SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems

Abstract

With the wide use of Automatic Speech Recognition (ASR) in applications such as human machine interaction, simultaneous interpretation, audio transcription, etc., its security protection becomes increasingly important. Although recent studies have brought to light the weaknesses of popular ASR systems that enable out-of-band signal attack, adversarial attack, etc., and further proposed various remedies (signal smoothing, adversarial training, etc.), a systematic understanding of ASR security (both attacks and defenses) is still missing, especially on how realistic such threats are and how general existing protection could be. In this paper, we present our systematization of knowledge for ASR security and provide a comprehensive taxonomy for existing work based on a modularized workflow. More importantly, we align the research in this domain with that on security in Image Recognition System (IRS), which has been extensively studied, using the domain knowledge in the latter to help understand where we stand in the former. Generally, both IRS and ASR are perceptual systems. Their similarities allow us to systematically study existing literature in ASR security based on the spectrum of attacks and defense solutions proposed for IRS, and pinpoint the directions of more advanced attacks and the directions potentially leading to more effective protection in ASR. In contrast, their differences, especially the complexity of ASR compared with IRS, help us learn unique challenges and opportunities in ASR security. Particularly, our experimental study shows that transfer attacks across ASR models is feasible, even in the absence of knowledge about models (even their types) and training data.

Automatic Speech Recognition Method Based on Deep Learning Approaches for Uzbek Language

“…ASR is an active and essential research area owing to its wide range of applications, such as security [ 2 ], education [ 3 ], smart healthcare [ 4 , 5 ], and smart cities [ 6 ], as well as the development of interfaces and computing instruments that can enable voice processing. It is a combination of various approaches that assist in the conversion of acoustic data into text, using text matching applied to the detected speech signal occurring in the result.…”