Skip to main content
27th Telecommunications Forum, TELFOR 2019November 2019, Article number 897121527th Telecommunications Forum, TELFOR 2019; Belgrade; Serbia; 26 November 2019 through 27 November 2019; Category numberCFP1998P-CDR; Code 157254

Synthesized Speech Detection Based on Spectrogram and Convolutional Neural Networks(Conference Paper)

  • Nosek, T.,
  • Suzic, S.,
  • Papic, B.,
  • Jakovljevic, N.
  Save all to author list
  • University of Novi Sad, Faculty of Technical Sciences, Trg Dositeja Obradoviša 6, Novi Sad, 21102, Serbia

Abstract

The paper presents systems based on convolutional neural networks designed to classify genuine and artificially generated speech signals, which were evaluated on database for logical access designed for 3rd Automatic Speaker Verification Spoofing and Counter-measures Challenge (ASVspoof 2019). Proposed systems achieved remarkable results on the development set, but rather modest on the evaluation set, i.e. equal error rate on development set is 0 % and on evaluation set 9.57 %. © 2019 IEEE.

Author keywords

CNNspectrogramssynthesized speechvoice spoof

Indexed keywords

Engineering controlled terms:Classification (of information)ConvolutionSpectrographsSpeech recognition
Engineering uncontrolled termsAutomatic speaker verificationEqual error rateSpectrogramsSpeech signalsSynthesized speech
Engineering main heading:Convolutional neural networks

Funding details

Funding sponsor Funding number Acronym
Ministarstvo Prosvete, Nauke i Tehnološkog RazvojaTR 32035MPNTR

  • 1

    This work was supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia, TR 32035.

  • ISBN: 978-172814789-5
  • Source Type: Conference Proceeding
  • Original language: English
  • DOI: 10.1109/TELFOR48224.2019.8971215
  • Document Type: Conference Paper
  • Sponsors: "Telekom Srbija" a.d.,et al.,Ministry of Trade, Tourism and Telecommunications,Nokia,Temporary List,VLATACOM d.o.o
  • Publisher: Institute of Electrical and Electronics Engineers Inc.


© Copyright 2020 Elsevier B.V., All rights reserved.

Cited by 7 documents

Zaman, K. , Samiul, I.J.A.M. , Sah, M.
Hybrid Transformer Architectures with Diverse Audio Features for Deepfake Speech Classification
(2024) IEEE Access
Singh Yadav, A.K. , Xiang, Z. , Bhagtani, K.
PS3DT: Synthetic Speech Detection Using Patched Spectrogram Transformer
(2023) Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023
Singh Yadav, A.K. , Bhagtani, K. , Xiang, Z.
DSVAE: Disentangled Representation Learning for Synthetic Speech Detection
(2023) Proceedings - 22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023
View details of all 7 citations
Inform me when this document is cited in Scopus:
Set citation alert Set citation feed
{"topic":{"name":"Spoofing; Speech Communication; Speaker Verification","id":23255,"uri":"Topic/23255","prominencePercentile":95.235214,"prominencePercentileString":"95.235","overallScholarlyOutput":0},"dig":"97f1d8dfea852630451b92ae0e0056ab955661511aa7d5ee2ab32df0efd6d423"}

SciVal Topic Prominence

Topic:
Prominence percentile: