AUDIO PROCESSING FOR AN ACOUSTICAL ENVIRONMENT
    71.
    发明申请
    AUDIO PROCESSING FOR AN ACOUSTICAL ENVIRONMENT 审中-公开
    音频处理的声学环境

    公开(公告)号:WO2017164996A1

    公开(公告)日:2017-09-28

    申请号:PCT/US2017/016376

    申请日:2017-02-03

    Abstract: An apparatus for detecting a sound in an acoustical environment includes a microphone array configured to detect an audio signal in the acoustical environment. The apparatus also includes a processor configured to determine an angular location of a sound source of the audio signal. The angular location is relative to the microphone array. The processor is also configured to determine at least one reverberation characteristic of the audio signal. The processor is further configured to determine a distance, relative to the microphone array, of the sound source along an axis associated with the angular location based on the at least one reverberation characteristic.

    Abstract translation: 用于检测声学环境中的声音的设备包括被配置为检测声学环境中的音频信号的麦克风阵列。 该装置还包括配置成确定音频信号的声源的角度位置的处理器。 角度位置相对于麦克风阵列。 处理器还被配置为确定音频信号的至少一个混响特性。 处理器还被配置为基于至少一个混响特性来确定沿着与角位置相关联的轴的声源相对于麦克风阵列的距离。

    시간 영역에서의 차신호 에너지법에 의한 음주 판별 방법, 이를 수행하기 위한 기록 매체 및 장치
    73.
    发明申请
    시간 영역에서의 차신호 에너지법에 의한 음주 판별 방법, 이를 수행하기 위한 기록 매체 및 장치 审中-公开
    用于确定在时域中的差分信号能量使用的酒精的方法,以及记录介质和用于实现其的装置

    公开(公告)号:WO2015147364A1

    公开(公告)日:2015-10-01

    申请号:PCT/KR2014/002851

    申请日:2014-04-02

    Abstract: 음주 판별 방법은, 입력된 음성 신호의 복수의 유효 프레임을 검출하는 단계; 유효 프레임의 원신호의 차신호를 검출하는 단계; 각 유효 프레임마다 원신호의 평균 에너지 및 차신호의 평균 에너지를 검출하는 단계; 및 각 유효 프레임마다 원신호의 평균 에너지와 차신호의 평균 에너지 차이에 기초하여 음주 상태를 판단하는 단계를 포함한다. 이에 따라, 음성 신호를 이용한 차신호 에너지법에 의하여 원거리에 있는 운전자 또는 운항자의 음주 여부 및 정도를 파악할 수 있으므로, 음주 운전 또는 운항으로 인한 사고를 예방할 수 있다.

    Abstract translation: 用于确定酒精使用的方法包括以下步骤:检测输入音频信号中的多个有效帧; 检测有效帧的原始信号中的差分信号; 检测各个有效帧的原始信号的平均能量和差分信号的平均能量; 并且基于原始信号的平均能量与各个有效帧的差分信号的平均能量之间的差来确定酒精使用的状态。 因此,本发明可以通过使用音频信号的差分信号的能量来识别驾驶员或操作者在长距离处的酒精使用的状态和程度,并且因此可以防止在影响下由驾驶或操作引起的事故 醇。

    単語アライメントスコア算出装置、単語アライメント装置、及びコンピュータプログラム
    74.
    发明申请
    単語アライメントスコア算出装置、単語アライメント装置、及びコンピュータプログラム 审中-公开
    字对准计算设备,字对齐设备和计算机程序

