• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.33-38
• /
• 2018

Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.

• Proceedings of the KIEE Conference
• /
• 2006.10b
• /
• pp.175-180
• /
• 2006

In this paper, we develope a type of humanoid robot which can express its emotion against human actions. To interact with human, the developed robot has several abilities to express its emotion, which are verbal communication with human through voice/image recognition, motion tracking, and facial expression using fourteen Servo Motors. The proposed humanoid robot system consists of a control board designed with AVR90S8535 to control servor motors, a framework equipped with fourteen server motors and two CCD cameras, a personal computer to monitor its operations. The results of this research illustrate that our intelligent emotional humanoid robot is very intuitive and friendly so human can interact with the robot very easily.

• Journal of The Korean Association of Information Education
• /
• v.3 no.2
• /
• pp.113-119
• /
• 2000

I studied a distance education model for English learning on the Internet. Basic WWW files, that contain courseware, are constructed with HTML, and functions, which are required in learning, are implemented with Java. Students and educators can access the preferred unit composed of the appropriate text, voice and image data by using a WWW browser at any time. The education system supports the automatic generation facility of English problems to practice reading and writing by making good use of the courseware data or various English text resources located on the Internet. Our system has functions to manage and control the flow of distance learning and to offer interaction between students and the system in a distributed environment. Educators can manage students' learning and can immediately be aware of who is attending and who is quitting the lesson in virtual space. Also, students and educators in different places can communicate and discuss a topic through the server. I implemented these functions, which are required in a client/server environment of distance education, with the use of Java. The URL for this system is "http://park.taegu-e.ac.kr" in the name of GAIA.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1997.10a
• /
• pp.245-248
• /
• 1997

As the increasing the demand on information service, high-capacity and high-speed telecommunication networks are required. For the networks, very intelligent telecommunication equipments such as DCS(Digital Cross-connect System) will be employed for the fast service on the various types of information including voice, data and image. This paper considers the transmission networks composed of DCSs and optical fibers as nodes and links of the networks, respectively. For the networks, some types of restoration algorithms are compared their characteristics for their potential applications. And a distributed control algorithm is described as an empirical example which is implemented on the BDCS(Broadband Digital Cross-connect System), where the BDCS is a type of DCS developed in Korea. Finally, some remarks on the associated further researches are added.

• The Journal of Society for e-Business Studies
• /
• v.1 no.1
• /
• pp.159-171
• /
• 1996

Nowadays, multimedia and Hypermedia become hot topics in information industry. Due to high capacity of media storage and fast communication network, it is possible to exchange text data as well as image, moving picture and voice. Especially to apply hypermedia under CALS standard environment, the relation between international standard and CALS standard needs to be considered. This study introduces conceptual background and processing model of HyTime (Hypermedia Time-based Structuring Language) which is a specification of hypermedia exchange, Hyper ODA (Hyper Open Document Architecture) which is a major multimedia communication basis, MMCF (Multimedia Communication Forum), AHM(Amsterdam Hypermedia Model), and DSRM(DAVIC System Reference Model) reference model which helps determination of hypermedia communication specification Although they are international standard, provisional standard or non-standard, it discusses the Possibility of adopting them as CALS standard. Hence, this paper chooses the best recommend for CALS among these models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.6
• /
• pp.1062-1065
• /
• 2001

with the splendid development of internet environment Korea is a diverse proving ground and supplies the highest ADSL in the world. This thesis examines the tole-medicine treatment which connects the doctor's computer with the in each house and transmits blood pressure, pulsation, temperature, blood sugar, image picture stethoscope, voice.

• Journal of the Korean Society for information Management
• /
• v.10 no.1
• /
• pp.15-30
• /
• 1993

Hypermedia system supports associative linking concept for multimedia information using link and node concept, and overcomes the limitations of database system and text retrieval system in some application areas. This study shows the design and implementation of a hypermedia system which supports text, graphics, image and voice /sound information. This system has been designed to integrate the browsing and searching functions of the hypermedia system for efficient multimedia information retrieval and user-interface. To demonstrate the function and capability of the system, an application was made in the area of Bible and related information.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05d
• /
• pp.797-801
• /
• 2002

Information network technologies introduce a new education environment. Cyber education is growing rapidly as a field of practice especially in distance education system. The development of multimedia environment based on such technology as graphics, image, voice, and video, personal computer systems use has become the media for interactive teaching-teaming service. These features have made integrated multimedia education feasible. This research suggested a direction for the development of an interactive distance education system. I have developed an education system which cooperate problem bank and learning system. This system support arbitration of the relative difficulty in the problem bank database. An ongoing version of this research was evaluated. Those findings reveal several factors that influence how the proposed system can be tailored to the students' perspectives in order to come up with the enhanced version of this system.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.295-298
• /
• 1997

We developed the system that enables patients to be treated at home during their daily life through digital telemetry and public communication line. This system records and transfers ECG signals through wireless digital telemetry unhindering the patient's normal activities in long-term recording, and transmits the processed data, which enables real-time remote examination via ISDN phone line. Patient's image, voice, and transmitted signals are transferred to medical experts in remote medical center interactively.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1391-1394
• /
• 2005

The VoIP (Voice over IP) is being used world-widely and already put to practical use in many fields. However, it is needed to ensure the security of VoIP call in special situations. It is relatively difficult to eavesdrop commonly used PSTN network in that a 1:1 circuit connects it. However, it is difficult to ensure the security of a call on Internet because many users are connected to the Internet concurrently. This paper suggests a new model for Internet telephony to prevent eavesdrops, using VoIP (using SIP protocol) with the use the VPN protocol and establish the feasibility of its practical use comparing it with the conventional Internet telephony.