Miomir Mijic's research while affiliated with University of Belgrade and other places

What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.

It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.

If you're a ResearchGate member, you can follow this page to keep up with this author's work.

If you are this author, and you don't want us to display this page anymore, please let us know.

Publications (3)

Figure 1. Rational approximation of the number π In this paper,...
One categorization of microtonal scales
Article
Full-text available
  • Jan 2018
This study considers rational approximations of musical constant $\beta=\log_2(3/2)$, which defines perfect fifth. This constant has been the subject of the numerous studies, and this paper determines quality of rational approximations in regards to absolute error. We analysed convergents and secondary convergents (some of these are the best Huygen...
Cite
Download full-text
Fig. 1. Block diagram for LFCC/TELFCC and MFCC/TEMFCC based coefficients. 
Table 1 . Average WRR with Margin of Error of LFCC feature vectors (in %).
Table 5 . p-values for H0A/H1A hypotheses.
Table 6 . p-values for H0B/H1B hypotheses.
Application of Teager Energy Operator on Linear and Mel Scales for Whispered Speech Recognition
Article
Full-text available
  • Jan 2018
This paper presents experimental results on whispered speech recognition based on Teager Energy Operator for linear and mel cepstral coefficients including the Cepstral Mean Subtraction normaliza-tion technique. The feature vectors taken into consideration are Linear Frequency Cepstral Coefficients, Teager Energy based Linear Frequency Cepstral Coe...
Cite
Download full-text
Fig. 4. A "left-to-right" model.
Average WRR (in %) for all scenarios and DTW method
Average WRR (in %) for all scenarios and HMM method
Whispered speech recognition based on gammatone filterbank cepstral coefficients
Article
Full-text available
  • Nov 2017
This paper presents the results on whispered speech recognition using gammatone filterbank cepstral coefficients for speaker dependent mode. The isolated words used for this experiment are taken from the Whi-Spe database. Whispered speech recognition is based on dynamic time warping and hidden Markov models methods. The experiments are focused on t...
Cite
Download full-text

Citations

... Whisper speech detection has become a research topic of interest [1], [2]. The differences in whispered vs. normally phonated speech are primarily due to the noisy structure, lower Signal-to-Noise-ratio (SNR), absence of glottal vibrations, shift in formant structures, etc. [3]. ...
Reference: Teager Energy Cepstral Coefficients for Classification of Normal vs. Whisper Speech
View full-text
... (Filter 3) The Gammatone filter was designed to express the performance of the human auditory system and to improve the automatic speech recognition system [14,24]. It is a linear filter that uses logarithmically spaced defined in the impulse response time, which is measured by the product of a sinusoidal tone and gamma distribution. ...
Reference: An ensemble technique for speech recognition in noisy environments
View full-text