-
公开(公告)号：KR100651712B1
公开(公告)日：2006-11-30
申请号：KR1020030046861
申请日：2003-07-10
IPC: G10L19/12
CPC classification number: G10L19/125
Abstract: 광대역 음성 부호화기 및 그 방법과 광대역 음성 복호화기 및 그 방법이 개시된다. 본 발명에 따른 광대역 음성 부호화기는 부호화할 광대역 음성신호의 개회로 피치값과 선형예측계수를 이용하여 현재 프레임에 해당하는 음성의 특성을 규정하는 음성 특성 분류부, 적응 코드북을 검색하여 적응 코드북 피치 지연값 및 적응 코드북 피치 이득값을 얻고, 1차 고정 코드북 목적신호를 생성하는 적응 코드북 검색부, 1차 고정 코드북을 검색하여 1차 고정 코드북 인덱스와 1차 고정 코드북 이득값을 얻고, 2차 고정 코드북 목적신호를 생성하는 1차 고정 코드북 검색부, 음성 특성에 따라 적어도 둘 이상의 2차 고정 코드북들을 구비하며, 음성 특성 정보에 따라 하나의 2차 고정 코드북을 선택 및 검색하여 2차 고정 코드북 인덱스들과 2차 고정 코드북 이득값들 검색하는 2차 고정코드북 검색부 및 각 부에서 얻어지는 파라미터들을 양자화 및 다중화하여 비트열로 만들어 외부의 음성 복호화단으로 전송하는 파라미터 다중화부를 포함하는 것을 특징으로 하며, 음성 특성에 따라 2개 이상으로 구성된 2차 고정 코드북들로부터 음성 특성에 적합한 2차 고정 코드북을 선택함으로써 광대역 음성신호에 대해 보다 우수한 음질을 제공할 수 있다.
-
公开(公告)号：KR100465318B1
公开(公告)日：2005-01-13
申请号：KR1020020081663
申请日：2002-12-20
CPC classification number: H04L12/66
Abstract: A system for transmitting and receiving a wideband speech signal includes an A/D converter for receiving an analog speech signal to convert it into a digital speech signal, encoding a difference between a baseband speech signal and a standard baseband between a synthesized standard baseband signal, and an IP network interface for multiplexing the coded standard and additional baseband signals and enhancement residual band signal.
Abstract translation: 一种用于发送和接收宽带语音信号的系统包括：A / D转换器，用于接收模拟语音信号以将其转换为数字语音信号;在合成的标准基带信号与标准基带信号之间对基带语音信号与标准基带之间的差进行编码; 以及用于多路复用编码标准和附加基带信号以及增强残余频带信号的IP网络接口。
-
公开(公告)号：KR1020040050811A
公开(公告)日：2004-06-17
申请号：KR1020020077996
申请日：2002-12-09
IPC: G10L19/002 , G10L19/02 , G10L19/04
CPC classification number: G10L19/24 , G10L21/038
Abstract: PURPOSE: A transceiver for encoding and decoding voice using an additional bit assignment method is provided to offer a high-quality voice service by assigning only additional bits admitted in a system using a voice encoder used in an old voice processing system. CONSTITUTION: A standard voice encoding unit(102) classifies an inputted voice signal into spectrum information indicating a vocal tract transfer function and an excitation signal component, and models and quantizes spectrum information and the excitation signal component. The standard voice encoding unit(102) performs the standard encoding of the quantized signal, and generates a standard-encoded bit series. A quality improvement encoding unit(103) obtains an error between a signal in which spectrum information is not quantized and a signal in which spectrum information is quantized by the standard voice encoding unit(102). The quality improvement encoding unit(103) obtains an error between a signal in which the excitation signal component is not quantized and a signal in which the excitation signal component is quantized. The quality improvement encoding unit(103) additionally quantizes the obtained errors, and generates an encoded bit series. A multiplexing unit(104) multiplexes the bit series obtained in the standard voice encoding unit(102) and the quality improvement encoding unit(103), and transmits the multiplexed bit series.
