Audio Spoof Detection from Theory to Practical Application

Audio Spoof Detection (ASD) systems play a pivotal role in evaluating whether the input speech signal has been manipulated by an imposter attempting unauthorized access to an authentic user's account or if it genuinely originates from the declared user. Primarily used for person authentication, these systems strive to verify the speaker's claimed identity. Despite substantial technological advancements, recent testing has revealed persistent vulnerabilities to spoofing, commonly referred to as a spoof attack. Various techniques such as mimicry, replay, text to speech (TTS), and voice conversion (VC) are frequently used in ASV systems to execute logical access (LA) or physical access (PA) spoofing attacks. To protect an ASD system from these attacks, many researchers have proposed effective security models as countermeasures. In addition, numerous review papers by different researchers have discussed various countermeasures developed to secure ASD systems. However, there is a notable absence of an authored book that comprehensively addresses this critical research topic, encompassing frontend, backend, dataset, and types of attacks considerations. Therefore, there is an urgent need for a book that can serve as a valuable resource for upcoming researchers, offering insights into securing ASD systems and bridging the existing gap in the literature. Hence, this book represents an effort by the authors in that direction.

Mohit Dua earned his Ph.D. in Automatic Speech Recognition from the National Institute of Technology, Kurukshetra, India, in 2018. He is presently working as an assistant professor in the Department of Computer Engineering at NIT Kurukshetra, India. He has more than 17 years of teaching and research experience. He is a member of Institute of Electrical and Electronics Engineers (IEEE), and life member of the Computer Society of India (CSI) and Indian Society for Technical Education (ISTE). His research interests include speech processing, chaos-based cryptography, information security, theory of formal languages, statistical modelling and natural language processing. He has published approximately 100+ research papers including abroad paper presentations in the USA, Canada, Australia, Singapore, Mauritius, and Dubai.

Nidhi Chakravarty earned her Ph.D. in Audio Spoof Detection from the National Institute of Technology, Kurukshetra, India, in 2024. She is presently working as an assistant professor in the Department of Computer Science and Engineering at Thapar Institute of Engineering and Technology, Patiala, India. She has published approximately 20+ research papers in various reputed journals and international conferences.

Shelza Dua earned her Ph.D. in Image Encryption from Banasthali Vidyapith, Banasthali Rajasthan, India, in 2019. She is presently working as a research associate in the Department of Electrical Engineering at NIT Kurukshetra, India. She has more than 20+ years of teaching and research experience. She is a life member of IETE. Her research interests include chaos-based cryptography and image encryption. She has published approximately 30+ research papers in various reputed journals and international conferences.