VOICE-BASED IDENTIFICATION AND CONTRIBUTION TO THE EFFICIENCY OF CRIMINAL PROCEEDINGS

Today, forensic voice identification is a powerful tool in the fight against crime, in situations where it is necessary to identify a suspect or to acquit an innocent person. In this type of expertise, multidisciplinary approach is applied in which several scientific disciplines are included - linguistics, phonetics, acoustics, psychology, mathematical statistics, law and criminalistics. The perpetrator’s voice is characterized by pitch, volume, timbre, or tone of the sound produced i.e., a series of individual characteristics that make each individual's voice, regardless of the variations expressed, suitable for identification. Some of these characteristics are natural features, determined by hereditary and physiological factors, and some are acquired habits. The aim of this paper is to present the most commonly used procedures and methods of analysis-assessment of voice and speech in order to identify persons as well as more modern approaches to the analysis of the speech signal.

Analysis of Methods and Techniques Used for Speaker Identification, Recognition, and Verification: A Study on Quarter-Century Research Outcomes

The theories and applications of speaker identification, recognition, and verification are among the well-established fields. Many publications and advances in the relevant products are still emerging. In this paper, research-related publications of the past 25 years (from 1996 to 2020) were studied and analysed. Our main focus was on speaker identification, speaker recognition, and speaker verification. The study was carried out using the Science Direct databases. Several references, such as review articles, research articles, encyclopaedia, book chapters, conference abstracts, and others, were categorized and investigated. Summary of these kinds of literature is presented in this paper, together with statistical analyses to represent the publications and their categories over the mentioned period. Important information, including the dataset used, the size of the data adopted, the implemented methods, and the accuracy of the obtained results in the analysed research, are extracted from the explored publications and tabulated. The results show that the sum of published research articles is outnumbering other categories of publications. The number of researches in speech and speaker identification, recognition, and verification shows an increasing trend. Based on the normalized comparative factors of research publications, we found that many of them reached a high level of accuracy in their findings; hence the significantly superior techniques were derived and discussed for future researches. This survey paper would be beneficial for all those who wish to enhance their researches in the area of voice identification, recognition, and verification.

Identifying unfamiliar voices: the influence of sample duration and parade size.

Voice identification parades can be unreliable due to the error-prone nature of earwitness responses. Home Office guidelines (2003) recommend that voice parades should consist of nine-voices, each played for 60-seconds. This makes parades resource-consuming to construct. In the present paper we conducted two experiments to see if voice parade procedures could be simplified. In Experiment 1, we investigated if reducing the duration of the voice samples on a nine-voice parade would negatively affect performance. In Experiment 2, we first explored if the same sample duration conditions used in Experiment 1 would lead to different outcomes if a six-voice parade were used. Following this, we investigated if there were any difference in identification performance based solely on whether a nine-voice (Experiment 1) or six-voice (Experiment 2) parade was used. Overall, the results suggest that voice durations can be safely reduced without disrupting listener performance. Performance on target-absent parades – which simulate an innocent suspect being apprehended – were at chance-levels in both parade sizes, but the increased number of foils in the nine-voice parade offers increased protection to an innocent suspect by virtue of statistical probability. Thus, we argue that the Home Office guidelines recommending a parade with nine-voices should be maintained.

Development of security systems using DNN and i & x-vector classifiers

The widespread use of biometric systems entails increased interest from cybercriminals aimed at developing attacks to crack them. Thus, the development of biometric identification systems must be carried out taking into account protection against these attacks. The development of new methods and algorithms for identification based on the presentation of randomly generated key features from the biometric base of user standards will help to minimize the disadvantages of the above methods of biometric identification of users. We present an implementation of a security system based on voice identification as an access control key and a verification algorithm developed using MATLAB function blocks that can authenticate a person's identity by his or her voice. Our research has shown an accuracy of 90 % for this user identification system for individual voice characteristics. It has been experimentally proven that traditional MFCCs using DNN and i and x-vector classifiers can achieve good results. The paper considers and analyzes the most well-known approaches from the literature to the problem of user identification by voice: dynamic programming methods, vector quantization, mixtures of Gaussian processes, hidden Markov model. The developed software package for biometric identification of users by voice and the method of forming the user's voice standards implemented in the complex allows reducing the number of errors in identifying users of information systems by voice by an average of 1.5 times. Our proposed system better defines voice recognition in terms of accuracy, security and complexity. The application of the results obtained will improve the security of the identification process in information systems from various attacks.

Pengaruh Perubahan Pitch dan Formant Terhadap Hasil Identifikasi Kepemilikan Suara Dengan Metode Audio Forensik

Audio forensics is a field of science that analyzes audio such as sound recordings. Voice recordings always have information in the form of frequency characteristics, the identities of these frequencies can be identified. Furthermore, an analysis of changes in pitch and formant will be carried out. This study used pitch analysis and analysis of variance on formants. With the correct procedure for handling recorded sound evidence which is then followed by procedural examination and analysis, it is hoped that the results of the voice recognition examination can scientifically show the ownership of the voice in the recording. Based on the results of the overall analysis of the sound recordings of evidence and comparison after carrying out various stages of analysis, the voice recordings are "not identical" from the same person. The thing that causes the inequality in voice identification is the difference in intonation or tone of the subject's speech when the voice is recorded.

A flexible method to create wave file features

Digital audio signal is one of the most important data type at present, it is used in various vital applications, such as human knowledge, security and banking applications, most applications require signal identification and recognition, and to increase the efficiency of these applications we must seek a method to represent the audio file by a small set of values called a features vector. In this paper research we will introduce an enhanced method of features extraction based on k-mean clustering. The method will be tested and implemented to show how the proposed method can reduce the efforts of voice identification, and can minimize the recognition time a set of voice extracted features must be used instead of using the voice wave file.