Edvin Pakoci

According to our database, Edvin Pakoci authored at least 10 papers between 2014 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2022

Overcoming Data Sparsity in Automatic Transcription of Dictated Medical Findings.

Edvin Pakoci, Darko Pekar, Branislav M. Popovic, Milan Secujski, Vlado Delic

Proceedings of the 30th European Signal Processing Conference, 2022

2021

Methods for Using Class Based N-gram Language Models in the Kaldi Toolkit.

Edvin Pakoci, Branislav M. Popovic

Proceedings of the Speech and Computer - 23rd International Conference, 2021

2019

Using Morphological Data in Language Modeling for Serbian Large Vocabulary Speech Recognition.

Edvin Pakoci, Branislav M. Popovic, Darko Pekar

Comput. Intell. Neurosci., 2019

2018

A Comparison of Language Model Training Techniques in a Continuous Speech Recognition System for Serbian.

Branislav M. Popovic, Edvin Pakoci, Darko Pekar

Proceedings of the Speech and Computer - 20th International Conference, 2018

2017

End-to-End Large Vocabulary Speech Recognition for the Serbian Language.

Branislav M. Popovic, Edvin Pakoci, Darko Pekar

Proceedings of the Speech and Computer - 19th International Conference, 2017

Language Model Optimization for a Deep Neural Network Based Speech Recognition System for Serbian.

Edvin Pakoci, Branislav M. Popovic, Darko Pekar

Proceedings of the Speech and Computer - 19th International Conference, 2017

2016

A Phonetic Segmentation Procedure Based on Hidden Markov Models.

Edvin Pakoci, Branislav M. Popovic, Niksa Jakovljevic, Darko Pekar, Fathy Yassa

Proceedings of the Speech and Computer - 18th International Conference, 2016

Advanced voice activity detection on mobile phones by using microphone array and phoneme-specific Gaussian mixture models.

Branislav M. Popovic, Edvin Pakoci, Darko Pekar

Proceedings of the 14th IEEE International Symposium on Intelligent Systems and Informatics, 2016

2015

Deep Neural Network Based Continuous Speech Recognition for Serbian Using the Kaldi Toolkit.

Branislav M. Popovic, Stevan Ostrogonac, Edvin Pakoci, Niksa Jakovljevic, Vlado Delic

Proceedings of the Speech and Computer - 17th International Conference, 2015

2014

Speaker Detection Using Phoneme Specific Hidden Markov Models.

Edvin Pakoci, Niksa Jakovljevic, Branislav M. Popovic, Dragisa Miskovic, Darko Pekar

Proceedings of the Speech and Computer - 16th International Conference, 2014