• Journal of Advanced Marine Engineering and Technology
• /
• 제32권5호
• /
• pp.768-774
• /
• 2008

In many areas of speech signal processing such as automatic speech recognition and packet based voice communication technique, VAD (voice activity detection) plays an important role in the performance of the overall system. In this paper, we present a new feature parameter for VAD which is the product of energy of the signal and the difference of two types of entropies. For this end, we first define a Mel filter-bank based entropy and calculate its difference from the conventional entropy in frequency domain. The difference is then multiplied by the spectral energy of the signal to yield the final feature parameter which we call PEED (product of energy and entropy difference). Through experiments. we could verify that the proposed VAD parameter is more efficient than the conventional spectral entropy based parameter in various SNRs and noisy environments.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.261-263
• /
• 2006

Nowadays, technologies such as RFID, sensor network makes our life comfortable more and more. In this paper we propose a wearable computing system for blind and deaf person who can be easily out of sight from our technology. We are making a wearable computing system that is consisted of embedded board to processing data, ultrasonic sensors to get distance data and motors that make vibration as a signal to see the screen for a deaf person. This system offers environmental informations by text and voice. For example, distance data from a obstacle to a person are calculated by data compounding module using sensed ultrasonic reflection time. This data is converted to text or voice by main processing module, and are serviced to a handicapped person. Furthermore we will extend this system using a voice recognition module and text to voice convertor module to help communication among the blind and deaf persons.

• 한국생산제조학회지
• /
• 제20권2호
• /
• pp.207-213
• /
• 2011

In this paper, we present a study on the real-time implementation of mobile robot to which the interactive voice recognition technique is applied. The speech command utters the sentential connected word and asserted through the wireless remote control system. We implement an automatic distance speech command recognition system for voice-enabled services interactively. We construct a baseline automatic speech command recognition system, where acoustic models are trained from speech utterances spoken by a microphone. In order to improve the performance of the baseline automatic speech recognition system, the acoustic models are adapted to adjust the spectral characteristics of speech according to different microphones and the environmental mismatches between cross talking and distance speech. We illustrate the performance of the developed speech recognition system by experiments. As a result, it is illustrated that the average rates of proposed speech recognition system shows about 95% above.

• 한국산업융합학회 논문집
• /
• 제18권1호
• /
• pp.10-17
• /
• 2015

We describe a research about remote control of mobile robot based on voice command in this paper. Through real-time remote control and wireless network capabilities of an unmanned remote-control experiments and Home Security / exercise with an unmanned robot, remote control and voice recognition and voice transmission are possible to transmit on a PC using a microphone to control a robot to pinpoint of the source. Speech recognition can be controlled robot by using a remote control. In this research, speech recognition speed and direction of self-driving robot were controlled by a wireless remote control in order to verify the performance of mobile robot with two drives.

• 한국음향학회지
• /
• 제18권6호
• /
• pp.71-76
• /
• 1999

디지털 이동 통신 시스템에서 서로 다른 음성 압축기를 사용하는 단말기 사이의 통신은 음성 신호를 두 번의 압축/복원 과정을 거쳐 전달하므로 음질 저하, 계산량 증가, 전달 지연 증가 등의 문제를 발생시킨다. 본 논문에서는 이와 같은 단말기 사이의 통신에서의 문제점을 해결하기 위하여 음성 패킷 변환 방법을 제안하고, 13kbps QCELP 패킷을 8kbps QCELP 패킷으로 변환하는 방법을 개발한다. 여러 음성 신호를 이용한 모의 실험 결과, 본 논문에서 개발된 패킷 변환기가 짧은 음성전달 지연과 약 33%의 계산량으로 일반적인 이중 압축 방법과 동등한 음질의 음성 신호를 합성하는 것을 확인하였다.

• International journal of advanced smart convergence
• /
• 제9권4호
• /
• pp.209-214
• /
• 2020

VoIP technology has been widely used for exchanging voice or image data through IP networks. VoIP technology, often called Internet Telephony, sends and receives voice data over the RTP protocol during the session. However, there is an exposition risk in the voice data in VoIP using the RTP protocol, where the RTP protocol does not have a specification for encryption of the original data. We implement programs that can extract meaningful information from the user's dialogue. The meaningful information means the information that the program user wants to obtain. In order to do that, our implementation has two parts. One is the client part, which inputs the keyword of the information that the user wants to obtain, and the other is the server part, which sniffs and performs the speech recognition process. We use the Google Speech API from Google Cloud, which uses machine learning in the speech recognition process. Finally, we discuss the usability and the limitations of the implementation with the example.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.567-569
• /
• 2021

Due to the important role of avatars in computer-mediated communication (CMC), a growing number of CMC-based services now support avatar customization options. However, in many cases, customization and personalization options are limited to visual features. In this paper, we propose and describe a prototype for a vocal customization web application. Titled Voice Creator, the app is designed for both able-bodied and speech- or hearing-impaired users who seek to communicate anonymously using digital voice identities.

