• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.12
• /
• pp.1841-1854
• /
• 1993

In this paper, the packet voice protocol for the transmission of voice signal onto ethernet is implemented in a personal computer (PC). The packet voice protocol used is a modified one from CCITT G.764 packetized voice protocol. The hardware system to facilitate the voice communication onto ethernet is divided into telephone interface, speech processing, PC interface and controllers. The software structure of the protocol is designed according to the OSI seven layer architecture and is divided into three routines : ethernet device driver, telephone interface, and processing routine of the packet voice protocol. Experiments through ethernet with telephone interface show that this packet voice communication achieves satisfactory quality when the network traffic is light.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.8A
• /
• pp.1206-1212
• /
• 2000

The subscriber loop subnet at domestic wired telephony networks uses one circuit per one subscriber and the transmission network subnet uses TDM that is composed to 30 voice channels and is assigned to 64kbps per one voice channel of 2.048Mbps in El. On the contrary, the subscriber networks for cellular networks is extent to channel capacity and make it efficiency use CDMA method but the transmission network is used to the same as telephony. In this paper, The subscriber loop at wired network also is shown to increasing effective and lower expensive using CDM.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.9
• /
• pp.825-831
• /
• 2007

In this paper, an interface between a human and a computer is presented. The human and computer interface(HCI) serves as another area of human and machine interfaces. Methods for the HCI we used are voice recognition and image recognition for detecting human's emotional feelings. The idea is that the computer can recognize the present emotional state of the human operator, and amuses him/her in various ways such as turning on musics, searching webs, and talking. For the image recognition process, the human face is captured, and eye and mouth are selected from the facial image for recognition. To train images of the mouth, we use the Hopfield Net. The results show 88%$\sim$92% recognition of the emotion. For the vocal recognition, neural network shows 80%$\sim$98% recognition of voice.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.2
• /
• pp.143-146
• /
• 2017

In this paper, a novel approach is proposed to improve the performance of speech/music classification using the recurrent neural network (RNN) in the enhanced voice services (EVS) of 3GPP for hearing aids. Feature vectors applied to the RNN are selected from the relevant parameters of the EVS for efficient speech/music classification. The performance of the proposed algorithm is evaluated under various conditions and large speech/music data. The proposed algorithm yields better results compared with the conventional scheme implemented in the EVS.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.2 no.3
• /
• pp.9-16
• /
• 2003

In this paper, we propose the burst error reduction (BER) algorithm for VoIP service in the wireless LAN network. In end point device, this BER algorithm can be achieved packet loss bounded QoS provisioning using interleaving in buffering and FEC (Forward Error Correction) through transmitting voice packet. BER algorithm can reduced the voice packet loss rate 5.5%-60% in VoIP network using wireless LAN.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.32.3-32
• /
• 2001

This paper proposes a layered protocol to interpret voice commands of the user´s own language to a machine, to control it in real time. The layers consist of speech signal capturing layer, lexical analysis layer, interpretation layer and finally activation layer, where each layer tries to mimic the human counterparts in command following. The contents of a continuous voice command are captured by using Hidden Markov Model based speech recognizer. Then the concepts of Artificial Neural Network are devised to classify the contents of the recognized voice command ...

• Journal of KIISE:Information Networking
• /
• v.27 no.1
• /
• pp.68-75
• /
• 2000

In this paper, a media access control protocol is proposed for voice/data integrated services in the packet CDMA network, and the performance of the proposed protocol is analyzed. The proposed protocol uses the spreading code sensing and the reservation schemes. This protocol gives higher priority to the delay-sensitive voice traffic than to the data traffic. A voice terminal can reserve an available spreading code during a talkspurt to transmit multiple voice packets. On the other hand, whenever a data packet is generated, the data terminal transmits the packet through one of the available spreading codes that are not used by the voice terminals. In this protocol, the voice packets do not come into collision with the data packets. The numerical results show that this protocol can increase the maximum number of voice terminals. The performance for the data traffic degrades by increasing the voice traffic load because of the low priority. But it shows that the data traffic performance can be increased in proportion to the number of spreading codes.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.369-372
• /
• 2018

This paper suggests non-parallel-voice-conversion network conversing voice between unmapped voice pair as source voice and target voice. Conventional voice conversion researches used learning methods that minimize spectrogram's distance error. Not only these researches have some problem that is lost spectrogram resolution by methods averaging pixels. But also have used parallel data that is hard to collect. This research uses PPGs that is input voice's phonetic data and a GAN learning method to generate more clear voices. To evaluate the suggested method, we conduct MOS test with GMM based Model. We found that the performance is improved compared to the conventional methods.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.42 no.2 s.332
• /
• pp.89-96
• /
• 2005

In this paper, we propose a customer premise platform for processing multimedia data service on the ATM network. The proposed platform has a specific AAL2 processor that includes AAL2 protocol and scheduler algorithm so as to off-load large potion of burden from host processor and make it easy to process multimedia data from the ATM network in real time compared with conventional platform in which AAL/ATM tasks are processed by software. The ATS scheduler that is implemented based on 2-level time slot ring provides a simple and efficient method for scheduling data of VBR-rt, UBR and CBR traffics. TMS320C5402 DSP is used to process voice-related tasks such as voice compression and voice packet manupulation and AAL2 processor is implemented on $0.35\;{\mu}m$ process line. We implemented the customer premise equipment for VoDSL service and tested the proposed platform on a test bed network. The experimental results show that the proposed equipment has the call success rate of $97\%$ at least and provides voice service of toll-qualify.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.11
• /
• pp.2405-2410
• /
• 2012

The 4th generation mobile communication system, LTE, does not support an additional core network to provide voice service, and it is merged into a packet network based on all IP. Although Voice service over LTE can be supported by VoIP, it will be provided by the existing 3G networks because of the discontinuity of LTE coverage. However, it is inevitable to adopt VoIP over LTE to provide high quality voice service. In this paper, we investigate the capacity of VoIP over LTE. Our results indicate that spectral efficiency can be significantly improved as channel bandwidth increases in terms of VoLTE capacity. In addition, we can achieve higher VoLTE capacity without decreasing control channel capacity.