I agree that this site is using cookies. You can find further informations here.
X
Ghahabi, Omid
27  results:
Search for persons X
?
1

Deep Learning in Speaker Recognition:

, In: Development and Analysis of Deep Learning Architectures; Studies in Computational Intelligence,
Ghahabi, Omid ; Safari, Pooyan ; Hernando, Javier - p. 145-169 , 2019
Link: https://doi.org/10.1007/..
 
?
2

Restricted Boltzmann machines for vector representation of ..:

Ghahabi, Omid ; Hernando, Javier
Computer Speech & Language.  47 (2018)  - p. 16-29 , 2018
Link: https://doi.org/10.1016/..
 
?
3

Deep Learning Backend for Single and Multisession i-Vector ..:

Ghahabi, Omid ; Hernando, Javier
IEEE/ACM Transactions on Audio, Speech, and Language Processing.  25 (2017)  4 - p. 807-817 , 2017
Link: https://doi.org/10.1109/..
 
?
4

Deep Learning Backend for Single and Multisession i-Vector ..:

Ghahabi, Omid ; Hernando, Javier ; Ghahabi, Omid.
IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP).  25 (2017)  4 - p. 807-817 , 2017
Link: https://dl.acm.org/doi/1..
 
?
5

Adaptive Variable Degree- Zero-Trees for Re-Encoding of Per..:

Ghahabi, Omid ; Savoji, Mohammad Hassan
ISRN Signal Processing.  2011 (2011)  - p. 1-16 , 2011
Link: https://doi.org/10.5402/..
 
?
6

EML Online Speech Activity Detection for the Fearless Steps..:

Ghahabi, Omid ; Fischer, Volker
http://arxiv.org/abs/2106.11075.  , 2021
Link: http://arxiv.org/abs/210..
 
?
7

EML System Description for VoxCeleb Speaker Diarization Cha..:

Ghahabi, Omid ; Fischer, Volker
http://arxiv.org/abs/2010.12497.  , 2020
Link: http://arxiv.org/abs/201..
 
?
8

Restricted Boltzmann machines for vector representation of ..:

Ghahabi, Omid ; Hernando Pericás, Francisco Javier
http://www.sciencedirect.com/science/article/pii/S0885230816302923?via%3Dihub.  , 2018
Link: http://hdl.handle.net/21..
 
?
9

Deep learning backend for single and multisession i-vector ..:

Ghahabi, Omid ; Hernando Pericás, Francisco Javier
http://ieeexplore.ieee.org/document/7847321/?reload=true.  , 2017
Link: http://hdl.handle.net/21..
 
?
10

Speaker recognition by means of restricted Boltzmann machin..:

Safari, Pooyan ; Ghahabi, Omid ; Hernando Pericás, Francisco Javier , 2016
Link: http://hdl.handle.net/21..
 
?
11

From features to speaker vectors by means of restricted Bol..:

Safari, Pooyan ; Ghahabi, Omid ; Hernando Pericás, Francisco Javier
http://www.isca-speech.org/archive/Odyssey_2016/pdfs/15.pdf.  , 2016
Link: http://hdl.handle.net/21..
 
?
12

Deep Learning for Single and Multi-Session i-Vector Speaker..:

Ghahabi, Omid ; Hernando, Javier
http://arxiv.org/abs/1512.02560.  , 2015
Link: http://arxiv.org/abs/151..
 
?
13

Adaptive Variable Degree-k Zero-Trees for Re-Encoding of Pe..:

Ghahabi, Omid ; Savoji, Mohammad H
http://arxiv.org/abs/1101.3051.  , 2011
Link: http://arxiv.org/abs/110..
 
?
14

Deep learning for i-vector speaker and language recognition:

Ghahabi Esfahani, Omid
TDX (Tesis Doctorals en Xarxa).  , 2018
Link: http://hdl.handle.net/21..
 
?
15

Deep learning for i-vector speaker and language recognition:

Ghahabi Esfahani, Omid
Ghahabi Esfahani, O. Deep learning for i-vector speaker and language recognition. Tesi doctoral, UPC, Departament de Teoria del Senyal i Comunicacions, 2018. DOI 10.5821/dissertation-2117-118780..  , 2018
Link: http://hdl.handle.net/21..
 
1-15