Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Jovan Galic"'
Autor:
Jovan Galic, Branko Markovic
Publikováno v:
2020 Zooming Innovation in Consumer Technologies Conference (ZINC).
In this paper an analysis on the recognition of words from speech database Whi-Spe in normal and whispered phonation, based on the conventional HMM/GMM framework, is presented. The analysis based on multi-style training is performed in the speaker de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fc3b775b03e2bef3589b2acc1c7cd2fc
https://doi.org/10.1109/zinc50678.2020.9161815
https://doi.org/10.1109/zinc50678.2020.9161815
Publikováno v:
Journal of Communications Technology and Electronics. 62:1255-1261
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
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1cc033b21e97b5e72b2159f46bba8b8c
https://doi.org/10.1134/s1064226917110134
https://doi.org/10.1134/s1064226917110134
Publikováno v:
Advances in Electrical and Computer Engineering, Vol 17, Iss 1, Pp 21-26 (2017)
This article presents an analysis of different cepstral normalization techniques in automatic recognition of whispered and bimodal speech (speech+whisper). In these experiments, conventional GMM-HMM speech recognizer was used as speaker-dependant aut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d9c3f608cf582b1b0e31f36bad37fbde
https://doaj.org/article/9cd6d513acde440db1d31508dcb3fb32
https://doaj.org/article/9cd6d513acde440db1d31508dcb3fb32
Publikováno v:
2019 18th International Symposium INFOTEH-JAHORINA (INFOTEH).
This paper presents the implementation of an Internet of Things (IoT) application that performs the sound level monitoring. The phonometer used for sound level measuring is connected on Arduino MEGA combined with ESP8266 WiFi module. The data transfe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3bfe8ddefc29de166b52fda6fd548a62
https://doi.org/10.1109/infoteh.2019.8717759
https://doi.org/10.1109/infoteh.2019.8717759
Publikováno v:
Applied Sciences, Vol 14, Iss 18, p 8223 (2024)
Modern Automatic Speech Recognition (ASR) systems are primarily designed to recognize normal speech. Due to a considerable acoustic mismatch between normal speech and whisper, ASR systems suffer from a significant loss of performance in whisper recog
Externí odkaz:
https://doaj.org/article/5fb45371a47c41fe8d1f0764bdf75b57
Publikováno v:
2018 International Symposium on Industrial Electronics (INDEL).
In this paper, the design and the implementation of the low-voltage class D audio amplifier is presented. The amplifier topology with reduced distortion, based on the Pulse Density Modulation (PDM) technique, is proposed. The verification of the prop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::934349255f6a32bb22c7a01cd8a8fadb
https://doi.org/10.1109/indel.2018.8637607
https://doi.org/10.1109/indel.2018.8637607
Autor:
Branko Markovic, Slobodan T. Jovicic, Dragana Sumarac Pavlovic, Jovan Galic, Dorde T. Grozdic
Publikováno v:
2017 25th Telecommunication Forum (TELFOR).
This paper presents the results of experiments in recognition of whispered speech, as a specific mode of verbal communication, using SVM (Support Vector Machines) classifier. For training and testing purposes, part of the speech database Whi-Spe with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85a53863ce4a06ca413f61402f96db0a
https://doi.org/10.1109/telfor.2017.8249360
https://doi.org/10.1109/telfor.2017.8249360
Publikováno v:
2016 Zooming Innovation in Consumer Electronics International Conference (ZINC).
In this paper, an analysis of intermodulation distortion of class D audio amplifier is presented. Class D audio amplifier uses MOSFETs in switching mode is designed. The amplifier system contains a modulator and an output low-pass filter. Both modula
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7323db84342f80b48fd3a4674cc73b97
https://doi.org/10.1109/zinc.2016.7513652
https://doi.org/10.1109/zinc.2016.7513652
Autor:
Slobodan T. Jovicic, Đorđe Grozdić, Dragana Sumarac Pavlovic, Branko Markovic, Jovan Galic, Vlado Delic
Publikováno v:
SPIIRAS Proceedings. 3:27
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fe282f87fa16087f97f51a8fa471a038
https://doi.org/10.15622/sp.58.2
https://doi.org/10.15622/sp.58.2
Publikováno v:
12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL).
The differences between normal speech and whisper, particularly in terms of their acoustic characteristics, are serious problem of ASR (Automatic Speech Recognition) systems. This paper presents the preliminary results of the new way of speech signal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b840856abd35d6c7fedc43f2bf14ae68
https://doi.org/10.1109/neurel.2014.7011492
https://doi.org/10.1109/neurel.2014.7011492