Abstract
Speaker recognition depends on specific predefined steps. The most important steps are feature extraction and features matching. In addition, the category of the speaker voice features has an impact on the recognition process. The proposed speaker recognition makes use of biometric (voice) attributes to recognize the identity of the speaker. The long-term features were used such that maximum frequency, pitch and zero crossing rate (ZCR). In features matching step, the fuzzy inner product was used between feature vectors to compute the matching value between a claimed speaker voice utterance and test voice utterances. The experiments implemented using (ELSDSR) data set. These experiments showed that the recognition accuracy is 100% when using text dependent speaker recognition.
Highlights
One of the most critical tasks of information security is developing a method to recognize the identity of the user based on the digitization of that identity which is required to access these systems with an acceptable level of trust
Banerjee et al (2018) used short term spectral features learned from the Deep Belief Networks (DBN) augmented with Mel Frequency Cepstral Coefficients (MFCC) features to perform the task of speaker recognition, they achieved a recognition accuracy of 95% as compared to 90% when using standalone MFCC features on the English Language Speech Database for Speaker Recognition (ELSDSR) dataset [5]
Speaker recognition depends on the type of features extracted from the speaker voice signal
Summary
One of the most critical tasks of information security is developing a method to recognize the identity of the user based on the digitization of that identity which is required to access these systems with an acceptable level of trust. The identity refers to a group of well-defined properties that make an entity recognized compared to other entities [1]. While the digital identity is a set of features owned by an entity used by information systems to represent an identity of individual. Voice attributes rich with information that could be digitized to recognize between users. The voice attributes have many advantages , they are unique and easy to capture
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have