Abstract translation: 目的：提供一种用于使用附加位分配方法对语音进行编码和解码的收发器，以通过仅使用在旧语音处理系统中使用的语音编码器仅分配系统中允许的附加比特来提供高质量语音服务。 构成：标准语音编码单元（102）将输入的语音信号分类为指示声道传递函数和激励信号分量的频谱信息，并对频谱信息和激励信号分量进行建模和量化。 标准语音编码单元（102）执行量化信号的标准编码，并生成标准编码比特序列。 质量改进编码单元（103）获得频谱信息未被量化的信号与频谱信息由标准语音编码单元（102）量化的信号之间的误差。 质量改进编码单元（103）获得其中激励信号分量未被量化的信号与激励信号分量被量化的信号之间的误差。 质量改进编码单元（103）另外量化所获得的误差，并生成编码比特序列。 复用单元（104）复用在标准语音编码单元（102）和质量改进编码单元（103）中获得的比特序列，并且发送多路复用的比特序列。
-
公开(公告)号：KR100467326B1
公开(公告)日：2005-01-24
申请号：KR1020020077996
申请日：2002-12-09
IPC: G10L19/002 , G10L19/02 , G10L19/04
CPC classification number: G10L19/24 , G10L21/038
Abstract: The present invention relates to a transmitter and a receiver for speech coding and decoding by using an additional bit allocation method. The transmitter and the receiver according to the present invention realize a voice communication service of high quality by using additional bits permitted in system requirements while using a conventional speech coder as it is. In addition, the transmitter and the receiver according to the present invention have an advantage in that they enable insertion of additional quantization blocks while not changing the structure of the conventional standard speech coder, since they allocate additional bits by applying a multi-stage quantization procedure not in a speech signal domain but in a parameter domain.
Abstract translation: 本发明涉及通过使用附加比特分配方法进行语音编码和解码的发射机和接收机。 根据本发明的发射机和接收机通过使用系统要求中允许的附加比特来实现高质量的语音通信服务，同时使用常规的语音编码器。 另外，根据本发明的发射机和接收机具有这样的优点，即它们能够插入额外的量化块，而不改变常规标准语音编码器的结构，因为它们通过应用多级量化过程来分配附加比特 不在语音信号域中，而是在参数域中。
-
公开(公告)号：KR1020050006883A
公开(公告)日：2005-01-17
申请号：KR1020030046861
申请日：2003-07-10
IPC: G10L19/12
CPC classification number: G10L19/125
Abstract: PURPOSE: A wideband voice encoder, a method therefor, a wideband decoder and a method therefor are provided to offer excellent voice quality in a voice interval which is not processed by an algebraical codebook by performing multi-stage fixed codebook retrieval. CONSTITUTION: A voice characteristic classifying unit(105) classifies the characteristic of a voice corresponding to a current frame using an open-loop pitch value of a recognition weight filtered signal of a wideband voice signal and a linear prediction factor by a statistical method. An adaptive codebook retrieving unit(106) retrieves a pitch delay value near the open-loop pitch value, calculates a pitch gain value, and generates an adaptive codebook contribution signal. The adaptive codebook retrieving unit outputs difference between the generated adaptive codebook contribution signal and the recognition weight filtered signal as a primary fixed codebook target signal. A primary fixed codebook retrieving unit(107) obtains a primary fixed codebook index and a primary fixed codebook gain value, generates a primary fixed codebook contribution signal corresponding to the obtained primary fixed codebook index. The primary fixed codebook retrieving unit outputs different between the generated primary fixed codebook contribution signal and the primary fixed codebook target signal as a secondary codebook target signal. A secondary fixed codebook retrieving unit(108) has at least two or more fixed codebooks according to voice characteristics, selects one secondary fixed codebook according to voice characteristic information, and retrieves secondary fixed codebook indexes and secondary fixed codebook gain values according to the voice characteristics. A parameter multiplexing unit(110) multiplexes voice characteristic information, the pitch delay value, the pitch gain value, the primary fixed codebook index, the primary fixed codebook gain value, the secondary fixed codebook indexes and the secondary fixed codebook gain values, generates a bit stream, and transmits the bit stream to an external voice decoding terminal.
