Hello, We are Looking for a highly professional and experienced Developer who understands Voice Bio Metrics "speaker recognition technologies” includes text-dependent & Text-independent. . Here, We need to develop a stand-alone voice recognition applications (Voice Bio Metric Application) on C#.Net in which we want to get voice samples from a sql database and match them with another voice sample.
For example, we have sql database of different voice samples (sample1, sample2, sample3) of different persons. And also we have a recorded voice sample (sample-X). Now we just want our application to match Sample-X with all the stored voice samples in database and display us result in the matching percentage. We also want to set the False Acceptance Rate (FAR) value to get nearest matching result.
We have searched many 3rd party SDK and Libraries in which few are giving us result we are expecting, but 3rd party solution doesn't meet our application look and feel requirement, also there is a problem of licensing.
Hence, we are looking for a developer who can create such application for us with the same matching result without any licensing dependencies with the good back-end support to implement and deployment of the product. The application will be used in the windows operating system without any WAN/LAN connection.
Speaker recognition is the identification of the person who is speaking by characteristics of their voices (voice bio metrics). Using this speaker recognition Application, computers can be used to recognize humans by the sound of their voices. This Speaker recognition Application, extracts characteristics from user's voice that can be used to validate user's claimed identity.
• Automatic voice activity detection.
• 1-to-1 matching (verification) and 1-to-many (identification) modes.
• False Rejection (FR): The larger the FR value is, the higher is the probability that the voices are of the same speaker.
• False Acceptance( FA) : The smaller the FA value is, the higher the probability that the two voice samples are from the same speaker
• Likelihood Ratio (LR) : is a measure of similarity between two voices being compared.
• Voice identification with any pitch.
• Complete and fully-functional working program(s) in executable form as well as complete source code of all work done.
• Software installation package that will install the software in ready-to-run condition on the platform specified in this bid request.