专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

KR1020010086492A 음성 인식기의 단어 모델 생성 방법 失效
标题翻译：用于生成声音识别器的字模型的方法
公开(公告)号：KR1020010086492A
公开(公告)日：2001-09-13
申请号：KR1020000010413
申请日：2000-03-02
申请人： 주식회사 현대오토넷
发明人： 김선화
IPC分类号： G10L15/14
摘要： PURPOSE: A method for generating a word model of a sound recognizer is provided to embody a special sound recognition function. CONSTITUTION: A sound recognizer inputs a word model as Korean Character complete code in order to perform a predetermined sound recognition function(S10). The word model of the Korean Character complete code is converted into a combination code(S20). The word model of the combination code is converted into a word model which is really pronounced(S30). The word model which is really pronounced is converted into a predetermined 3 byte code(S40). A special similarity phoneme row corresponding to the word mode of the predetermined 3 byte code is generated and stored(S50).
摘要翻译：目的：提供一种用于生成声音识别器的单词模型的方法，以体现特殊的声音识别功能。构成：为了执行预定的声音识别功能，声音识别器将字模型输入为韩文字符完整码（S10）。韩文字符完整码的字模型被转换为组合码（S20）。组合代码的单词模型被转换成真正发音的单词模型（S30）。真正发音的单词模型被转换成预定的3字节代码（S40）。生成并存储对应于预定3字节代码的字模式的特殊相似性音素行（S50）。

2. 发明公开

KR1020070059265A 차량용 에이·브이·엔 시스템의 내비게이션 화면자동전환장치 및 방법 无效
标题翻译：导航屏幕自动转换系统和AVN系统方法
公开(公告)号：KR1020070059265A
公开(公告)日：2007-06-12
申请号：KR1020050117920
申请日：2005-12-06
申请人： 주식회사 현대오토넷
发明人： 김선화
IPC分类号： G08G1/0962
摘要： An apparatus and a method for converting a screen of an AVN(Audio Video Navigation) system are provided to prevent inconvenience due to a manual key-in operation by automatically converting a video screen into a guidance screen. An apparatus for converting a screen of an AVN system includes a detecting unit(1), a micom(2), an image signal switching unit(3), and a display unit(4). The detecting unit detects whether a driving guidance signal is input from a navigation device of the AVN system. The micom analyzes an inputted detection signal from the detecting unit and outputs a screen selection control signal. The image signal switching unit selectively switches an image signal from a predetermined image signal generating unit according to the screen selection control signal from the micom. The display unit receives the image signal from the image signal switching unit and displays images according to the image signal.
摘要翻译：提供了一种用于转换AVN（音频视频导航）系统的屏幕的装置和方法，以通过将视频屏幕自动转换为引导屏幕来防止由手动键入操作引起的不便。一种用于转换AVN系统的屏幕的设备包括检测单元（1），微机（2），图像信号切换单元（3）和显示单元（4）。检测单元检测是否从AVN系统的导航装置输入驾驶引导信号。微型机分析来自检测单元的输入的检测信号，并输出屏幕选择控制信号。图像信号切换单元根据来自微机的画面选择控制信号有选择地切换来自预定图像信号生成单元的图像信号。显示单元从图像信号切换单元接收图像信号，并根据图像信号显示图像。

3. 发明授权

KR100305446B1 음성 데이터 베이스 구축 방법 失效
标题翻译：语音数据库建立方法
公开(公告)号：KR100305446B1
公开(公告)日：2001-11-07
申请号：KR1019990039234
申请日：1999-09-14
申请人： 주식회사 현대오토넷
发明人： 김선화
IPC分类号： G10L15/12
摘要： 본발명은음성데이터베이스구축방법에관한것이다. 본발명은특정한화자가발성하는단어나문장을수집하는음성수집단계(S10)와, 수집된특정한화자의음성으로부터예상되는소정의유사음소를추출하는단계(S20), 및추출된유사음소마다각각특정한확장자명과 4개의숫자로구성되는파일명을지정하여음성데이터베이스에저장하는레이블링단계(S30)로이루어지며, 이에따라서, 화자의음성을인식하기위하여유사음소(Phoneme Like Unit) 단위로음성데이터베이스를구축하도록되어있다.

4. 发明公开

KR1020010054192A 음성인식 시스템내의 단어 처리 장치 无效
标题翻译：语音识别系统中的字处理装置
公开(公告)号：KR1020010054192A
公开(公告)日：2001-07-02
申请号：KR1019990054870
申请日：1999-12-03
申请人： 주식회사 현대오토넷
发明人： 박성희 , 김선화
IPC分类号： G10L15/16
摘要： PURPOSE: A word processing apparatus in a voice recognition system is provided to raise the probability of rejecting a nonregistered word and receiving a registered word by reducing uncertainty of a regulation platform. CONSTITUTION: A word processing apparatus is constituted by a detector(100), a voice storage(200), a voice result output unit(300), a data memory(400), a fuzzy interference organization(500). The detector(100) extracts a necessary feature coefficient from a voice data from a user. The voice storage(200) stores feature coefficients extracted from the detector(100). The voice result output unit(300) compares the reference pattern stored in the voice storage(200) with a voice pattern inputted from the detector(100) to output a recognition result. The data memory(400) regulates experiences and knowledge of experts about voice recognition, and stores regulated data. The fuzzy interference organization(500) compares the recognition data from the voice result output unit(300) with the regulated data in the data memory(400) to judge receipt or rejection of the recognition result.
摘要翻译：目的：提供语音识别系统中的文字处理装置，以通过减少调节平台的不确定性来提高拒绝非注册字和接收注册字的可能性。构成：字处理装置由检测器（100），语音存储器（200），语音结果输出单元（300），数据存储器（400），模糊干扰组织（500）构成。检测器（100）从用户的语音数据中提取必要的特征系数。语音存储器（200）存储从检测器（100）提取的特征系数。语音结果输出单元（300）将存储在语音存储器（200）中的参考模式与从检测器（100）输入的语音模式进行比较，以输出识别结果。数据存储器（400）调节专家关于语音识别的经验和知识，并且存储经调节的数据。模糊干扰组织（500）将来自语音结果输出单元（300）的识别数据与数据存储器（400）中的调节数据进行比较，以判断识别结果的接收或拒绝。

