MingmChen / Speaker_Verification Public

Notifications You must be signed in to change notification settings
Fork 0
Star 4

Academic Project for Speech and Speaker Recognition course DD2119

4 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 80 Commits
speech_feature_extraction		speech_feature_extraction
500_first_ids.npy		500_first_ids.npy
500_first_ids.txt		500_first_ids.txt
50_first_ids.npy		50_first_ids.npy
50_first_ids.txt		50_first_ids.txt
README.md		README.md
__init__.py		__init__.py
another_upload.py		another_upload.py
constants.py		constants.py
evaluation.py		evaluation.py
gcloud_wrappers.py		gcloud_wrappers.py
labeled_indices.npy		labeled_indices.npy
load_data.py		load_data.py
model.py		model.py
siamese.py		siamese.py
train.py		train.py
utils.py		utils.py

Repository files navigation

#VoxCeleb1

pip install speechpy
contains over 100,000 utterances for 1,251 celebrities, extracted from videos uploaded to YouTube.

Verification split dev test

of speakers 1,211 40
of videos 21,819 677
of utterances 148,642 4,874

Identification split dev test

of speakers 1,251 1,251
of videos 21,245 1,251
of utterances 145,265 8,251

Dataset

Link to dataset: https://drive.google.com/drive/folders/1__Ob2AUuAdzVDRCVhKtKSvGmTKHUKTuR
Username: voxceleb1904
Password: 9hmp7488

Project files

Constants.py: Contains all the constants for preprocessing the data.
vox1_meta.csv: Contains the meta data of the dataset in a csv format.
preprocess/utils.py: This file includes routines for basic signal processing including framing and computing power spectra. Author: James Lyons 2012

About

Academic Project for Speech and Speaker Recognition course DD2119

Report repository

Releases

No releases published

Packages

No packages published

Languages