I'm looking for existing "Baby Cry Detection", which has been done in any framework(preferably Tensorflow, but GLOW and CMSIS-NN Projects are okay). Does anyone know an existing repository or user manual to build that project?
Hi Emin,
NXP does have voice dection solution, please refer below web links for the detailed info:
Wish it helps.
best regards,
Mike
I was not looking for the solution which is taking real-time micropohone input. I am looking for a project, which takes certain datasets like voice files or binary files to read as input and doing model inference
Hi,
I do not find related "Baby Cry" data model. Could you please check with below NXP Voice partner:
Wish it helps.
Mike