use case: Identification of speakers
How can I identify new speakers in my media assets?
the challenge
Expand the speaker database
Face recognition is already widely used today, but there are still many formats in which a face cannot always be recognized, such as audio-only files. In this case, it is essential to be able to reliably identify speakers based on their audio characteristics.
How can DeepVA help me to store individual speakers as a data set in order to structure my image material?
the solution
Deep Model Customizer
With Deep VA’s Deep Customizer you can individualize the speaker recognition with your own personalities. Simply upload one or more audio files of the personality and title the speaker’s name. Expanding and Individualizing your speaker database couldn’t be easier.
Since training data is one of the most important elements in the use of AI, we offer data set functions to manage your training data transparently, intuitively and efficiently while respecting data privacy. The system can be used on-premise or in the cloud. If it is to be part of a workflow, integration is required. Via our RESTful API it can be easily integrated in any existing system or workflow.
What results can be obtained?
Build a speaker database without effort, using a very intuitive and easy to use system
Create a completely unique speaker database exactly for your purpose
faster data acquisition
COST REDUCTION
faster labelling
identification of speakers
Function overview
Speaker Training
In just a few seconds, new faces are trained using our Face Training and can be used in the Recognition Services.
Contact us
Do you have any questions?
Related use cases
Take a look at our other use cases
Automatically build a face recognition dataset
How can I automatically build training datasets from my media footage?
Individual person identification
How can I recognize less-known or regional people in my footage?
Automatically build a speaker dataset
How can I build up a dataset for my speaker recognition?
