Giters

vineeths96 / Spoken-Keyword-Spotting

In this repository, we explore using a hybrid system consisting of a Convolutional Neural Network and a Support Vector Machine for Keyword Spotting task.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How to train for new keyword?

boleamol opened this issue · comments

commented

Dear @vineeths96

Thank you for awesome recipe.

I have few questions

  1. How to train for new keyword?
  2. How to tune hyper parameter?
  3. How to display position (at what second/minute) of keyword in audio file (e.g. keyword found at 5th second, 9th second in audio file)?
commented

Hey @boleamol! Did you figure it out? Or is there any better model nowadays?

commented

@RahulBhalley: Not yet.... If you have any other option, please suggest.

commented

Hmm, I'm new to this. Just got an idea that maybe we can create a dataset of specific keyword and train it.
And the new spoken words can be generated using some TTS software.