Abstract translation: 目的：提供一种宽带语音编码器，其方法，宽带解码器及其方法，以通过执行多级固定码本检索在代码码本不处理的语音间隔中提供优良的语音质量。 构成：语音特征分类单元（105）使用统计方法使用宽带语音信号的识别权重滤波信号和线性预测因子的开环音调值来分类与当前帧相对应的语音的特性。 自适应码本检索单元（106）检索开环音调值附近的音调延迟值，计算音调增益值，并生成自适应码本贡献信号。 自适应码本检索单元输出生成的自适应码本贡献信号和识别权重滤波信号之间的差作为主要固定码本目标信号。 主固定码本检索单元（107）获得主固定码本索引和主固定码本增益值，生成与所获得的主固定码本索引相对应的主固定码本贡献信号。 主固定码本检索单元在所生成的主固定码本贡献信号和主固定码本目标信号之间输出不同的第二码本目标信号。 第二固定码本检索单元（108）根据语音特征具有至少两个或多个固定码本，根据语音特征信息选择一个辅助固定码本，并根据语音特征检索辅助固定码本索引和辅助固定码本增益值 。 参数复用单元（110）多路复用语音特征信息，音调延迟值，音调增益值，主固定码本索引，主固定码本增益值，辅助固定码本索引和辅助固定码本增益值，生成 并将比特流发送到外部语音解码终端。
-
Patent Agency Ranking
公开(公告)号：KR1020040055073A
公开(公告)日：2004-06-26
申请号：KR1020020081663
申请日：2002-12-20
CPC classification number: H04L12/66
Abstract: PURPOSE: An apparatus and a method for transmitting/receiving a wideband voice signal are provided to offer high sound quality 16 kHz sampled wideband voice signal and compatibility with an existing system. CONSTITUTION: A analyzing/filtering unit(301) receives a digital voice signal and outputs a low band voice signal having a bandwidth of 0-4 kHz of 8 kHz sampling period. A low band standard coding unit(302) receives the low band voice signal, codes it and outputs a coded low band standard signal. A low band additional coding unit(304) receives a difference between a filtered low band voice signal and a composite signal that has been decoded by a low band standard decoding unit(303) and codes them to generate a low band additional signal. An enhancement residual band coding unit(306) up-samples a composite signal obtained by combining signals outputted from the low band standard decoding unit(303) and the low band additional decoding unit(305), obtains a difference between the up-sampled signal and a voice signal inputted to the analyzing/filtering unit(301), and generates an enhancement residual band signal.
Abstract translation: 目的：提供用于发送/接收宽带语音信号的装置和方法，以提供高音质16kHz采样宽带语音信号和与现有系统的兼容性。 构成：分析/滤波单元（301）接收数字语音信号并输出具有8kHz采样周期的0-4kHz带宽的低频语音信号。 低频标准编码单元（302）接收低频语音信号，对其编码并输出编码的低频带标准信号。 低频带附加编码单元（304）接收滤波后的低频语音信号和由低频带标准解码单元（303）解码的复合信号之间的差，并对它们进行编码以产生低频带附加信号。 增强残差频带编码单元（306）对通过组合从低频带标准解码单元（303）和低频带附加解码单元（305）输出的信号获得的复合信号进行上采样，获得上采样信号 以及输入到分析/滤波单元（301）的语音信号，并产生增强剩余频带信号。
-
公开(公告)号：KR1020130094626A
公开(公告)日：2013-08-26
申请号：KR1020120016026
申请日：2012-02-16
Applicant: 한국전자통신연구원
IPC: H04N13/00
CPC classification number: G06T7/593 , G06T2207/10012 , H04N2013/0081
