Year: 2020
Type: dissertation
Abstract: Automatic speaker recognition is used in authentication, surveillance, and forensic applications.Authentication applications use voice as a convenient method to access physical locations or log in to devices.For surveillance purposes, recognition technology can be used, for example, by security agencies to find a criminal by monitoring speech data on telephone networks.In forensic cases, the voices recorded from a crime scene may be analyzed and identified automatically to find clues and evidence relating to the crime.All the above applications benefit from the improvements to speaker recognition technology.The improvements can include increased speed, robustness, and security.Faster recognition systems help create a better user experience in authentication applications and facilitate surveillance by allowing more speech data to be processed in the same amount of time.Robustness helps in all applications by mitigating the detrimental effects caused by variabilities in speech, such as variation caused by recording devices, acoustic environments, and the speaker's health.Finally, the security of speaker recognition must be considered if the technology is used for authentication to minimize the risks associated with malicious use.This doctoral dissertation presents a versatile selection of studies on the above three topics: speed, robustness, and the security of automatic speaker recognition.The studies include both theoretical and experimental research as well as tutoriallike discussions, challenge organization work (ASVspoof 2019), and science popularization elements.In addition to the studies included in the dissertation, this dissertation offers a technical overview of the selected techniques commonly used in modern speaker recognition systems.The speed of speaker recognition systems is considered in three studies.The first study compares multiple fast-to-train speaker recognition systems based on dimensionality reduction of Gaussian mixture model (GMM) supervectors.The second study deploys one of the compared systems in a web application used for demonstrating speaker recognition technology to the public.This study focuses on recognition speed rather than the speed of training.In the last study, the training speed of the wellknown i-vector model is improved by performing computations using a graphics processing unit.Likewise, robustness is considered in three studies.The first two studies address the issue of mismatch between speaker enrollment and testing utterances by proposing robust acoustic features.The proposed features, based on time-varying linear prediction, reveal promising results in mismatch conditions caused by reverberation and changing the speaking style to whispering.The third study takes a different approach by focusing on the utterance-level features (embeddings) rather than on acoustic features.This study combines the ideas of GMMs, generative ivector models, and deep neural network-based feature extractors into a so-called neural i-vector model.v Finally, the topic of security is also discussed in three studies.These studies consider various kinds of spoofing attacks against automatic speaker verification (ASV) systems.The first one presents the ASVspoof 2019 challenge and its results.This challenge evaluated anti-spoofing methods against replayed, converted, and synthesized speech.The second study evaluates the effectiveness of mimicry attacks enhanced using technology-assisted target-speaker selection.The last study proposes so called worst-case false alarm rate metric, which can be used to evaluate the potential of technology-assisted target-speaker selection attacks.Additionally, the study proposes a generative model of ASV scores, which allows the estimation of the proposed metric for arbitrary speaker population sizes.In summary, this dissertation advances and supports speaker recognition research on multiple fronts.It provides some future directions for improving the core technology, and it supports further research on ASV security.It explains the peculiarities of speaker recognition for whispered speech, and it offers ideas on how to design engaging speaker recognition technology demonstrations.
Author: Ville Vestman
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3127842507
