| Issue Date | Title | Author(s) |
| 1 | 19-Oct-2016 | Advanced voice activity detection on mobile phones by using microphone array and phoneme-specific Gaussian mixture models | Popović, Boris; Pakoci, Edvin ; Pekar, Darko |
| 2 | 1-Jan-2016 | An algorithm for phase manipulation in a speech signal | Pekar, Darko ; Suzić, Siniša ; Mak R.; Friedlander M.; Sečujski, Milan |
| 3 | 1-Dec-2011 | Automatic prosody generation for Serbo-Croatian speech synthesis based on regression trees | Sečujski, Milan ; Pekar, Darko ; Jakovljević, Nikša |
| 4 | 1-Jan-2018 | A Comparison of Language Model Training Techniques in a Continuous Speech Recognition System for Serbian | Popović, Boris; Pakoci, Edvin ; Pekar, Darko |
| 5 | 18-Apr-2018 | A comparison of multi-style DNN-based TTS approaches using small datasets | Suzić, Siniša ; Delić, Tijana; Jovanović, Veljko; Sečujski, Milan ; Pekar, Darko ; Delić, Vlado |
| 6 | 1-Oct-2010 | Eigenvalues Driven Gaussian Selection in continuous speech recognition using HMMs with full covariance matrices | Janev M.; Pekar, Darko ; Jakovljević, Nikša ; Delić, Vlado |
| 7 | 1-Jan-2017 | End-to-end large vocabulary speech recognition for the serbian language | Popović, Boris; Pakoci, Edvin ; Pekar, Darko |
| 8 | 1-Jan-2018 | Improvements in Serbian speech recognition using sequence-trained deep neural networks | Pakoci, Edvin ; Popović, Boris; Pekar, Darko |
| 9 | 12-Dec-2012 | A language model for highly inflective non-agglutinative languages | Ostrogonac S.; Mišković, Dragiša ; Sečujski, Milan ; Pekar, Darko ; Delić, Vlado |
| 10 | 1-Jan-2017 | Language model optimization for a deep neural network based speech recognition system for Serbian | Pakoci, Edvin ; Popović, Boris; Pekar, Darko |
| 11 | 1-Jan-2018 | Learning prosodic stress from data in neural network based text-to-speech synthesis | Sečujski, Milan ; Ostrogonac S.; Suzić, Siniša ; Pekar, Darko |
| 12 | 2-Mar-2011 | Naturalness, adaptation and cooperativeness in spoken dialogue systems | Gnjatović, Milan ; Pekar, Darko ; Delić, Vlado |
| 13 | 23-Oct-2017 | Novel alignment method for DNN TTS training using HMM synthesis models | Suzić, Siniša ; Delić, Tijana; Pekar, Darko ; Ostojić, Vladimir |
| 14 | 1-Jan-2012 | A novel split-and-merge algorithm for hierarchical clustering of Gaussian mixture models | Popović B.; Janev M.; Pekar, Darko ; Jakovljević, Nikša ; Gnjatović, Milan ; Sečujski, Milan ; Delić, Vlado |
| 15 | 1-Jan-2014 | On the realization of AnSpeechCollector, system for creating transcribed speech database | Suzić, Siniša ; Pekar, Darko ; Delić, Vlado |
| 16 | 1-Dec-2010 | On the use of higher frame rate in the training phase of ASR | Pekar, Darko ; Jakovljević, Nikša ; Janev M.; Mišković, Dragiša ; Delić, Vlado |
| 17 | 1-Jan-2016 | A phonetic segmentation procedure based on hidden markov models | Pakoci, Edvin ; Popović, Boris; Jakovljević, Nikša ; Pekar, Darko ; Yassa F. |
| 18 | 23-Apr-2018 | Rapid development of new TTS voices by neural network adaptation | Delić, Tijana; Suzić, Siniša ; Sečujski, Milan ; Pekar, Darko |
| 19 | 1-Jan-2014 | Speaker detection using phoneme specific hidden markov models | Pakoci, Edvin ; Jakovljević, Nikša ; Popović, Boris; Mišković, Dragiša ; Pekar, Darko |
| 20 | 10-Oct-2013 | Speech and language resources within speech recognition and synthesis systems for Serbian and kindred South Slavic languages | Delić, Vlado ; Sečujski, Milan ; Jakovljević, Nikša ; Pekar, Darko ; Mišković, Dragiša ; Popović, Boris; Ostrogonac S.; Bojanić, Milana ; Knežević, Dejan |