• Title/Summary/Keyword: 음성분석 및 변환

Search Result 65, Processing Time 0.024 seconds

Matching Pursuit Estimation and Quantizer Design for Sinusoidal Model-based Coder (정현파 모델 부호화기를 위한 MP(Matching Pursuit) 알고리즘과 파라미터 양자화기)

  • Ahn Yeong-Uk;Jeong Gyu-Hyeok;Kim Jong-Hak;Yang Yong-Ho;Lee In-Sung
    • The Journal of the Acoustical Society of Korea
    • /
    • v.24 no.7
    • /
    • pp.402-409
    • /
    • 2005
  • In this paper. we propose a coding method using a matching pursuit algorithm in a strongly periodic highband signal. Also. we propose an efficient quantizer for the estimated parameters : spectral magnitude and phase. Based on the error concealment principle and sinusoidal model. the MP algorithm requires the high-precision pitch period estimation. To estimate more accurate pitch period. the refined pitch obtained from lowband speech is used. which increases the efficiency of bit allocation. The spectral magnitude parameters are quantized by the method which is combined with MDCT (Modified Discrete Cosine Transform) and multi-stage structure. The spectral phase quantizer uses the $2{\pi}$ modular characteristic of phases and the weighted function by spectral magnitudes. To evaluate the efficiency of the proposed method. we applied it to analysis-by-synthesis system. Furthermore we suggest the possibillity of scalable wideband speech codecs based on band-split structure.

Morphology Representation using STT API in Rasbian OS (Rasbian OS에서 STT API를 활용한 형태소 표현에 대한 연구)

  • Woo, Park-jin;Im, Je-Sun;Lee, Sung-jin;Moon, Sang-ho
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2021.10a
    • /
    • pp.373-375
    • /
    • 2021
  • In the case of Korean, the possibility of development is lower than that of English if tagging is done through the word tokenization like English. Although the form of tokenizing the corpus by separating it into morpheme units via KoNLPy is represented as a graph database, full separation of voice files and verification of practicality is required when converting the module from graph database to corpus. In this paper, morphology representation using STT API is shown in Raspberry Pi. The voice file converted to Corpus is analyzed to KoNLPy and tagged. The analyzed results are represented by graph databases and can be divided into tokens divided by morpheme, and it is judged that data mining extraction with specific purpose is possible by determining practicality and degree of separation.

  • PDF

Real-Time Implementation of the EHSX Speech Coder Using a Floating Point DSP (부동 소수점 DSP를 이용한 4kbps EHSX 음성 부호화기의 실시간 구현)

  • 이인성;박동원;김정호
    • The Journal of the Acoustical Society of Korea
    • /
    • v.23 no.5
    • /
    • pp.420-427
    • /
    • 2004
  • This paper presents real time implementation of 4kbps EHSX (Enhanced Harmonic Stochastic Excitation) speech coder that combines the harmonic vector excitation coding with time-separated transition coding. The harmonic vector excitation coding uses the harmonic excitation coding for voiced frames and used the vector excitation coding with the structure of analysis-by-synthesis for unvoiced frames, respectively. For transition frames mixed with voiced and unvoiced signal, we use the time-separated transition coding. In this paper. we present the optimization methods of implementation speech coder on the EMS320C6701/sup (R)/ DSP. To reduce the complex for real-time implementation. we perform the optimization method in algorithm by replacing the complex sinusoidal synthesis method with IFFT. and we apply fully pipelines hand assembly coding after converting it from floating source to fixed source. To generate a more efficient code. we also make use or the available EMS320C6701/sup (R)/ resources such as Fastest67x library and memory organization.

A Study on Knowledge based Conference Management System Architecture (지식 기반 회의관리 시스템 아키텍처에 관한 연구)

  • Kim Chang-Su;Jung Hoe-Kyung;Lee Soo-Youn
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.10 no.9
    • /
    • pp.1691-1699
    • /
    • 2006
  • This thesis proposes standard of knowledge-base system architecture for managing conferences in order to make ontology in the put of a conference rather than all parts. Also, this thesis proposes possibility of developing into the system that systematize transformed and processed information through various recognition systems, video conference, speech recognition, motion recognition, and so on, make knowledge and analyze it after preparing standards of objective estimation through simulation and analysis.

