ZeroSpeech2017
Published January 13, 2018 | Version v1
Dataset Open

Phoneme Based Embedded Segmental K-Means for ZeroSpeech2017 Track 2

Creators

  • 1. Indian Institute of Technology Hyderabad

Description

Our submission applying the phoneme based embedded segmental k-means model to the ZeroSpeech2017 challenge track 2. 

This is a preliminary version. More details can be found here: https://www.kamperh.com/papers/bhati+kamper+murty_icassp2018.pdf and  https://github.com/Saurabhbhati/recipe_zs2017_track2

 

Files

Files (9.3 MB)

Name Size Download all
md5:bd55c8f76e4ed5cc32da73df87b9bed5
9.3 MB Download