    公开(公告)号:WO2015133238A1

    公开(公告)日:2015-09-11

    申请号:PCT/JP2015/053825

    申请日:2015-02-12

    CPC classification number: G06F17/2827 G06F17/2818 G10L25/30

    Abstract: 【課題】高精度で単語アライメントをするための装置を提供する。 【解決手段】この装置は、対訳文対と、当該対訳文対に対する単語アライメントとを受けて、所定の順序で第1の言語の文の単語f j を順番に選択する選択手段と、対訳文対の第2の言語のうちで単語アライメントa j により単語f j と対応付けられた単語e a_{j} と単語f j とからなる単語対が正しい可能性を示すスコア102を第1の言語の文の全単語について算出し、当該スコアに基づいて単語アライメントa j のスコアを算出するリカレント型ニューラル・ネットワーク(RNN)100とを含む。RNN100は、単語対(f j、 e a_{j} )のスコアを算出するときに、循環接続118により、単語アライメントa j のうち単語対(f j、 e a_{j} )の単語f j より前に選択手段により選択された単語のアライメント全てa 1 j-1 に基づき単語対(f j、 e a_{j} )のスコア102を算出する。

    Abstract translation: [问题]提供用于以高精度执行字对齐的装置。 [解决方案]该装置包括:用于接收双语句子对的双语语句对和单词对齐的选择装置,并按规定的顺序依次选择第一语言的单词(fj); 以及用于计算第一语言的句子中的每个单词的循环神经网络(RNN)(100),表示由各个单词(fj)组成的单词对的正确性的可能性的得分(102)和单词 (ea_ {j}),其处于双语句子对的第二语言中,并且通过字对齐(aj)与单词(fj)对齐,并且基于该对齐方式(aj)计算单词对齐(aj)的分数 得分了。 当计算字对(fj,ea_ {j})的得分时,RNN(100)通过循环连接(118)计算字对(fj,ea_ {j})的得分(102) 基于在字对(fj,ea_ {j})的单词(fj)之前由选择装置选择的单词的字对齐(aj)的全部(a1 j-1)的基础上。

    VOLUME LEVELER CONTROLLER AND CONTROLLING METHOD
    75.
    发明申请
    VOLUME LEVELER CONTROLLER AND CONTROLLING METHOD 审中-公开
    体积调节器和控制方法

    公开(公告)号:WO2014160542A3

    公开(公告)日:2014-11-20

    申请号:PCT/US2014030385

    申请日:2014-03-17

    Abstract: Volume leveler controller and controlling method are disclosed. In one embodiment, A volume leveler controller includes an audio content classifier for identifying the content type of an audio signal in real time; and an adjusting unit for adjusting a volume leveler in a continuous manner based on the content type as identified. The adjusting unit may configured to positively correlate the dynamic gain of the volume leveler with informative content types of the audio signal, and negatively correlate the dynamic gain of the volume leveler with interfering content types of the audio signal.

    Abstract translation: 本发明公开了一种体积调节器控制器和控制方法。 在一个实施例中,音量调节器控制器包括用于实时识别音频信号的内容类型的音频内容分类器; 以及用于基于所识别的内容类型以连续方式调整音量调整器的调整单元。 调整单元可以被配置为将音量调整器的动态增益与音频信号的信息内容类型正相关,并且将音量调整器的动态增益与音频信号的干扰内容类型负相关。

    MONAURAL SPEECH FILTER
    76.
    发明申请
    MONAURAL SPEECH FILTER 审中-公开
    单声道过滤器

    公开(公告)号:WO2013149123A1

    公开(公告)日:2013-10-03

    申请号:PCT/US2013/034564

    申请日:2013-03-29

    CPC classification number: G10L21/0208 G10L21/0232 G10L25/30 G10L2021/02087

    Abstract: A system receives monaural sound which includes speech and background noises. The received sound is divided by frequency and time into time-frequency units (TFUs). Each TFU is classified as speech or non-speech by a processing unit. The processing unit for each frequency range includes at least one of a deep neural network (DNN) or a linear support vector machine (LSVM). The DNN extracts and classifies the features of the TFU and includes a pre- trained stack of Restricted Boltzmann Machines (RBM), and each RBM includes a visible and a hidden layer. The LSVM classifies each TFU based on extracted features from the DNN, including those from the visible layer of the first RBM, and those from the hidden layer of the last RBM in the stack. The LSVM and DNN include training with a plurality of training noises. Each TFU classified as speech is output.