Home Gateway Technology and Standardization (홈게이트웨이 표준화 동향)

  • Lee, H.R.;Jeong, Y.K.
    • Electronics and Telecommunications Trends
    • /
    • v.19 no.5 s.89
    • /
    • pp.71-77
    • /
    • 2004
  • 홈네트워크 산업은 최근 국민소득 2만 달러 시대를 달성하기 위해 범 국가적으로 추진중인 9대 신성장동력에 포함되는 등 국내외적으로 그 중요성이 확산되고 있다. 이러한 홈네트워크 산업을 구성하는 핵심 기술인 홈게이트웨이 기술은 액세스망과 댁내망을 연결하는 네트워크 접속을 주 기능으로 하여 네트워크주소관리, 네트워크 보안, 프로토콜 변환, 음성서비스 기능 등을 제공하는 장치로서, 가정 내의 모든 정보가전기기가 유ㆍ무선 홈네트워크로 연결되어 누구나 기기, 시간, 장소에 구애받지 않고 다양한 홈디지털서비스를 제공 받을 수 있는 미래 지향적인 가정 환경을 제공하는 기술이다. 세계 각국에서는 이와 같은 홈게이트웨이 제품 및 관련 홈네트워크 서비스의 상호호환성과 상호운용성 증진을 도모함과 동시에 세계시장을 선점하고, 기술적 우위를 확보하기 위해 전략적으로 표준화 활동에 참여하고 있는 추세이다. 본 고에서는주요 외국의 홈게이트웨이 제품 동향과 국내외 주요 표준화 단체의 최근 표준화 진행 동향에 대해 살펴본다.

Sequence-to-sequence based Morphological Analysis and Part-Of-Speech Tagging for Korean Language with Convolutional Features (Sequence-to-sequence 기반 한국어 형태소 분석 및 품사 태깅)

  • Li, Jianri;Lee, EuiHyeon;Lee, Jong-Hyeok
    • Journal of KIISE
    • /
    • v.44 no.1
    • /
    • pp.57-62
    • /
    • 2017
  • Traditional Korean morphological analysis and POS tagging methods usually consist of two steps: 1 Generat hypotheses of all possible combinations of morphemes for given input, 2 Perform POS tagging search optimal result. require additional resource dictionaries and step could error to the step. In this paper, we tried to solve this problem end-to-end fashion using sequence-to-sequence model convolutional features. Experiment results Sejong corpus sour approach achieved 97.15% F1-score on morpheme level, 95.33% and 60.62% precision on word and sentence level, respectively; s96.91% F1-score on morpheme level, 95.40% and 60.62% precision on word and sentence level, respectively.

Performance Enhancement of Underwater Acoustic Communication System Using Hydrophone Transmit Array (하이드로폰 송신 어레이를 이용한 수중 음향 통신 시스템의 성능 향상)

  • 이외형;손윤준;김기만
    • The Journal of the Acoustical Society of Korea
    • /
    • v.21 no.7
    • /
    • pp.606-613
    • /
    • 2002
  • In this paper we applied a transmit beamforming technique to the underwater acoustic communication system for high rate data transmission. A prototype transmit system was designed and implemented with the general purpose DSP processor and multiple digital-to-analog converters. The performances of the implemented system were evaluated by the experiment in water tank. In order to simplify the procedure the channel coding and equalizer were omitted. And the simplest OOK (On-Off Keying) technique in digital communication methods was applied. The experimental result shows that the transmission data rate is higher about 3 times in the case of 5 hydrophone transmitting may than 1 hydrophone transmitter at bit error rate 10/sup -2/. We verified that the maximum data rate was 400 bps for speech signal transmission in water tank.

