VJTI-FYP | Comparative Study of GMM and SincNet models

VJTI-FYP is a Jupyter Notebook library. VJTI-FYP has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub.

The human ear is a marvelous organ. Beyond our uniquely human ability to receive and decode spoken language, the ear supplies us with the ability to perform many diverse functions. These include, for example, localization of objects, enjoyment of music, and the identification of people by their voices. Currently, along with efforts to develop computer procedures that understand spoken messages, there is also considerable interest in developing procedures that identify people from their voices [1]. Speaker recognition is a generic term which refers to any task which discriminates between people based upon their voice characteristics[1]. Voice being a unique characteristic to humans, it may be used as a biometric identity. Amidst all the authentication alternatives that are applicable today, speaker recognition shall prove to be a more reliable mechanism for personal identification. Security applications such as physical access control (eg: voice-controlled door), computer data access control or telephone transaction control (eg: telephonic payments) are prime targets for developing Automatic Speaker Recognition (ASR) systems[13]. ASR also finds its use in forensics (to identify culprits) and gathering reconnaissance information on either military or home environments. There are two major applications of speaker recognition technologies and methodologies. If the speaker claims to be of a certain identity and the voice is used to verify this claim, this is called verification or authentication[2]. On the other hand, identification is the task of determining an unknown speaker’s identity. In a sense, speaker verification is a 1:1 match where one speaker’s voice is matched to a particular template whereas speaker identification is a 1:N match where the voice is compared against multiple templates. From a security perspective, identification is different from verification. Speaker verification is usually employed as a "gatekeeper" in order to provide access to a secure system. These systems operate with the users' knowledge and typically require their cooperation. Speaker identification systems can also be implemented covertly without the user’s knowledge to identify talkers in a discussion, alert automated systems of speaker changes, check if a user is already enrolled in a system, etc[2]. Since the advent of developing technologies that make machines learn to act or think, researchers have toiled to come up with techniques that enable machines to identify sounds or voices.Extensive research work has been done in the past with a wide spectrum of techniques developed, ranging from core statistical approaches to state-of-the-art neural networks machines (deep learning approach)[7]. As part of our project work, we wish to implement these techniques and study their characteristics and extent of accuracy on used datasets.