5. 发明授权

KR100611894B1 음성 인식기의 단어 모델 생성 방법 失效
标题翻译：语音识别系统的WORD模型生成方法
公开(公告)号：KR100611894B1
公开(公告)日：2006-08-11
申请号：KR1020000010413
申请日：2000-03-02
申请人： 주식회사 현대오토넷
发明人： 김선화
IPC分类号： G10L15/14
摘要： 본 발명은 음성 인식기의 단어 모델 생성 방법에 관한 것이다.
본 발명은 음성 인식기가 소정의 음성 인식 기능을 수행할 수 있도록 하기 위한 단어 모델을 한글 완성형 코드로 입력하는 단계(S10)와, 한글 완성형 코드로 입력되는 단어 모델을 조합형 코드로 변환하는 단계(S20)와, 조합형 코드로 변환되는 단어 모델을 실제로 발음되는 단어 모델로 변환한 후(S30) 3 바이트 코드로 변환하는 단계(S40), 및 3 바이트 코드로 변환되는 입력 단어 모델에 대응하는 특정한 유사 음소열을 생성하여 저장하는 단계(S50)로 이루어지며,
이것에 의해서, 음성 인식기가 소정의 음성 인식 기능을 수행할 수 있도록 하기 위한 단어 모델을 용이하게 생성하여 음성 인식기에 적용할 수 있다.
음성 인식기, 단어 모델, 유사 음소, PLU, 단어 모델 생성 방법

6. 发明公开

KR1020010027464A 음성 데이터 베이스 구축 방법 失效
标题翻译：构建语音数据库的方法
公开(公告)号：KR1020010027464A
公开(公告)日：2001-04-06
申请号：KR1019990039234
申请日：1999-09-14
申请人： 주식회사 현대오토넷
发明人： 김선화
IPC分类号： G10L15/12
摘要： PURPOSE: A method for constructing a voice database is provided to recognize a voice by constructing a voice database in phoneme like units. CONSTITUTION: The method for constructing a voice database comprises the following steps of a collection process(S10), an extraction process(S20), and a labelling process(S30). The collection process(S10) is to collect a word or a sentence from a particular speaker. The extraction process(S20) is to extract phoneme like units predicted from the collected voice of the specific speaker. The labelling process(S30) is to designate specific extension names and file names of each extracted phoneme like unit and store them to a voice database.
摘要翻译：目的：提供一种构建语音数据库的方法，通过以音素单位构建语音数据库来识别语音。构成：构成语音数据库的方法包括收集处理（S10），提取处理（S20）和标签处理（S30）的以下步骤。收集过程（S10）是从特定说话者收集一个单词或一个句子。提取处理（S20）是从特定说话者的收集的声音中提取与单元预测相似的音素。标签处理（S30）是指定每个提取的音素单元的特定扩展名和文件名，并将其存储到语音数据库。

7. 发明公开

KR1020000040574A GPFN 알고리즘과 LVQ 알고지즘을 이용한 음성인식 방법 无效
标题翻译：使用高斯潜在功能网络算法和学习矢量量化算法进行语音识别的方法
公开(公告)号：KR1020000040574A
公开(公告)日：2000-07-05
申请号：KR1019980056236
申请日：1998-12-18
申请人： 주식회사 현대오토넷
发明人： 안종영 , 김선화
IPC分类号： G10L15/02
摘要： PURPOSE: A method for voice recognition using gaussian potential function network algorithm and learning vector quantization algorithm is provided to generate optimal code book for voice recognition. CONSTITUTION: A method for voice recognition using gaussian potential function network algorithm and learning vector quantization algorithm includes a firth through a sixth steps. At the first step(S10), a digital data of characteristic part of digital data is extracted by using SPC(linear prediction coefficient) algorithm. At the second step(S20), an output vector x(t) is generated by using GPFN(Gaussian Potential Function Network) algorithm. At the third step(S30), the output vector x(t) is input to LVQ(learning vector quantization) algorithm and a LVQ algorithm study is performed. At the forth step(S40), an optimal code book is generated. At the fifth step(S50), user's voice of a characteristic feature is recognized. At the sixth step(S60), the voice expressed by the user is recognized.
摘要翻译：目的：提出一种使用高斯势函数网络算法和学习矢量量化算法进行语音识别的方法，以生成语音识别的最优码书。构成：使用高斯势函数网络算法和学习矢量量化算法进行语音识别的方法包括第六步。在第一步（S10）中，通过使用SPC（线性预测系数）算法来提取数字数据的特征部分的数字数据。在第二步（S20）中，通过使用GPFN（高斯势函数网络）算法生成输出向量x（t）。在第三步（S30）中，将输出矢量x（t）输入到LVQ（学习矢量量化）算法，并进行LVQ算法研究。在第四步骤（S40）中，生成最佳代码簿。在第五步骤（S50）中，识别特征特征的用户声音。在第六步骤（S60）中，识别由用户表达的语音。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式