Speaker identification from data returned from Speech To Text API
Budget: $30 – $250 USD
Hello guys,
I am using Vosk speech to text service and I have speaker identification data from this service, the speaker data I receive is an array of floats that needs to be compared with a speaker signature using cosine distance. The page below shows an example from the authors:
https://github.com/alphacep/vosk-api/blob/7b4d396eb139991fce925e2eec4c1fcd8ba0d592/python/example/test_speaker.py
I want to implement this in java or c# (others if I can use them in C# is fine) and be able to use it in my app. The goal is to send speaker data to a method which compares them with speaker signature from a data source and gives the speaker id or name.
Let me know if this is something you can help with.
Thank you
Speech to text service I'm using is:
https://github.com/alphacep/vosk-api
I am using Vosk speech to text service and I have speaker identification data from this service, the speaker data I receive is an array of floats that needs to be compared with a speaker signature using cosine distance. The page below shows an example from the authors:
https://github.com/alphacep/vosk-api/blob/7b4d396eb139991fce925e2eec4c1fcd8ba0d592/python/example/test_speaker.py
I want to implement this in java or c# (others if I can use them in C# is fine) and be able to use it in my app. The goal is to send speaker data to a method which compares them with speaker signature from a data source and gives the speaker id or name.
Let me know if this is something you can help with.
Thank you
Speech to text service I'm using is:
https://github.com/alphacep/vosk-api
Related categories:
Business, Accounting, Human Resources & Legal
Algorithm
C# Programming
Machine Learning (ML)