pit-speech-separation icon indicating copy to clipboard operation
pit-speech-separation copied to clipboard

Published 20 hours ago • verified publisher icon snsun

hi,can you offer me some data for train,i am new to the LSTM

Open gao-shi opened this issue 6 years ago • 5 comments

gao-shi avatar Mar 18 '18 02:03 gao-shi

Hi, I am sorry that I can not share the WSJ data to you because of the restrictions. Actually, you are not necessary to use the same corpus, you can use any data set you have to produce mixed speech with a little modification of the matlab scripts.

snsun avatar Mar 18 '18 03:03 snsun

Never mind. Thank you for your reply

gao-shi avatar Mar 18 '18 04:03 gao-shi

Hi，what should i do after i generate mixed wav files and use gen_tfrecords.py to create tfrecords？ Can i contact you more effectively?

gao-shi avatar Mar 20 '18 09:03 gao-shi

We can use wechat. Send me your wechat id by your personal email.

snsun avatar Mar 21 '18 22:03 snsun

hello ，i have some question，能联系你吗？我的qq是851566168

bailiangze avatar Nov 05 '20 03:11 bailiangze