• 한국군사과학기술학회지
• /
• 제14권2호
• /
• pp.222-231
• /
• 2011

In this paper, we have proposed a method which can make it possible to stably transmit and receive data like the ARC-164 radio frequency hopping environment as a S/W packet modem with PSK modulation. This is a method that the S/W packet modem with PSK digital modulation and the use of PC sound cards change over from data to voice signals and then transmit/receive data. We confirmed not only that it is possible to solve the slow speed communication with the use of sending data through multi-channels and PSK modulation that has the ability to methodically improve transmission rates, but also that it is possible to send the state of frequency hopping stably. In conclusion, we've confirmed both tactical values that though the transmission rate may be a tad slow, a state of frequency hopping of more than 94% confidence plus voice and data can be sent via radio at the same time. In this paper, the proposed S/W packet modem is only an implemented S/W component, so when we apply it to aircraft that we don't consider EMC problems with, then we have the advantage of a wider use of conventional UHF/VHF/HF radio that is possible to voice communication. If we recognize these operational requirements, we can apply for a lot of field equipment efficiently.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2010년도 제42차 하계학술발표논문집 18권2호
• /
• pp.173-179
• /
• 2010

현재 통신 시스템은 무선화와 멀티미디어화의 두 방향으로 진행되고 있으며 이전 시스템에 비해 커다란 전송 용량을 요구하고 있다. 이러한 상황에서 통신 서비스는 서로 다른 전송률과 특징을 가지는 두 개의 다른 서비스 형태로 존재한다. 예를 들어 음성/비디오 서비스는 약간의 오류를 허용하나 실시간 전송이 돼야 하고, 데이터는 실시간성은 떨어지나 하나의 비트 오류라도 재전송을 해야 한다. 음성/데이터 혼합 트래픽의 갑작스러운 증가에 대해 오류가 허용되는 실시간 음성/영상 데이터에 대해 우선 전송하고 지연이 허용되는 일반 데이터는 BER이 낮아진 후에 전송하면 높은 쓰루풋을 갖게 될 것이다. 이 논문에서는 비동기 unslotted ALOHA CDMA 시스템을 가정하여 이 시스템에 대해 혼합된 음성/영상 및 컴퓨터 데이터가 전송될 때 트래픽 용량의 계산식을 유도하였으며 그 결과를 제시하였다. 이를 이용하면 시스템의 트래픽 분석과 변화하는 트래픽에 대해 이론적 해석이 쉬워지리라 본다.

• 한국통신학회논문지
• /
• 제11권2호
• /
• pp.108-121
• /
• 1986

音聲과 데이터가 集積된 패킷 通信網의 性能을 豫測하고 시스템 파라메터를 最適化하기 위한 시뮬레이터의 개발에 관하여 記述하였다. 具現된 시뮬레이터는 CCITT의 勸告事項에 따라 運用되는 데이터 터미널이나 host는 물론 패킷 音聲터미널도 연결가능한 音聲 및 데이터集積通信網의 性能을 여러 상황에서 豫測할 수 있다. 시뮬레이션 技法으로는 지금까지 알려진 세가지 discrete event 시뮬레이션 技法 중 process interaction 方法이 사용되었는데 이 方法을 사용하면 실제 시스템과 가장 비슷한 시뮬레이터를 具現할 수 있다. 시뮬레이터는 약 4,000line의 GPSS 시뮬레이션 언어와 PL/I으로 具現되었다. 시뮬레이터의 컴퓨터 run time을 줄이기 위하여 GPSS의 LINK block을 사용함으로써 條件的 event의 數를 줄이는 方法을 사용하였다. 구현된 시뮬레이터를 사용하여 7-node 通信網의 性能을 豫測하였다. 또 개발된 시뮬레이터의 妥當性을 檢證하기 위하여 간단한 音聲과 데이터 multiplexer를 시뮬레이션 모델로 구성한 뒤 그 시뮬레이션 결과를 解釋的 방법에 依한 결과와 比較하였다.