    Abstract translation: 系统接收包含语音和背景噪声的单声道声音。 接收的声音被频率和时间分为时间单位(TFU)。 每个TFU被处理单元分类为语音或非语音。 每个频率范围的处理单元包括深神经网络(DNN)或线性支持向量机(LSVM)中的至少一个。 DNN提取并分类了TFU的特征,并且包括一个预先训练的限制玻尔兹曼机器(RBM),每个RBM包括可见和隐藏层。 LSVM根据来自DNN的提取的特征(包括来自第一个RBM的可见层的那些)以及堆叠中最后一个RBM的隐藏层的特征对每个TFU进行分类。 LSVM和DNN包括具有多种训练噪音的训练。 输出分类为语音的每个TFU。

    A SIGNAL PROCESS, A SIGNAL RECOGNITION PROCESS AND A SIGNAL RECOGNITION SYSTEM
    77.
    发明申请
    A SIGNAL PROCESS, A SIGNAL RECOGNITION PROCESS AND A SIGNAL RECOGNITION SYSTEM 审中-公开
    信号处理,信号识别过程和信号识别系统

    公开(公告)号:WO2013063643A1

    公开(公告)日:2013-05-10

    申请号:PCT/AU2012/001331

    申请日:2012-10-31

    CPC classification number: G10L15/02 G10L25/30

    Abstract: A signal recognition process, including: receiving signal data representing a signal; filtering the signal data to generate filtered data representing signal amplitudes as a function of time and one or more other dimensions represented by the signal data; setting signal amplitudes exceeding a saturation threshold to a saturation value representing reinforcement; and applying lateral inhibition across each of the one or more other dimensions to generate, for each said other dimension, inhibitive signal amplitude values at values of said dimension flanking dominant ones of the signal amplitudes along said dimension.

    Abstract translation: 一种信号识别处理,包括:接收表示信号的信号数据; 对信号数据进行滤波以产生表示作为时间的函数的信号幅度的滤波数据和由信号数据表示的一个或多个其它维度; 将信号幅度超过饱和阈值设置为表示加强的饱和值; 以及跨越所述一个或多个其他维度的每一个施加横向抑制,以对于每个所述其他维度,沿着所述维度的信号幅度中的主要信号幅度侧面的所述维度的值产生抑制信号幅度值。

    RHYTHM PROCESSING AND FREQUENCY TRACKING IN GRADIENT FREQUENCY NONLINEAR OSCILLATOR NETWORKS
    78.
    发明申请
    RHYTHM PROCESSING AND FREQUENCY TRACKING IN GRADIENT FREQUENCY NONLINEAR OSCILLATOR NETWORKS 审中-公开
    梯级频率非线性振荡器网络中的RHYTHM处理和频率跟踪

    公开(公告)号:WO2011152888A3

    公开(公告)日:2012-01-26

    申请号:PCT/US2011022993

    申请日:2011-01-28

    Inventor: LARGE EDWARD W

    CPC classification number: G10L25/30 G06N3/049

    Abstract: A method for mimicking the auditory system's response to rhythm of an input signal having a time varying structure comprising the steps of receiving a time varying input signal x(t) to a network of n nonlinear oscillators, each oscillator having a different natural frequency of oscillation and obeying a dynamical equation of the form(the mathematic formula should be inserted here) wherein ? represents the response frequency, r is the amplitude of the oscillator and F is the phase of the oscillator. Generating at least one frequency output from said network useful for describing said varying structure.

