There is a newer version of the record available.

Published June 17, 2017 | Version 1.0.0

astorfi/speech_feature_extraction: SpeechPy

Authors/Creators

Description

This packages contains the feature extraction software implementation for our paper Text-Independent Speaker Verification Using 3D Convolutional Neural Networks (Torfi, Nasrabadi, Dawson), arXiv:1705.09422 [hep-ph]. It includes important pre-processing operations such as frame-stacking and feature-extraction functions for features such as MFCC and etc.

Files

astorfi/speech_feature_extraction-1.0.0.zip

Files (8.4 MB)

Name Size Download all
md5:68fce5a3076e0ddc77baac749c3ebb67
8.4 MB Preview Download

Additional details