Abstract: PURPOSE: A stereo matching apparatus and method are provided to output a disparity map having divided objects and background by performing stereo matching through the preprocessing of an inputted image. CONSTITUTION: A stereo matching method is as follows. A stereo matching apparatus receives binocular images obtained from first and second cameras (S100). The stereo matching apparatus increases the contradiction between an object and a background in the obtained images using a preset first algorithm (S200). The stereo matching apparatus performs stereo matching using the processed images (S300). [Reference numerals] (AA) Start; (BB) End; (S100) Input a binocular image; (S200) Image processing through a first algorithm; (S300) Perform stereo matching
Abstract translation: 目的：提供一种立体匹配装置和方法，通过对输入图像的预处理进行立体匹配来输出具有分割对象和背景的视差图。 构成：立体匹配方法如下。 立体匹配装置接收从第一和第二相机获得的双眼图像（S100）。 立体匹配装置使用预设的第一算法增加所获得的图像中的对象与背景之间的矛盾（S200）。 立体匹配装置使用处理后的图像进行立体匹配（S300）。 （附图标记）（AA）开始; （BB）结束; （S100）输入双目图像; （S200）通过第一算法进行图像处理; （S300）执行立体匹配
-
公开(公告)号：KR101236475B1
公开(公告)日：2013-02-22
申请号：KR1020090032372
申请日：2009-04-14
Applicant: 한국전자통신연구원
CPC classification number: G06K9/00255 , G06T7/593 , G06T7/74 , G06T2207/10012 , G06T2207/30201
Abstract: 얼굴 검출 장치 및 이를 이용한 거리 측정 방법에서는, 스테레오 카메라로부터 획득된 좌우 영상을 이용하여 얼굴이 검출된다. 동시에 스테레오 정합 과정 없이 오직 스테레오 카메라로부터 제공된 영상 프레임을 이용하여 스테레오 카메라로부터 얼굴까지의 거리가 측정된다. 따라서, 저성능의 시스템에서도, 얼굴 검출 기능과 거리 측정 기능이 동시 수행될 수 있는 저성능 시스템의 설계가 가능하다.
Abstract translation: 提供了一种脸部检测装置和使用其的距离测量方法。 面部检测装置使用从立体摄像机获取的左右图像来检测脸部。 面部检测装置使用从立体摄像机提供的没有立体匹配处理的图像帧来测量从立体摄像机到脸部的距离。 因此，脸部检测装置即使在低性能系统中也同时执行面部检测和距离测量。
-
公开(公告)号：KR101192365B1
公开(公告)日：2012-10-17
申请号：KR1020080129632
申请日：2008-12-18
Applicant: 한국전자통신연구원
CPC classification number: G06K9/00228 , G06K9/00973
Abstract: 얼굴 검출 시스템 및 그 방법에서, 전처리 영상에 대응하는 전처리 계수 값들이 병렬적으로 산출되는 윈도우 추출부와, 병렬적으로 산출된 상기 전처리 계수 값들에 근거하여 코스트값을 병렬적으로 산출하는 코스트값 계산부가 구비된다. 이러한 병렬 연산 기법에 의해 전체 시스템의 연산처리속도가 향상되고, 그 결과, 고속의 실시간으로 얼굴 패턴의 검출이 가능하다.
-
公开(公告)号：KR101059892B1
公开(公告)日：2011-08-29
申请号：KR1020080114116
申请日：2008-11-17
Applicant: 한국전자통신연구원
Abstract: 본 발명은 개개의 화자식별 결과의 신뢰도 측정 방법에 관한 것으로, 각 프레임의 화자식별 결과에 대한 공헌 정도를 측정하고, 이 각 프레임의 화자식별 공헌도를 기반으로 화자식별 결과의 신뢰도를 측정하고, 이를 화자 진위 판단에 이용함으로써, 화자 검증시에 제시된 화자의 진위를 정확하게 판단하여, 원거리 다채널 환경에서 화자식별의 정확도를 높일 수 있다.
화자식별, 화자식별 결과의 신뢰도, 원거리 다채널 환경, 화자식별 결과 통합.Abstract translation: 本发明测量测量的程度基于每个帧结果的扬声器识别的贡献以促进与所述个体说话者识别结果的可靠性测量方法的每个帧的说话者识别结果，识别所述说话者的可靠性，它 可以准确地确定在验证讲话者时呈现的讲话者的真实性，从而提高远程多信道环境中讲话者识别的准确性。
-
-
-
-
-
-
-
-
-
Search Results
170
records
(took 0.028 seconds)
