专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明授权

EP2710590B1 SUPER-WIDEBAND NOISE SUPRESSION 有权转让
标题翻译：超宽带噪声抑制
公开(公告)号：EP2710590B1
公开(公告)日：2015-10-07
申请号：EP11722677.9
申请日：2011-05-16
申请人： Google Inc.
发明人： PANICONI, Marco , SKOGLUND, Jan
IPC分类号： G10L21/0208 , G10L21/0232 , G10L21/0224 , G10L25/78
CPC分类号： G10L21/0208 , G10L21/0224 , G10L21/0232 , G10L25/78

12. 发明公开

EP2828852A1 POST-PROCESSING GAINS FOR SIGNAL ENHANCEMENT 有权
标题翻译： NACHBEARBEITUNG VONVERSTÄRKUNGFÜRSIGNALVERBESSERUNG
公开(公告)号：EP2828852A1
公开(公告)日：2015-01-28
申请号：EP13714812.8
申请日：2013-03-21
申请人： Dolby Laboratories Licensing Corporation
发明人： SUN, Xuejing , DICKINS, Glenn N.
IPC分类号： G10L21/0316
CPC分类号： G10L21/0364 , G10K11/16 , G10L21/0224 , G10L21/0316 , G10L21/034 , G10L25/78 , H03G3/301 , H03G3/32
摘要： A method, an apparatus, and logic to post-process raw gains determined by input processing to generate post-processed gains, comprising using one or both of delta gain smoothing and decision-directed gain smoothing. The delta gain smoothing comprises applying a smoothing filter to the raw gain with a smoothing factor that depends on the gain delta: the absolute value of the difference between the raw gain for the current frame and the post-processed gain for a previous frame. The decision-directed gain smoothing comprises converting the raw gain to a signal-to-noise ratio, applying a smoothing filter with a smoothing factor to the signal-to-noise ratio to calculate a smoothed signal-to-noise ratio, and converting the smoothed signal-to-noise ratio to determine the second smoothed gain, with smoothing factor possibly dependent on the gain delta.
摘要翻译：一种用于后处理由输入处理确定的原始增益以生成后处理增益的方法，装置和逻辑，包括使用增量增益平滑和决策导向增益平滑中的一者或两者。 Δ增益平滑包括对平滑滤波器施加平滑因子，该平滑滤波器依赖于增益增量：当前帧的原始增益与前一帧的后处理增益之间的差的绝对值。决策导向增益平滑包括将原始增益转换为信噪比，将具有平滑因子的平滑滤波器应用于信噪比以计算平滑的信噪比，并将平滑的信噪比以确定第二平滑增益，平滑因子可能取决于增益增量。

13. 发明公开

EP2748814A1 AUDIO OR VOICE SIGNAL PROCESSOR 审中-公开
标题翻译：音频或语音信号处理器
公开(公告)号：EP2748814A1
公开(公告)日：2014-07-02
申请号：EP11871237.1
申请日：2011-08-24
申请人： Huawei Technologies Co., Ltd
发明人： TALEB, Anisse , XU, Jianfeng , PANG, Liyun , MIAO, Lei
IPC分类号： G10L19/005 , H04J3/06 , H04N21/6437 , H04N21/442 , H04N21/439 , H04L29/06 , G10L21/04
CPC分类号： G10L21/0224 , G10L19/005 , G10L21/04 , H04J3/0632 , H04L29/06462 , H04L29/06489 , H04L29/06517 , H04L29/06523 , H04N21/4392 , H04N21/4398 , H04N21/44209 , H04N21/6437
摘要： The invention relates to a voice or audio signal processor for processing received network packets received over a communication network to provide an output signal, the voice or audio signal processor comprising a jitter buffer (911) being configured to buffer the received network packets (105), a voice or audio decoder (913) being configured to decode the received network packets (105) as buffered by the jitter buffer (911) to obtain a decoded voice or audio signal, a controllable time scaler (917) being configured to amend a length of the decoded voice or audio signal to obtain a time scaled voice or audio signal as the output voice or audio signal, and an adaptation control means (903) being configured to control an operation of the time scaler (917) in dependency on a processing complexity measure.
摘要翻译：本发明涉及一种语音或音频信号处理器，用于处理通过通信网络接收的网络分组以提供输出信号，语音或音频信号处理器包括抖动缓冲器（911），其被配置为缓冲接收到的网络分组（105），语音或音频解码器（913）被配置为解码由抖动缓冲器（911）缓冲的接收到的网络分组（105）以获得解码的语音或音频信号，可控制的时间缩放器（917）被配置为修改解码的语音或音频信号的长度以获得时间缩放的语音或音频信号作为输出语音或音频信号;以及适配控制装置（903），被配置为依赖于时间缩放器（917）的操作来控制处理复杂性度量。

