Spatial Reconstructed Local Attention Res2Net with F0 Subband for Fake Speech Detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fan, Cunhang, Xue, Jun, Tao, Jianhua, Yi, Jiangyan, Wang, Chenglong, Zheng, Chengshi, Lv, Zhao
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929412207804416
author Fan, Cunhang
Xue, Jun
Tao, Jianhua
Yi, Jiangyan
Wang, Chenglong
Zheng, Chengshi
Lv, Zhao
author_facet Fan, Cunhang
Xue, Jun
Tao, Jianhua
Yi, Jiangyan
Wang, Chenglong
Zheng, Chengshi
Lv, Zhao
contents The rhythm of bonafide speech is often difficult to replicate, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real speech. It is expected that the F0 feature contains the discriminative information for the fake speech detection (FSD) task. In this paper, we propose a novel F0 subband for FSD. In addition, to effectively model the F0 subband so as to improve the performance of FSD, the spatial reconstructed local attention Res2Net (SR-LA Res2Net) is proposed. Specifically, Res2Net is used as a backbone network to obtain multiscale information, and enhanced with a spatial reconstruction mechanism to avoid losing important information when the channel group is constantly superimposed. In addition, local attention is designed to make the model focus on the local information of the F0 subband. Experimental results on the ASVspoof 2019 LA dataset show that our proposed method obtains an equal error rate (EER) of 0.47% and a minimum tandem detection cost function (min t-DCF) of 0.0159, achieving the state-of-the-art performance among all of the single systems.
format Preprint
id arxiv_https___arxiv_org_abs_2308_09944
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Spatial Reconstructed Local Attention Res2Net with F0 Subband for Fake Speech Detection
Fan, Cunhang
Xue, Jun
Tao, Jianhua
Yi, Jiangyan
Wang, Chenglong
Zheng, Chengshi
Lv, Zhao
Sound
Audio and Speech Processing
The rhythm of bonafide speech is often difficult to replicate, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real speech. It is expected that the F0 feature contains the discriminative information for the fake speech detection (FSD) task. In this paper, we propose a novel F0 subband for FSD. In addition, to effectively model the F0 subband so as to improve the performance of FSD, the spatial reconstructed local attention Res2Net (SR-LA Res2Net) is proposed. Specifically, Res2Net is used as a backbone network to obtain multiscale information, and enhanced with a spatial reconstruction mechanism to avoid losing important information when the channel group is constantly superimposed. In addition, local attention is designed to make the model focus on the local information of the F0 subband. Experimental results on the ASVspoof 2019 LA dataset show that our proposed method obtains an equal error rate (EER) of 0.47% and a minimum tandem detection cost function (min t-DCF) of 0.0159, achieving the state-of-the-art performance among all of the single systems.
title Spatial Reconstructed Local Attention Res2Net with F0 Subband for Fake Speech Detection
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2308.09944