carl-robinson/voice-emotion-seq2seq
Voice emotion conversion model for DS/ML master's thesis. F0 contour mapping in sequence-to-sequence RNN-LSTM architecture in Tensorflow.
Jupyter NotebookMIT
Issues
- 0
- 1
how to open these wav samples?
#1 opened
Voice emotion conversion model for DS/ML master's thesis. F0 contour mapping in sequence-to-sequence RNN-LSTM architecture in Tensorflow.
Jupyter NotebookMIT