/Blind-T60-estimation-using-LSTM

Let start with feature extraction in "march 2018 progress.ipynb" (Jupyter notebook) then speechRecog.py

Primary LanguageJupyter Notebook

blind T60 estimation using LSTM

Digital signal processing hand-on for feature extraction that implement with python (Jupyter notebook)

-Convolution of room impulse response and speech signal

-Seven-Octave bandpass filterbank

-Envelope extraction using Ayncronous Complex Hilbert Transfrom

-MCFF (Mel Ceptrum Frequency Function)

Dataset/Corpus: 1.SMILE from JAIST (RIR) 2.Aachen University (RIR) 3.Open AIR Library (RIR) 4.TIMIT (Speech) 5.Centre for Speech Technology Research,University of Edinburgh (Speech) 6.CSTR VCTK Corpus,English Multi-speaker Corpus for CSTR Voice Cloning Toolkit University of Edinburgh (Speech) 7.Speech Synthesis