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
    • 1. 发明授权
    • Voice communication device, voice communication method, and voice communication program
    • 语音通信设备,语音通信方式和语音通信程序
    • US08462190B2
    • 2013-06-11
    • US12169656
    • 2008-07-09
    • Masahito TogamiAkio Amano
    • Masahito TogamiAkio Amano
    • H04N7/14H04R5/02
    • H04N7/15G10L21/00G10L2021/02166
    • Provided is a voice communication device for carrying out voice communication among a plurality of locations, including: a sound source direction identification block for identifying a direction of a sound source; a voice sender block for sending the collected voice to a different location; a voice receiver block for receiving a voice from a different location; a player block for playing the received voice; a playing information setting block for setting playing information for the voice being played; a speaker volume storage block for acquiring the direction of the sound source for which the playing information is set from the sound source direction identification block and storing the direction of the sound source in association with the playing information; and a voice manipulating block for acquiring the playing information corresponding to the direction of the sound source of the voice and manipulating the voice based on the playing information.
    • 提供一种用于在多个位置之间执行语音通信的语音通信设备,包括:用于识别声源的方向的声源方向识别块; 语音发送器块,用于将收集的语音发送到不同的位置; 用于从不同位置接收语音的语音接收器块; 用于播放所接收的语音的播放器块; 播放信息设置块,用于设置正在播放的声音的播放信息; 扬声器音量存储块,用于从声源方向识别块获取设置了播放信息的声源的方向,并且与播放信息相关联地存储声源的方向; 以及语音操纵块,用于获取与声音的声源的方向相对应的播放信息,并且基于播放信息来操纵语音。
    • 2. 发明申请
    • Sound source separating device, method, and program
    • 声源分离装置,方法和程序
    • US20070223731A1
    • 2007-09-27
    • US11700157
    • 2007-01-31
    • Masahito TogamiAkio AmanoTakashi Sumiyoshi
    • Masahito TogamiAkio AmanoTakashi Sumiyoshi
    • H04R3/00H04R1/02
    • H04R3/005
    • Conventional independent component analysis has had a problem that performance deteriorates when the number of sound sources exceeds the number of microphones. Conventional l1 norm minimization method assumes that noises other than sound sources do not exist, and is problematic in that performance deteriorates in environments in which noises other than voices such as echoes and reverberations exist. The present invention considers the power of a noise component as a cost function in addition to an l1 norm used as a cost function when the l1 norm minimization method separates sounds. In the l1 norm minimization method, a cost function is defined on the assumption that voice has no relation to a time direction. However, in the present invention, a cost function is defined on the assumption that voice has a relation to a time direction, and because of its construction, a solution having a relation to a time direction is easily selected.
    • 传统的独立分量分析存在的问题是,当声源的数量超过麦克风的数量时,性能会恶化。 常规的l1范数最小化方法假设不存在除声源之外的噪声,并且在存在诸如回声和混响的声音之外的环境的环境中性能恶化是有问题的。 除了作为成本函数的l1范数之外,本发明考虑噪声分量的功率作为成本函数,当l1范数最小化方法分离声音时。 在l1范数最小化方法中,假定语音与时间方向无关,则定义成本函数。 然而,在本发明中,在语音与时间方向有关系的假设下定义成本函数,并且由于其构造,容易选择与时间方向有关的解决方案。
    • 10. 发明授权
    • Speech recognition apparatus using neural network and fuzzy logic
    • 使用神经网络和模糊逻辑的语音识别装置
    • US5179624A
    • 1993-01-12
    • US727089
    • 1991-07-09
    • Akio AmanoAkira IchikawaNobuo Hataoka
    • Akio AmanoAkira IchikawaNobuo Hataoka
    • G10L15/16
    • G10L15/16Y10S706/90
    • A speech recognition apparatus has: a speech input unit for inputting a speech; a speech analysis unit for analyzing the inputted speech to output the time series of a feature vector; a candidates selection unit for inputting the time series of a feature vector from the speech analysis unit to select a plurality of candidates of recognition result from the speech categories; and a discrimination processing unit for discriminating the selected candidates to obtain a final recognition result. The discrimination processing unit includes three components in the form of a pair generation unit for generating all of the two combinations of the n-number of candidates selected by said candidate selection unit a pair discrimination unit for discriminating which of the candidates of the combinations is more certain for each of all .sub.n C.sub.2 -number of combinations (or pairs) on the basis of the extracted result of the acoustic feature intrinsic to each of said candidate speeches and a final decision unit for collecting all the pair discrimination results obtained from the pair discrimination unit for each of all the .sub.n C.sub.2 -number of combinations (or pairs) to decide the final result. The pair discrimination unit handles the extracted result of the acoustic feature intrinsic to each of the candidate speeches as fuzzy information and accomplishes the discrimination processing on the basis of fuzzy logic algorithms, and the final decision unit accomplishes its collections on the basis of the fuzzy logic algorithms.
    • 语音识别装置具有:用于输入语音的语音输入单元; 语音分析单元,用于分析输入的语音以输出特征向量的时间序列; 候选选择单元,用于从语音分析单元输入特征向量的时间序列,以从语音类别中选择多个候选的识别结果; 以及鉴别处理单元,用于识别所选择的候选以获得最终识别结果。 鉴别处理单元包括成对生成单元形式的三个组成部分,用于产生由所述候选选择单元选择的n个候选项的所有两个组合中的一个对鉴别单元,用于鉴别组合中的哪个候选者更多 基于每个所述候选讲话所固有的声学特征的提取结果,以及用于收集从对鉴别单元获得的所有对鉴别结果的最终决定单元,对于所有nC2个组合(或对)中的每一个确定; 对于所有nC2个组合(或对)中的每一个来决定最终结果。 对鉴别单元处理作为模糊信息的每个候选语音固有的声学特征的提取结果,并且基于模糊逻辑算法完成鉴别处理,并且最终决策单元基于模糊逻辑来完成其集合 算法。