Zobrazeno 1 - 10 of 59 pro vyhledávání: '"Jae Jin Jeon"'
1
Akademický článek
Acoustical characteristic predictions of a multi-layer system of a submerged vehicle hull mounted sonar simplified to an infinite planar model
Autor: Sung-Hee Kim, Suk-Yoon Hong, Jee-Hun Song, Hyun-Gwon Kil, Jae Jin Jeon, Young-Soo Seo
Publikováno v: International Journal of Naval Architecture and Ocean Engineering, Vol 4, Iss 2, Pp 96-111 (2012)
Hull Mounted Sonar (HMS) is a long range submerged vehicle's hull-mounted passive sonar system which detects low-frequency noise caused by machineries of enemy ships or submerged vehicles. The HMS needs a sound absorption /insulation multi-layer stru
Externí odkaz: https://doaj.org/article/94c7f94c2631418f8d7c7ec9f5f54c16
Zobrazit plný text záznamu
3
Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning
Autor: Eesung Kim, Jae-Jin Jeon, Hyeji Seo, Hoon Kim
Self-supervised learning (SSL) approaches such as wav2vec 2.0 and HuBERT models have shown promising results in various downstream tasks in the speech community. In particular, speech representations learned by SSL models have been shown to be effect
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04ce232b95c8c34ad45beadd23ccea43
http://arxiv.org/abs/2204.03863
Zobrazit plný text záznamu
5
U-Convolution Based Residual Echo Suppression with Multiple Encoders
Autor: Hyeji Seo, Eesung Kim, Jae-Jin Jeon
Publikováno v: ICASSP
In this paper, we propose an efficient end-to-end neural network that can estimate near-end speech using a U-convolution block by exploiting various signals to achieve residual echo suppression (RES). Specifically, the proposed model employs multiple
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::8184055a6663ebf7552c097940c4d3f0
https://doi.org/10.1109/icassp39728.2021.9414753
Zobrazit plný text záznamu
6
Multitask Learning and Joint Optimization for Transformer-RNN-Transducer Speech Recognition
Autor: Eesung Kim, Jae-Jin Jeon
Publikováno v: ICASSP
Recently, several types of end-to-end speech recognition methods named transformer-transducer were introduced. According to those kinds of methods, transcription networks are generally modeled by transformer-based neural networks, while prediction ne
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7cdb990daac8a16d13ef9b86eb1f9689
http://arxiv.org/abs/2011.00771
Zobrazit plný text záznamu
7
Akademický článek
Pseudo Wigner–Ville Time-Frequency Distribution and Its Application to Machinery Condition Monitoring
Autor: Young S. Shin, Jae-Jin Jeon
Publikováno v: Shock and Vibration, Vol 1, Iss 1, Pp 65-76 (1993)
Machinery operating in a nonstationary mode generates a signature that at each instant of time has a distinct frequency. A Time-frequency domain representation is needed to characterize such a signature. Pseudo Wigner–Ville distribution is ideally
Externí odkaz: https://doaj.org/article/9b1f6e5c64ee4eaeb08d15df13f0b8b1
Zobrazit plný text záznamu
8
A simple iterative independent component analysis algorithm for vibration source signal identification of complex structures
Autor: Jae Ho Kim, Myeng-Hwan Kang, Dong-Sup Lee, Woo-Jin Jung, Jae-Jin Jeon, Kookhyun Kim, Dae-Seung Cho
Publikováno v: International Journal of Naval Architecture and Ocean Engineering, Vol 7, Iss 1, Pp 128-141 (2015)
INTERNATIONAL JOURNAL OF NAVAL ARCHITECTURE AND OCEAN ENGINEERING(7): 1
Independent Component Analysis (ICA), one of the blind source separation methods, can be applied for extracting unknown source signals only from received signals. This is accomplished by finding statistical independence of signal mixtures and has bee
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02d9e705e30ca83572f573398c41fd46
http://www.sciencedirect.com/science/article/pii/S2092678216301066
Zobrazit plný text záznamu
10
A Study on the Transmitter Design for Transmitting Output Power Enhancement of Active Magnetic Sensor
Autor: Jae-Jin Jeon, Chang-Seob Yang, Hyun-Ju Chung
Publikováno v: Journal of the Korean Magnetics Society. 23:159-165
A active magnetic sensor has been widely used in the underwater guided weapon system because it is able to detect a target accurately in close range, but the target doesn`t have any good countermeasure to overcome the threat from the active magnetic
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9483b63a2ad972b57b3cbfbf8765528a
https://doi.org/10.4283/jkms.2013.23.5.159
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje