Progressive unsupervised domain adaptation for asr using ensemble models and multi-stage training

HIGHLIGHTS

• What: In the experiments, three teacher models are considered, i.e N=3, and the student models are trained up to three stages M=3.
• Who: Ahmad and collaborators from the (ICASSP) is made available via the University of Sheffield Research and, The University of Sheffield, UK have published the Article: Progressive unsupervised domain adaptation for ASR using ensemble models and multi-stage training, in the Journal: (JOURNAL)
• How: As discussed in the previous work that the student performed better than the teachers therefore in this work the trained student is used as . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.