• Proceedings of the KSPS conference
• /
• 2006.05a
• /
• pp.89-93
• /
• 2006

This paper presents ETRI broadcast news speech recognition system. There are two major issues on the broadcast news speech recognition: 1) real-time processing and 2) out-of-vocabulary handling. For real-time processing, we devised the dual decoder architecture. The input speech signal is segmented based on the long-pause between utterances, and each decoder processes the speech segment alternatively. One decoder can start to recognize the current speech segment without waiting for the other decoder to recognize the previous speech segment completely. Thus, the processing delay is not accumulated. For out-of-vocabulary handling, we updated both the vocabulary and the language model, based on the recent news articles on the internet. By updating the language model as well as the vocabulary, we can improve the performance up to 17.2% ERR.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.157-159
• /
• 2014

In this paper, we introduce SlimSRP, an ultra-low-power digital signal processor (DSP) solution for mobile audio and voice applications. So far, application processors (APs) have taken charge of all the tasks in mobile devices. However, they have suffered from short battery life problems to deal with complex usage scenarios, such as always-on voice trigger with continuous audio playback. From extensive analysis of audio and voice application characteristics, SlimSRP is designed to relive the performance and power burden of APs. It employs three-issue VLIW architecture, and the major low-power and high-performance techniques include: (1) an optimized register-file architecture friendly for constants generation, (2) a powerful instruction set to reduce the number of register file accesses and (3) a unique instruction compression scheme that contributes to saved memory size and reduced cache miss. An implementation of SlimSRP runs at up to 200MHz and the logic occupies 95K NAND2 gates in Samsung 28LPP process. The experimental results demonstrate that a MP3 decoder application with a 128kbps 44.1kHz input can run at 5.1MHz and the logic consumes only 22uW/MHz.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.773-777
• /
• 2009

In recent years, the field of synthesizing voice has been developed rapidly, and the technologies such as reading aloud an email or sound guidance of a car navigation system are used in various scenes of our life. The sound quality is monotonous like reading news. It is preferable for a text such as a novel to be read by the voice that expresses emotions wealthily. Therefore, we have been trying to develop a system reading aloud novels automatically that are expressed clear emotions comparatively such as juvenile literature. At first it is necessary to identify emotions expressed in a sentence in texts in order to make a computer read texts with an emotionally expressive voice. A method on the basis of the meaning interpretation that utilized artificial intelligence technology for a method to specify emotions of texts is thought, but it is very difficult with the current technology. Therefore, we propose a method to determine only emotion every sentence in a novel by a simpler way. This method determines the emotion of a sentence according to an emotion that words such as a verb in a Japanese verb sentence, and an adjective and an adverb in a adjective sentence, have. The emotional characteristics that these words have are prepared beforehand as a emotional words dictionary by us. The emotions used here are seven types: "joy," "sorrow," "anger," "surprise," "terror," "aversion" or "neutral."

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.1024-1034
• /
• 2019

Preference for music is determined by a variety of factors, and identifying characteristics that reflect specific factors is important for music recommendations. In this paper, we propose a method to extract the singing voice related music features reflecting various musical characteristics by using a model learned for singer identification. The model can be trained using a music source containing a background accompaniment, but it may provide degraded singer identification performance. In order to mitigate this problem, this study performs a preliminary work to separate the background accompaniment, and creates a data set composed of separated vocals by using the proven model structure that appeared in SiSEC, Signal Separation and Evaluation Campaign. Finally, we use the separated vocals to discover the singing voice related music features that reflect the singer's voice. We compare the effects of source separation against existing methods that use music source without source separation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.11
• /
• pp.2178-2187
• /
• 2015

Bluetooth Low Energy (Bluetooth LE) is a representative break-through communication technology for wireless personal area networks on nowaday. In this environment, most of significant performance should be aiming to energy efficiency due to the policy for manufacturing light-weighted communication devices derived from requirement of world IoT market, and many researches have been developed to satisfy this requirement. While Bluetooth LE has been leading the low power communication technology required from the current market by employing duty cycle and frequency hopping approaches, it couldn't address the problem of reliability on broadcast transmissions. The main goal of this paper is aiming to addressing this problem by suggesting a new method. Furthermore analytic evaluations would also be proceeded to find objective results in the view point of broadcast transmission efficiency from Master device.

