Article · 2008
Short communicationPublished 25 Jun 2021
Research on speaker recognition attack method based on GAN
Abstract
Select any words in the title or abstract, or press this and choose a sentence.
Voice recognition is a biometric identity authentication technology, also known as speaker recognition. Its theoretical basis is that each voice has a unique feature, which can effectively distinguish the voices of different people. Compared with other biometric technology, voice recognition has no loss and forgetting, does not need to remember, easy to use, and does not involve privacy, therefore, users are easy to accept this technology. Voice recognition can be widely used in security verification, control and other aspects, especially identity recognition in telecommute application scenarios. In this paper, a GAN-based timbre conversion system is studied and implemented. The forged audio generated by the timbre conversion is used to successfully attack the speaker recognition system. Firstly, according to the GAN, combined with the VCC2016 voice data set, a model which can transform audio files between different timbre is obtained. The model can extract the key features of the audio files from the data set, including Linear Predictive Cepstrum Coefficients (LPCC), MEL Frequency Cepstral Coefficients (MFCC). By means of short-time Fourier transform, Characteristic parameters get different audio feature, so the GAN makes the network master these laws between the data, thus it may carry on the fitting of audio features to generate the required forged audio files. Through the verification of the existing main speaker recognition algorithms, the method proposed in this paper can effectively attack the existing main speaker recognition technologies, which proves that the security of the current recognition system is defective, and it is urgent to improve its security. (Up to 250 words)
Keywords
Subjects
EducationAsk about this article
Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.
Similar by topic
Conference abstract · 23 Oct 2017
Improvement of speaker recognition tasks using deep learning and fusion features
Research article · 24 Jul 2013
The Community Engagement and Translational Research Speaker Series: An Innovative Model of Health Education
Commentary · 2 Jun 2023
The Significance of Automatic Speaker Recognition in Mobile Forensics
Rapid communication · 29 Sep 2021
Efficiency Enhancing Parameters in Speaker Recognition System
More from this journal
The newest in Educational Research.
Article · 29 Jan 2025
Exploring the Impact of the COVID-19 Pandemic on Employees' Work Life: A Case Study of St. Mary's College Kisubi and University of Kisubi
Article · 24 Jan 2025
A Study on Different National Educational Policy with Special Reference to the Indian Education System in India
Article · 23 Jan 2025
Exploring the Effectiveness and Challenges of the Bilingual Business English Major at Chinese Universities: Huazhong Agricultural University as a case study
Conferences in this field
Upcoming conferences in this field.
Follow
New articles from what you follow go into your email digest, once you agree to alert emails.
- JournalEducational Research
- SubjectEducation
- BylineArticles whose byline prints “Peishun Liu”
