Styjun

Who was president?

Are illustrations in novels frowned upon?

Can't stopover at Sapporo when going from Asahikawa to Chitose airport?

I got kicked out from graduate school in the past. How do I include this on my CV?

Checking a beta regression model via glmmTMB with DHARMa package

Why different interest rates for checking and savings?

Efficiently pathfinding many flocking enemies around obstacles

Is “I am getting married with my sister” ambiguous?

Is a player able to change alignment midway through an adventure?

Why did this happen to Thanos's ships at the end of "Avengers: Endgame"?

Did a flight controller ever answer Flight with a no-go?

Why is my Earth simulation slower than the reality?

Mathematical uses of string theory

I have a player who yells

Does travel insurance for short flight delays exist?

Cultural before-and-afters

Which household object drew this pattern?

How do I request a longer than normal leave of absence period for my wedding?

Why do all fields in a QFT transform like *irreducible* representations of some group?

Irish Snap: Variant Rules

how do you harvest carrots in creative mode

Confirming resignation after resignation letter ripped up

Are there any elected officials in the U.S. who are not legislators, judges, or constitutional officers?

Can pay be witheld for hours cleaning up after closing time?

How to obtain Universal Background model in sidekit for language recognition

Speech recognition language modelWhat are language codes in Chrome's implementation of the HTML5 speech recognition API?How do speech recognition algorithms recognize homophones?How to do online single word recognition with background noise in JavaHow can I use voice recognition with other languages androidTensorflow: how to save/restore a model?Word Recognition custom language [eg. Elvish]How to create phonetic language model for CMU Sphinx?System.Speech.Recognition; background control or voice recognitionOffline voice recognition for an unpopular language

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;

0

I want to obtain ivectors in sidekit, so I have like 1000 audios , firstly I obtained my mfccs with:

frontend.features.mfcc(input_sig, lowfreq=100, maxfreq=8000, nlinfilt=0, nlogfilt=24, nwin=0.025, fs=16000, nceps=13, shift=0.01, get_spec=False, get_mspec=False, prefac=0.97)[source]

So I have my 2d array of mfccs, now I want to obtain my ubm and my ivectors but the command to obtain the ubm takes a feature server

ubm.EM_split(features_server=fs,
 feature_list=ubm_list,
 distrib_nb=1024,
 iterations=(1, 2, 2, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8),
 num_thread=10,
 save_partial=False,
 ceil_cov=10,
 floor_cov=1e-2
 )

How can I take my mfccs and make a feature server to obtain my ubm

There is very little documentation, so sorry if it is something basic
thankyou for your help

python speech-recognition voice-recognition gmm sidekit

share|improve this question

edited Apr 24 at 8:00

Anwarvic

2,23911 gold badge1717 silver badges3232 bronze badges

asked Mar 27 at 16:35

David RomeroDavid Romero

1344 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  There are much more recent and accurate speech recognition kits, try them instead.
  
  – Nikolay Shmyrev
  Apr 13 at 20:31
  

  
  
  
  

add a comment | 

0

I want to obtain ivectors in sidekit, so I have like 1000 audios , firstly I obtained my mfccs with:

frontend.features.mfcc(input_sig, lowfreq=100, maxfreq=8000, nlinfilt=0, nlogfilt=24, nwin=0.025, fs=16000, nceps=13, shift=0.01, get_spec=False, get_mspec=False, prefac=0.97)[source]

So I have my 2d array of mfccs, now I want to obtain my ubm and my ivectors but the command to obtain the ubm takes a feature server

ubm.EM_split(features_server=fs,
 feature_list=ubm_list,
 distrib_nb=1024,
 iterations=(1, 2, 2, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8),
 num_thread=10,
 save_partial=False,
 ceil_cov=10,
 floor_cov=1e-2
 )

How can I take my mfccs and make a feature server to obtain my ubm

There is very little documentation, so sorry if it is something basic
thankyou for your help

python speech-recognition voice-recognition gmm sidekit

share|improve this question

edited Apr 24 at 8:00

Anwarvic

2,23911 gold badge1717 silver badges3232 bronze badges

asked Mar 27 at 16:35

David RomeroDavid Romero

1344 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  There are much more recent and accurate speech recognition kits, try them instead.
  
  – Nikolay Shmyrev
  Apr 13 at 20:31
  

  
  
  
  

add a comment | 

I want to obtain ivectors in sidekit, so I have like 1000 audios , firstly I obtained my mfccs with:

frontend.features.mfcc(input_sig, lowfreq=100, maxfreq=8000, nlinfilt=0, nlogfilt=24, nwin=0.025, fs=16000, nceps=13, shift=0.01, get_spec=False, get_mspec=False, prefac=0.97)[source]

So I have my 2d array of mfccs, now I want to obtain my ubm and my ivectors but the command to obtain the ubm takes a feature server

ubm.EM_split(features_server=fs,
 feature_list=ubm_list,
 distrib_nb=1024,
 iterations=(1, 2, 2, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8),
 num_thread=10,
 save_partial=False,
 ceil_cov=10,
 floor_cov=1e-2
 )

How can I take my mfccs and make a feature server to obtain my ubm

There is very little documentation, so sorry if it is something basic
thankyou for your help

python speech-recognition voice-recognition gmm sidekit

share|improve this question

edited Apr 24 at 8:00

Anwarvic

2,23911 gold badge1717 silver badges3232 bronze badges

asked Mar 27 at 16:35

David RomeroDavid Romero

1344 bronze badges

frontend.features.mfcc(input_sig, lowfreq=100, maxfreq=8000, nlinfilt=0, nlogfilt=24, nwin=0.025, fs=16000, nceps=13, shift=0.01, get_spec=False, get_mspec=False, prefac=0.97)[source]

ubm.EM_split(features_server=fs,
 feature_list=ubm_list,
 distrib_nb=1024,
 iterations=(1, 2, 2, 4, 4, 4, 4, 8, 8, 8, 8, 8, 8),
 num_thread=10,
 save_partial=False,
 ceil_cov=10,
 floor_cov=1e-2
 )

share|improve this question

edited Apr 24 at 8:00

Anwarvic

2,23911 gold badge1717 silver badges3232 bronze badges

asked Mar 27 at 16:35

David RomeroDavid Romero

1344 bronze badges

share|improve this question

edited Apr 24 at 8:00

Anwarvic

2,23911 gold badge1717 silver badges3232 bronze badges

asked Mar 27 at 16:35

David RomeroDavid Romero

1344 bronze badges

edited Apr 24 at 8:00

Anwarvic

2,23911 gold badge1717 silver badges3232 bronze badges

edited Apr 24 at 8:00

Anwarvic

2,23911 gold badge1717 silver badges3232 bronze badges

asked Mar 27 at 16:35

David RomeroDavid Romero

1344 bronze badges

asked Mar 27 at 16:35

David RomeroDavid Romero

1344 bronze badges