Development of a regional voice dataset and speaker classification based on machine learning (original) (raw)
2021, Journal of Big Data
At present, voice biometrics are commonly used for identification and authentication of users through their voice. Voice based services such as mobile banking, access to personal devices, and logging into social networks are the common examples of authenticating users through voice biometrics. In Pakistan, voice-based services are very common in banking and mobile/cellular sector, however, these services do not use voice features to recognize customers. Therefore, the chance to use these services with false identity is always high. It is essential to design a voice-based recognition system to minimize the risk of false identity. In this paper, we developed regional voice datasets for voice biometrics, by collecting voice data in different local accents of Pakistan. Although, there is a global need for voice biometrics especially when voice-based services are common, however, this paper uses Pakistan as a use case to show how to build regional voice dataset for voice biometrics. To b...
Related papers
New Developments in Voice Biometrics for User Authentication
Voice biometrics for user authentication is a task in which the object is to perform convenient, robust and secure authentication of speakers. In this work we investigate the use of state-of-the-art text-independent and text-dependent speaker verification technology for user authentication. We evaluate four different authentication conditions: speaker specific digit stings, global digit strings, prompted digit strings, and text-independent. Harnessing the characteristics of the different types of conditions can provide benefits such as authentication transparent to the user (convenience), spoofing robustness (security) and improved accuracy (reliability). The systems were evaluated on a corpus collected by Wells Fargo Bank which consists of 750 speakers. We show how to adapt techniques such as joint factor analysis (JFA), Gaussian mixture models with nuisance attribute projection (GMM-NAP) and hidden Markov models with NAP (HMM-NAP) to obtain improved results for new authentication scenarios and environments
Voice Biometrics for User Authentication
2012
Voice biometrics for user authentication is a task in which the goal is to perform convenient, robust and secure authentication of speakers. In this work we investigate the use of state-of-theart text-independent and text-dependent speaker verification technology for user authentication. We evaluate three different authentication conditions: global digit strings, speaker specific digit stings and prompted digit strings. Harnessing the characteristics of the different types of conditions can provide benefits such as authentication transparent to the user (convenience), spoofing robustness (security) and improved accuracy (reliability). The systems were evaluated on a corpus collected by Wells Fargo Bank which consists of 750 speakers. We show how to adapt techniques such as joint factor analysis (JFA), i-vectors, Gaussian mixture models with nuisance attribute projection (GMM-NAP) and hidden Markov models with NAP (HMM-NAP) to obtain improved results for new authentication scenarios ...
A Review on User Identification using Voice as a Biometric Feature
2018
In this paper, we provide a concise overview for the user identification using his biometric featurespeech. Voice processing has multiple fields of research and is widely used in many applications. Speaker recognition to identify user is a complex process in which various techniques (feature extraction, feature matching, and identification) is used to match varied characteristics of voice between training and testing data to identify the user. This paper aims to discuss efficient method to implement the identification of user on basis of their biometric featurespeech.
Performance Evaluation of Machine Learning Algorithm Applied to a Biometric Voice Recognition System
— The article investigates the possibilities of applying machine learning algorithm to identify an individual through biometric voice recognition with the higher possible reliability. The emphasis in the analysis is placed on the possibility of using artificial intelligence approach methods for the purposes of recognizing a person unambiguously, uniquely on the basis of the data contained in his/her vocal spectral information. A large number of routes we can go to parametrically representing the speech signal for the voice recognition system such as Mel-Frequency Cepstrum Coefficients (MFCC). During the authentication phase the input voice signal is recorded and processed comparing it by using MFCC features with a signal that has been previously stored in the database by the same user. The main purpose is to compare some of the main machine learning algorithms to classify them on this particular application
IDENTITY AUTHENTICATION USING VOICE BIOMETRICS TECHNIQUE
Identification of people using name, appearances, badges, tags and register may be effective may be in a small organization. However, as the size of the organization or society increases, these simple ways of identifying individual become ineffective. Therefore, it may be necessary to employ additional and more sophisticated means of authenticating the identity of people as the population increases. Voice Biometrics is a method by which individuals can be uniquely identified by evaluating one or more distinguishing biological traits associated with the voice of such individuals. In this paper, an unconstrained text-independent recognition system using the Gaussian Mixture Model was applied to match recorded voice to stored voice for the purpose of identification of individual. Recorded voices were processed and stored in the enrollment phase while probing voices were used for comparison in the verification/recognition phase of the system.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.