    Abstract translation: 一种用于模拟听觉系统对具有时变结构的输入信号的节律的响应的方法,包括以下步骤:向n个非线性振荡器的网络接收时变输入信号x(t),每个振荡器具有不同的固有振荡频率 并遵守形式的动力学方程(这里应该插入数学公式),其中? 表示响应频率,r是振荡器的振幅,F是振荡器的相位。 从所述网络生成用于描述所述变化结构的至少一个频率输出。

    METHOD AND APPARATUS FOR CANONICAL NONLINEAR ANALYSIS OF AUDIO SIGNALS
    79.
    发明申请
    METHOD AND APPARATUS FOR CANONICAL NONLINEAR ANALYSIS OF AUDIO SIGNALS 审中-公开
    用于音频信号的经典非线性分析的方法和装置

    公开(公告)号:WO2011152889A2

    公开(公告)日:2011-12-08

    申请号:PCT/US2011/023015

    申请日:2011-01-28

    CPC classification number: G10L19/00 G06N3/049 G10L25/30

    Abstract: The present invention is directed to systems and methods designed to ascertain the structure of acoustic signals. The approach involves an alternative transform of an acoustic input signal, utilizing a network of nonlinear oscillators in which each oscillator is tuned to a distinct frequency. Each oscillator receives input and interacts with the other oscillators in the network, yielding nonlinear resonances that are used to identify structure in an acoustic input signal. The output of the nonlinear frequency transform can be used as input to a system that will provide further analysis of the signal. According to one embodiment, the nonlinear responses are defined as a network of n expanded canonical oscillators Z i with an input, for each oscillator as a function of an external stimulus. In this way, the response of oscillators to inputs that are not close to its natural frequency are accounted for.

    Abstract translation: 本发明涉及设计用于确定声信号结构的系统和方法。 该方法涉及声输入信号的替代变换,利用非线性振荡器网络,其中每个振荡器被调谐到不同的频率。 每个振荡器接收输入并与网络中的其他振荡器交互,产生用于识别声输入信号中的结构的非线性谐振。 非线性频率变换的输出可以用作将进一步分析信号的系统的输入。 根据一个实施例,对于作为外部刺激的函数的每个振荡器,非线性响应被定义为具有输入的n个扩展规范振荡器Z i的网络。 这样就可以解释振荡器对输入的响应不太接近固有频率。

    METHOD AND APPARATUS FOR DETECTION OF SPECIFIC INPUT SIGNAL CONTRIBUTIONS
    80.
    发明申请
    METHOD AND APPARATUS FOR DETECTION OF SPECIFIC INPUT SIGNAL CONTRIBUTIONS 审中-公开
    用于检测特定输入信号贡献的方法和装置

    公开(公告)号:WO2009028937A1

    公开(公告)日:2009-03-05

    申请号:PCT/NL2008/050565

    申请日:2008-08-25

    CPC classification number: G10L21/0272 G10L25/30

    Abstract: Apparatus and method for detecting a single source contribution in an input signal comprising contributions from more than one source. An input analysis device (3) receives the input signal, for providing a t ime - frequency representation of the input signal. A neural preprocessing device (5) is connected to the input analysis device (3), for separating a foreground signal from background signals in the time - frequency representation of the input signal. A featur e estimation device (7) is connected to the neural preprocessing device (5) for detecting specific features in the foreground signal. A model activation device (11) is connected to the feature estimation device (7) for activating one or more of a set of mo dels based on the detected specific features. A decision device (8) is connected to the model activation device (11) for monitoring the possible activation of a specific one of the models and generating an output based on the monitoring.

    Abstract translation: 用于检测包括来自多于一个源的贡献的输入信号中的单个源贡献的装置和方法。 输入分析装置(3)接收输入信号,以提供输入信号的图像频率表示。 神经预处理装置(5)连接到输入分析装置(3),用于在输入信号的时间 - 频率表示中将背景信号与背景信号分离。 特征估计装置(7)连接到用于检测前景信号中的特定特征的神经预处理装置(5)。 模型激活装置(11)连接到特征估计装置(7),用于基于检测到的特定特征来激活一组移动中的一个或多个。 决定装置(8)连接到模型激活装置(11),用于监视特定模型的可能激活,并且基于监视产生输出。

Patent Agency Ranking