error Rate (EER) of 13.74 %, beating all the individual FMs as well as baseline FM fusions and achieving SOTA results.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14131
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models
Phukan, Orchid Chetia
Jain, Sarthak
Behera, Swarup Ranjan
Buduru, Arun Balaji
Sharma, Rajesh
Prasanna, S. R Mahadeva
Audio and Speech Processing
Machine Learning
Sound
68T45
I.2.7
In this study, for the first time, we extensively investigate whether music foundation models (MFMs) or speech foundation models (SFMs) work better for singing voice deepfake detection (SVDD), which has recently attracted attention in the research community. For this, we perform a comprehensive comparative study of state-of-the-art (SOTA) MFMs (MERT variants and music2vec) and SFMs (pre-trained for general speech representation learning as well as speaker recognition). We show that speaker recognition SFM representations perform the best amongst all the foundation models (FMs), and this performance can be attributed to its higher efficacy in capturing the pitch, tone, intensity, etc, characteristics present in singing voices. To our end, we also explore the fusion of FMs for exploiting their complementary behavior for improved SVDD, and we propose a novel framework, FIONA for the same. With FIONA, through the synchronization of x-vector (speaker recognition SFM) and MERT-v1-330M (MFM), we report the best performance with the lowest Equal Error Rate (EER) of 13.74 %, beating all the individual FMs as well as baseline FM fusions and achieving SOTA results.
title Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models
topic Audio and Speech Processing
Machine Learning
Sound
68T45
I.2.7
url https://arxiv.org/abs/2409.14131