Vesper project summary. 1st half of 2024

From January 2024 We are implementing the Vesper project, which aims to create an innovative voice communicator. We informed about the project here https://biometriq.pl/en/vesper-save-voice-communication-platform-with-integration-of-biometric-services/

The aim of the first stage of the project, completed on December 31 this year, is to develop an innovative method for detecting the truthfulness of the speaker and the transmitting voice stream.
Implementing this method in the messenger will allow you to assess the compatibility of the interlocutor communicating, among others, smartphone or computer according to your expectations and prevent voice attacks.

And what we did?

1. We have developed the structure of the subsystem.

2. We have developed preliminary requirements for a methodology for detecting the veracity of the far-end voice source based on the received signal in the near-end device.

3. We have developed guidelines for measurement methodologies, taking into account the statistical significance of the results.
4. We have developed a preliminary version of research procedures taking into account the developed research scenarios for stage 1.

Scenarios and research procedures were developed taking into account the state of scientific knowledge at the time of work.

5. We have prepared a dataset for training neural networks.

6. We carried out the first training of neural networks and the selection and optimization of cost functions.
7. We performed a detailed analysis of QoE assessment methodologies in connection with qualitative objective parameters and proposed the framework of our own solution in this area.
8. We analyzed the possibilities of controlling and intervening in the audio path for mobile phones available on the market.
9. We have prepared and configured the first version of the VESPER test platform based on the Signal framework for Windows and Android.
10. We rented a DSP laboratory

11. We acquired a speech corpus for testing

12. We have purchased Voice Conversion engine licenses