会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 23. 发明公开
    • 음가의 강세를 이용한 발음기관 애니메이션 생성 장치 및 방법
    • 使用电话价值来生成VOCAL ORGANS动画的装置和方法
    • KR1020120109879A
    • 2012-10-09
    • KR1020110027666
    • 2011-03-28
    • (주)클루소프트
    • 박봉래
    • G06T13/00G06T13/40G10L11/00G10L15/02
    • G10L15/005G06T13/205G06T13/40G10L13/08G10L15/04G10L21/10G10L25/90
    • PURPOSE: An apparatus and a method for generating vocal organs are provided to generate vocal organs by reflecting a phonetic type of a native speaker changed according to the strength of phonetic values. CONSTITUTION: A phonetic value information generator(120) generates phonetic value configuration information. A per-accent phonetic value applying unit(130) applies detailed phonetic value per accent. A pronunciation type detector(140) detects pronunciation configuration information corresponding to the detail phonetic value. An animation generator(160) allots the detected pronunciation configuration information to each phonetic value. The animation generator generates a vocal organ animation corresponding to words included in character information. [Reference numerals] (110) Input unit; (120) Phonetic value information generator; (125) Phonetic value information storing unit; (130) Per-accent phonetic value applying unit; (135) Per-accent phonetic value storing unit; (140) Pronunciation type detector; (145) Pronunciation type information storing unit; (150) Animation controlling unit; (160) Animation generator; (170) Output unit
    • 目的:提供一种用于产生声乐器官的装置和方法,以通过反映根据语音值的强度而改变的母语者的语音类型来产生声乐器官。 构成:语音值信息生成器(120)产生语音值配置信息。 每重音音标值应用单元(130)每个重音应用详细的语音值。 发音型检测器(140)检测与细节语音对应的发音配置信息。 动画生成器(160)将检测到的发音配置信息分配给每个语音值。 动画生成器生成与包含在字符信息中的单词对应的声乐器动画。 (附图标记)(110)输入单元; (120)语音信息发生器; (125)语音值信息存储单元; (130)每口音语音应用单位; (135)每重音音标值存储单元; (140)发音型探测器; (145)发音类型信息存储单元; (150)动画控制单元; (160)动画发生器; (170)输出单元
    • 27. 发明公开
    • Transfer base voiced measuring mean and system
    • 转移基础声音测量平均和系统
    • KR20100044424A
    • 2010-04-30
    • KR20080103555
    • 2008-10-22
    • SAMSUNG ELECTRONICS CO LTD
    • KIM HYUN SOO
    • G10L15/20
    • G10L25/93G10L15/20G10L25/90
    • PURPOSE: A method and a system for measuring a voiced sound based on movement are provided to suggest an accurate and practical feature extracting method. CONSTITUTION: A system for measuring a voiced sound based on movement includes a harmonic measuring unit, a noise measuring unit, and a voiced sound measuring unit. The harmonic measuring unit measures the envelop of a harmonic peak of a voice signal(S2). The noise measuring unit measures the envelop of the noise peak of the voice signal(S3). The voiced sound measuring unit measures an environment noise degree through the envelope ratio of a noise peak to a harmonic peak and then moves the harmonic according to the environment noise degree to measure the degree of the voiced sound(S4).
    • 目的:提供一种基于运动测量浊音的方法和系统,以提出准确实用的特征提取方法。 构成:用于测量基于运动的浊音的系统包括谐波测量单元,噪声测量单元和浊音测量单元。 谐波测量单元测量语音信号的谐波峰值的包络(S2)。 噪声测量单元测量语音信号噪声峰值的包络(S3)。 声音测量单元通过噪声峰值与谐波峰值的包络比来测量环境噪声程度,然后根据环境噪声程度移动谐波以测量浊音的程度(S4)。
    • 28. 发明公开
    • 오디오 컨텐츠 검색 방법 및 장치
    • 搜索音频内容的方法和设备
    • KR1020100042705A
    • 2010-04-27
    • KR1020080101816
    • 2008-10-17
    • 주식회사 케이티
    • 허성필
    • G06F17/30
    • G06F17/30758G06F17/15G10L25/27G10L25/90
    • PURPOSE: A method and an apparatus for searching audio contents are provided to search desirable audio contents accurately from a massive content database. CONSTITUTION: A feature vector extractor(123) extracts from humming: musical notes constituting the humming; and characteristic amount of previous/next pitch and sound fields. A linearity matcher(124) generates a first search result based on the similarity of the characteristic amount of the audio contents. A dynamic programming matcher(125) creates a second result from the first result by using the dynamic programming matching, and a search result synthesis unit(126) synthesizes the first and second results to generate the audio result information.
    • 目的:提供一种用于搜索音频内容的方法和装置,以从海量的内容数据库中准确地搜索所需的音频内容。 构成:特征向量提取器(123)从嗡嗡声中提取:构成嗡嗡声的音符; 和前一个/下一个音高和声场的特征量。 线性匹配器(124)基于音频内容的特征量的相似度产生第一搜索结果。 动态编程匹配器(125)通过使用动态编程匹配从第一结果创建第二结果,并且搜索结果合成单元(126)合成第一和第二结果以产生音频结果信息。
    • 29. 发明公开
    • 피치 지연 추정
    • PITCH LAG估计
    • KR1020090077951A
    • 2009-07-16
    • KR1020097009703
    • 2007-10-01
    • 노키아 코포레이션
    • 라크소넨라쎄라모안씨바실라체아드리아나
    • G10L25/90G10L25/93
    • G10L25/90G10L19/09G10L25/06
    • Autocorrelation values are determined as a basis for an estimation of a pitch lag in a segment of an audio signal. A first considered delay range for the autocorrelation computations is divided into a first set of sections, and first autocorrelation values are determined for delays in a plurality of sections of this first set of sections. A second considered delay range for the autocorrelation computations is divided into a second set of sections such that sections of the first set and sections of the second set are overlapping. Second autocorrelation values are determined for delays in a plurality of sections of this second set of sections.
    • 自相关值被确定为用于估计音频信号的段中的音调滞后的基础。 用于自相关计算的第一被考虑的延迟范围被划分为第一组部分,并且为该第一组部分的多个部分中的延迟确定第一自相关值。 用于自相关计算的第二被考虑的延迟范围被划分成第二组部分,使得第一组的部分和第二组的部分重叠。 第二自相关值是针对该第二组部分的多个部分中的延迟而确定的。