Speaker Recognition and Diarization open resources

Speaker Recognition

ALIZE/LIA_RAL – C++

https://github.com/ALIZE-Speaker-Recognition/LIA_RAL

SIDEKIT  – python
MSR Identity Toolbox – matlab
Kaldi – scripting
Examples
===========================================================================

Discussion

http://habla.dc.uba.ar/gravano/ith-2014/presentaciones/Dehak_et_al_2010.pdf

 

GMM-UBM i-Vector

http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/cb/131104-ivector-microsoft-wj.pdf

https://people.csail.mit.edu/sshum/talks/ivector_tutorial_interspeech_27Aug2011.pdf

https://speechlab.sjtu.edu.cn/pages/sw121/homepage/2016/05/20/ivector-tutorial/

https://blog.csdn.net/xmu_jupiter/article/details/47209961

https://blog.csdn.net/zhangxueyang1/article/details/66971997

 

Speaker Diarization

LIUM – JAVA

http://www-lium.univ-lemans.fr/diarization/doku.php/welcome

https://github.com/StevenLOL/LIUM

kaldi CALLHOME_diarization – scripting

https://github.com/kaldi-asr/kaldi/tree/master/egs/callhome_diarization

https://github.com/Jamiroquai88/VBDiarization

Pyannote – python

https://github.com/pyannote/pyannote-audio

aalto speech – python for segment

https://github.com/aalto-speech/speaker-diarization

 

 

 

Advertisements