• Fire Science and Engineering
• /
• v.27 no.1
• /
• pp.14-19
• /
• 2013

In this paper, I have developed an automatic distress notification system (ADNS) working with an external VHF device in small ship. The proposed system is as part of a small ship disaster analysis system which can detect and quickly respond to the small ship disaster. The automatic notification system receives the location information signal from the disaster analysis system, and the signal will be converted into voice signal to broadcast of the accident position through external VHF device. It will be sending a distress message as form of voice information through VHF device until sinking under the water. Through this research, I expect we'll be make a quick response and prevent a terrible loss of human life.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.165-172
• /
• 2009

Integrated management model (SNMP/SMI) for lubiquitous egacy remote communication network or service make possible combination of various architecture. However, legacy management system cannot be applied some problems such as inefficient, complexly, implement and large network by reason of integration of voice and data, wired and wireless, and service area between service provider. For improve this, supplied JMX(Java Management eXtensions) on network management technology from SUN. JMX is integrated architecture for existing network management and monitoring. In this paper, we design and implement for integrated network management through multi-protocol agent using JMX.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.272-274
• /
• 2011

최근 들어 케이블 방송망을 기반으로 한 디지털 방송, VoIP(Voice over Internet Protocol), VOD(Video on Demand), 영상전화, 이동전화, 무선 랜 로밍 등의 다양한 멀티미디어 서비스의 출현과 향후 도입될 새로운 융합형 멀티미디어 서비스의 수용을 위해 케이블 망의 고도화에 대한 요구가 제기되었다. 특히 유럽을 중심으로 이러한 요구를 만족시키기 위해 DVB(Digital Video Broadcasting)-C2 규격의 개발이 진행되었다. DVB-C2 규격에서는 기존의 게이블 전송 규격인 DVB-C에 대해 30% 이상의 전송 효율을 높이고자 새로운 변조 방식과 채널 오류정정 부호 방식을 도입하였다. 이에 본 논문은 본 논문에서는 DVB-C2 규격에서 도입된 채널 오류정정 부호인 BCH(Bose, Chaudhuri, and Hocquenghem) 부호와 LDPC(Low Density Parity Check) 부호의 연접 방식에 대한 성능을 검증하고자 한다. 이를 위해 개발된 시뮬레이터의 소개와 이를 통한 시험결과를 제시한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.482-483
• /
• 2011

본 논문에서는 스마트TV향 VoIP(Voice over Internet Protocol) 컨퍼런스 기능을 위한 잡음제거 알고리즘의 성능비교 하였다. 기존에 연구 되어져 있는 Improved Minima Controlled Recursive Averaging(IMCRA)방식과 Gaussian분포 기반의 잡음제거 알고리즘, IMCRA방식과 Gamma분포 기반의 잡음제거 알고리즘, IMCRA방식과 Mel-filter를 적용한 잡음제거 알고리즘, R&L 알고리즘들의 방식을 비교하였으며, 성능 비교를 위해 각 알고리즘을 통해 나온 다양한 잡음 환경에서의 잡음이 제거된 신호의 PESQ와 연산속도를 비교한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.79-81
• /
• 2017

최근 오디오 기반의 그룹 대화 통신 기술이 급격히 발전하고 있는데 이는 원거리 간의 회의 또는 긴급 구조망, 음성 인식을 활용한 기술 분야에서 필요로 하기 때문이다. 과거 오디오 그룹 간의 실시간 서비스는 영상 통신보다 타이밍에 있어서 사용자에게 딜레이 되는 값을 전송하는 즉 버퍼 컨트롤이 문제가 되어 잘 사용되지 않았었다. 하지만 최근 다중경로 라우팅, QoS 전송량 감소 기술들이 소개되면서 N:N의 대화가 가능하게 되었다. 본 연구에서는 UDP Socket 방식을 활용하여 N:N 실시간 음성 서비스를 개발한다. 이는 무선단말기를 활용하여 3~4인이 그룹핑 되어 노래 경쟁을 할 수 있는 앱에 적용하여 개발하였다. 운전자가 혼자 운전할 때, 다른 지역에서 운전하는 사람들과 음성인식 인터페이스를 활용하여 즉각적인 그룹을 만들고, 자신과 다른 사람들이 노래를 부르고, 듣고 평가하는 과정에서 재미를 느끼게 함으로써 졸음을 방지할 수 있도록 개발하였다.