“2018-12-12”版本间的差异

• Learned TensorFlow documents about seq2seq model and made adjustments on vivi's params
• Had some problems on encoder-memory and decoder-memory, and was trying to figure out the difference

• Make adjustments on vivi
• Reproduce codes on Song Iambics generation

• run the AISHELL2 baseline
• read a few papers about low-rank matrix factorization for NN

• organize the fragment information and form a knowledge system of compression as soon as possible

• attend an academic conference

• keep on research of DID

• Read attention recipe on kaldi and try to establish baseline use thch30
• read the "PHONETIC-ATTENTION SCORING FOR DEEP SPEAKER FEATURES IN SPEAKER VERIFICATION"

and “GAUSSIAN-CONSTRAINED TRAINING FOR SPEAKER VERIFICATION”

• finish attention baseline

• Read papers about tensor decompositions
• Prepared a paper sharing about tensorizing neural work

• Run the code for the experimental part of the paper
• Learn more about the details

• 1.refactored my code and accelerated VPR speed.
• 2.modified some references error in Machine Learning book.

• try to release a stable app as soon as possible.