Voice spoofing detection corpus for single and multi-order audio replays. (January 2021)

• Record Type: Journal Article
• Authors: Baumann, Roland; Malik, Khalid Mahmood; Javed, Ali; Ball, Andersen; Kujawa, Brandon; Malik, Hafiz
• Is Part Of: Computer speech & language. Volume 65(2021)
• Publication Date: 2021-01
• Subjects: Multi-order voice replay attack -- Internet of multimedia things -- Voice replay spoofing -- Voice controlled devices -- Automatic speaker verification anti-spoofing -- Voice spoofing dataset; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2020.101132
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Development of a large-scale dataset for evaluation of audio forensics testbed. Development of a multi-order replay spoofing dataset consisting of bonafide, first-order replay and second-order replay samples that can effectively be used to evaluate the performance of anti-spoofing methods in multi-hop scenarios. A diverse replay spoofing detection corpus in terms of environment, recording and playback devices, human speakers, configurations, replay scenarios, etc. More specifically, we used 35 microphones, 25 unique recording configurations, 60 unique playback configurations to generate 14, 050 samples belonging to 19 human speakers of different age and gender. The proposed voice spoofing detection corpus can effectively be used for speaker verification as our dataset contain audio samples of 19 different speakers. Abstract: The evolution of modern voice-controlled devices (VCDs) has revolutionized the Internet of Things (IoT) and resulted in the increased realization of smart homes, personalization, and home automation through voice commands. These VCDs can be exploited in IoT driven environments to generate various spoofing attacks, including the chaining of replay attacks (i.e. multi-order replay attacks). Existing datasets like ASVspoof 2017, ASVspoof 2019, and ReMASC contain only first-order replay recordings (i.e. replayed once); therefore, they cannot offer evaluation of anti-spoofing algorithms capable of detecting multi-order replay attacks. Additionally, large-scale datasets like ASVspoof 2017 and ASVspoof 2019 do not capture the characteristics of microphone arrays, which are an essential characteristic of modern VCDs. Therefore, there exists a need for a diverse replay spoofing detection corpus that consists of multi-order replay recordings against bona fide voice samples. This paper presents a novel voice spoofing detection corpus (VSDC) to evaluate the performance of multi-order replay anti-spoofing methods. The proposed VSDC consists of first-order (i.e. replayed once) and second-order replay (i.e. replayed twice) samples against the bona fide audio recordings. We ensured to create a diverse replay spoofing detection corpus in terms of environments, recording and playback devices, speakers, configurations, replay scenarios, etc. More specifically, we used 35 microphones, 25 different recording configurations, and 60 different playback configurations for first- and second-order replays to generate a total of 14, 050 samples belonging to 19 speakers. Additionally, the proposed VSDC can also be used to evaluate the performance of speaker verification systems in terms of independent speaker verification. To the best of our knowledge, this is the first publicly available replay spoofing detection corpus comprised of first and second-order replay samples. Experimental results signify the effectiveness of the proposed VSDC in terms of evaluating the performance of anti-spoofing methods under multi-order replay attacks and diverse conditions.