BUTSpeechFIT/VBx

Issues

• Technical report link dead

  #69 opened 2 months ago by alephpi
  2

• On `xvec_transform` and `plda`

  #64 opened 7 months ago by alephpi
  18

• Issues on VBx reimplementation

  #67 opened 7 months ago by alephpi
  12

• inconsistency between code and technical report

  #68 opened 8 months ago by alephpi
  1

• Problem of different embedding extractors

  #65 opened 9 months ago by axuan731
  7

• Does VBx ever use the training partition in AMI-diarization-setup?

  #66 opened 9 months ago by alephpi
  3

• Derivation of updating formula for $\pi_s$

  #63 opened 10 months ago by alephpi
  2

• threshold value for AHC

  #61 opened a year ago by somiljain7
  1

• Question about impact of VAD .lab file and granularity

  #60 opened a year ago by AdolfVonKleist
  3

• AMI inconsistent RTTM

  #59 opened 2 years ago by HuangZiliAndy
  2

• Limit number of output speakers

  #58 opened 2 years ago by AlexandderGorodetski
  2

• Training data format

  #57 opened 2 years ago by barlowwww
  8

• How to load the ResNet model in pytorch

  #55 opened 2 years ago by anuragkumar95
  2

• How to run VBx on other dataset?

  #54 opened 2 years ago by ooobsidian
  13

• Can VBx work on the windows?

  #52 opened 2 years ago by Bagfish
  1

• use the score.py appear :[winerror 193]%1 is not a valid win32 application is happening

  #53 opened 2 years ago by Bagfish
  3

• using ground-truth VAD

  #51 opened 2 years ago by ZhaZhaFon
  4

• The parameters about overlap in ur paper

  #50 opened 2 years ago by axuan731
  2

• Inconsistency on pip installation

  #48 opened 2 years ago by underdogliu
  3

• Documentation for using the pre-trained model?

  #44 opened 2 years ago by manish-kumar-iisc
  5

• what are ref.rttm and sys.rttm meaning?

  #49 opened 2 years ago by DTDwind
  5

• Error: Empty input file in predict.py

  #47 opened 2 years ago by Themba4Sho
  3

• "AHC" from library

  #42 opened 2 years ago by cherif54
  3

• Not detecting exact number of speakers

  #45 opened 2 years ago by manish-kumar-iisc
  1

• PermissionError with scorelib

  #43 opened 3 years ago by ajcassell
  0

• Number of CPU cores as argument

  #41 opened 3 years ago by lucgeo
  4

• Transition matrix update in every iteration

  #40 opened 3 years ago by desh2608
  3

• Is it possible to run clustering algorithm on GPU?

  #34 opened 3 years ago by Sarah-Xing
  17

• How to train the xvector extractor with own data

  #39 opened 3 years ago by llior
  3

• twoGMMcalib_lin's theory

  #38 opened 3 years ago by xiaosujie
  3

• AMI DER result cannot be reproduced

  #37 opened 3 years ago by xiaosujie
  15

• Pytorch backend problem

  #36 opened 3 years ago by xiaolling
  0

• what is the difference between plda_psi and plda_tr in line 93 and lines 97 and 98?

  #35 opened 3 years ago by xuanjihe
  2

• Speaker loop elimination

  #28 opened 3 years ago by videodanchik
  2

• More detail for package version

  #24 opened 3 years ago by DTDwind
  6

• VBx written in C++

  #31 opened 3 years ago by xuanjihe
  5

• Update links to new paper

  #27 opened 3 years ago by fnlandini
  1

• Ark file

  #26 opened 3 years ago by COmpSci1212
  3

• VB clustering

  #25 opened 3 years ago by Vuducbao913
  2

• How to use GPU?

  #23 opened 3 years ago by Vuducbao913
  3

• Create VAD

  #22 opened 3 years ago by Vuducbao913
  5

• plda and transform.h5

  #32 opened 3 years ago by cathyeee77
  2

• AMI beamformed wav

  #30 opened 3 years ago by DTDwind
  2

• AHC DER

  #29 opened 3 years ago by DTDwind
  3

• Division by zero in AHC

  #21 opened 3 years ago by Jamiroquai88
  3

• Error Handling for the empty/silence audio files

  #19 opened 4 years ago by vinayentc
  2

• feature diff vs kaldi

  #20 opened 4 years ago by wbgxx333
  0

• telephone codec

  #18 opened 4 years ago by wbgxx333
  2

• How to process 1h30m of audio?

  #17 opened 4 years ago by johnarevalo
  2

• Attempting to fix maxSpeakers to 2 sometimes yields a forward-backward error

  #16 opened 4 years ago by AdolfVonKleist
  5