Test Case Generation of GSMP Protocol for Open Multiservice Switching System (개방형 멀티서비스 교환 시스템에서 GSMP의 시험열 생성 기법)

  • Lee, Hyun-Jeong;Choi, Young-Il;Lee, Byung-Sun;Jun, Kyung-Pyo
    • Annual Conference of KIPS
    • /
    • 2000.10b
    • /
    • pp.1129-1132
    • /
    • 2000
  • 최근 인터넷 수요의 증가로 통신망에서 음성, 영상 및 데이터(data)를 복합적으로 지원할 수 있는 멀티서비스(multiservice)의 교환 기술이 필수적이다. 또한 망 사업자들이 여러 벤더(vendor)들로부터 최적의 장비를 선택하여 망을 구축할 수 있도록 통신 장비들의 상호 운용성을 지원하는 개방형 구조의 망 및 스위치 시스템(switch system)을 정의하는 작업이 필요하다. 페트리 넷(Petri Nets)은 시스템(system)을 분석하기 위한 도구로서, 시스템은 페트리 넷 이론에 의해 시스템의 수학적 표현인 페트리 넷으로 설계될 수 있다. CPN(Colored Petri Nets)은 페트리넷의 확장형으로서, 토근(token)에 칼라를 부여하여 다양한 특성을 지닌 시스템을 표현하기에 적합하다. Design/CPN은 CPN의 사용을 지원하는 소프트웨어 패키지(software package)이다. 본 논문에서는 개방형 멀티서비스 교환 시스템의 핵심으로 스위치와 제어기(Controller) 사이의 표준 프로토콜인 GSMP(General Switch Management Protocol) 프로토콜을 Design/CPN 으로 변환하고, 이로부터 시험열을 생성한다.

  • PDF

A Study on the Design and Implementation of an AI Mock Interview System for Computer Science Interview Preparation Using LLM-based ChatGPT (LLM 기반 ChatGPT를 활용한 컴퓨터 분야 면접 준비용 AI 모의 면접 시스템의 설계 및 구현에 대한 연구)

  • Jae-Sung Chun;Hee-Kwon Jang;Ji-Hye Kim;Chang-Min Bae;Dong-Gyu Lee;Il-Young Moon
    • Journal of Practical Engineering Education
    • /
    • v.16 no.5_spc
    • /
    • pp.643-651
    • /
    • 2024
  • This study aims to design and implement an AI mock interview system for Computer Science (CS) interview preparation using LLM (Large Language Model) based ChatGPT. The system utilizes AI's natural language processing and speech recognition capabilities to analyze and provide real-time feedback on interview responses, helping users improve their weaknesses during the preparation process. According to a survey, 90% of users reported that the real-time feedback function provided substantial assistance in their interview preparation. Key features include GPT prompt generation and Speech-to-Text functionality, which converts voice data into text. The system received positive evaluations for its response time and feedback accuracy. Future research will explore expanding the range of question types and applying the system to various industries.

Design and Analysis of a New Video Conference System Supporting the NAT of Firewall (방화벽 NAT를 지원하는 새로운 다자간 화상회의 시스템의 설계 및 분석)

  • Jung, Yong-Deug;Kim, Gil-Choon;Jeon, Moon-Seog
    • The Journal of Society for e-Business Studies
    • /
    • v.9 no.4
    • /
    • pp.137-155
    • /
    • 2004
  • A video-conference system is being utilized in web based application services in various fields due to the widespread use of Internet and the progress of computer technologies. This system should use the public IP address for sharing file and white board and it is difficult to manage the internal network users of the firewall and non-public IP address users. In this paper, we propose an Application Level Gateway which transforms non-public IP address into public IP address. This mechanism is for the internal network users of the firewall or non-public IP address users over the Internet. We also propose a Control Daemon which manages video and audio media dynamically according to network bandwidth. This mechanism can start and terminate a video conference and manage the process of the video conference.

  • PDF