Skip to content

A tensorflow implementation of the Attention-based End-to-End Models for Small-Footprint Keyword Spotting

Notifications You must be signed in to change notification settings

rxhmdia/attention-based-keyword-spotting

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Attention based keyword spotting

A tensorflow implementation of the Attention-based End-to-End Models for Small-Footprint Keyword Spotting

requirements

see requirements.txt

Usage

  • feature: generate fbank or other feature, save to tfrecord format (todo)
  • training: run train.sh
  • inference: run infer.sh
  • evaluate: (todo)

Modify

Modify the original model to streaming model which can support random length inputs.

Support

  • model: gru & lstm
  • loss: focal loss & cross entropy loss & kl loss

Refernce

Changhao Shan, Junbo Zhang, Yujun Wang, Lei Xie Attention-based End-to-End Models for Small-Footprint Keyword Spotting.

About

A tensorflow implementation of the Attention-based End-to-End Models for Small-Footprint Keyword Spotting

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published