14. 发明公开

EP2709105A1 Method and system for reducing impulsive noise disturbance 有权
标题翻译： Verfahren，System and Computerprogrammprodukt zur Verringerung vonImpulsstörungenin einem Audiosignal
公开(公告)号：EP2709105A1
公开(公告)日：2014-03-19
申请号：EP12184317.1
申请日：2012-09-13
申请人： NXP B.V.
发明人： Gautama, Temujin
IPC分类号： G10L21/0208 , H04B1/10 , G11B20/24 , H03G3/32
CPC分类号： G10K11/178 , G10L21/0208 , G10L21/0224 , G10L21/0232 , H03G3/345 , H04B1/1027
摘要： FM and AM receivers in car environments require a noise blanker circuit or method to reduce the audible disturbances generated by impulse noise, such as ignition noise, in the audio signal. The invention proposes a combination of time-domain and frequency-domain processing to reduce the audible distortion. The time-domain processing interpolates the signal during the impulse noise bursts, and the frequency-domain processing disperses the remaining signal distortion over time, or relocates it to positions in time where it is attenuated by a windowing technique.
摘要翻译：汽车环境中的FM和AM接收机需要一个噪声抑制电路或方法来减少由音频信号中的脉冲噪声（如点火噪声）产生的声音干扰。本发明提出了时域和频域处理的组合，以减少可听失真。时域处理在脉冲噪声突发期间内插信号，并且频域处理随着时间的推移分散剩余的信号失真，或者将其重定位到通过加窗技术被衰减的时间位置。

15. 发明公开

EP2466581A3 Sound processing apparatus and sound processing program 有权
标题翻译：声音处理设备和声音处理程序
公开(公告)号：EP2466581A3
公开(公告)日：2012-10-24
申请号：EP11193313.1
申请日：2011-12-13
申请人： Fujitsu Limited
发明人： Matsuo, Naoshi
IPC分类号： G10L21/02
CPC分类号： G10L21/0208 , G10L21/0224 , G10L2021/02165 , H04R3/005 , H04R5/00
摘要： A sound processing apparatus includes a first calculator (130R) that calculates a first power based on a first signal received by a first microphone (110R); a second calculator (130L) that calculates a second power based on a second signal received by a second microphone (110L); a gain calculator (140) that calculates a gain on the basis of the ratio of the first power to the second power; and a multiplier (160) that processes the second signal using the gain calculated by the gain calculator.
摘要翻译：声音处理设备包括：第一计算器（130R），其基于由第一麦克风（110R）接收的第一信号来计算第一功率; 第二计算器（130L），其基于由第二麦克风（110L）接收到的第二信号来计算第二功率; 增益计算器（140），其基于第一功率与第二功率的比率来计算增益; 以及使用由增益计算器计算的增益处理第二信号的乘法器（160）。

16. 发明授权

EP3252765B1 NOISE SUPPRESSION IN A VOICE SIGNAL 有权
公开(公告)号：EP3252765B1
公开(公告)日：2018-12-12
申请号：EP17173212.6
申请日：2017-05-29
申请人： Fujitsu Limited
发明人： Matsuo, Naoshi
IPC分类号： G10L21/0208 , H03G3/32 , H03G3/34 , G10L21/0216 , G10L21/0316 , G10L21/0224
CPC分类号： G10L21/0264 , G10L21/0208 , G10L21/0224 , G10L21/0316 , G10L25/06 , G10L25/21 , G10L2021/02082 , G10L2021/02087 , G10L2021/02165 , H03G3/32 , H04R3/005 , H04R3/04
摘要： A noise suppression device includes: an adaptive filter unit that suppresses, using an adaptive filter, a noise component contained in a voice signal generated from a voice captured by a voice input unit to generate a corrected voice signal; a noise generation detection unit that detects timing of generation of the noise component in the voice signal; and a period suppression unit that suppresses the corrected voice signal during a predetermined period of time after the timing of the generation of the noise component.

17. 发明公开

EP3392883A1 METHOD FOR PROCESSING AN INPUT AUDIO SIGNAL AND CORRESPONDING ELECTRONIC DEVICE, NON-TRANSITORY COMPUTER READABLE PROGRAM PRODUCT AND COMPUTER READABLE STORAGE MEDIUM 审中-公开
公开(公告)号：EP3392883A1
公开(公告)日：2018-10-24
申请号：EP18165900.4
申请日：2018-04-05
申请人： THOMSON LICENSING
发明人： PAREKH, Sanjeel , OZEROV, Alexey , DUONG, Quang Khanh Ngoc , RICHARD, Gaël , ESSID, Slim , PEREZ, Patrick
IPC分类号： G10L21/0272 , G10L25/57
CPC分类号： G10L21/028 , G10L21/0224 , G10L21/0232 , G10L21/0272 , G10L25/57
摘要： The present disclosure relates to a method for processing an input signal comprising an audio component and to the corresponding electronic device, non-transitory computer readable program product and computer readable storage medium.
According to an embodiment of the present disclosure, the method comprises:
• obtaining a set of time parameters from a time frequency transformation of the audio component of the input signal, said audio component being a mixture of audio signals comprising at least one first audio signal of a first audio source;
• determining at least one motion feature of said first audio source from a visual sequence corresponding to the first audio signal;
• obtaining a weight vector of the set of time parameters based on the motion feature; and
• determining a time frequency transformation of the first audio signal based on the weight vector.

18. 发明公开

EP3291234A1 VERFAHREN ZUM BEURTEILEN EINER QUALITÄT EINES STIMMEINSATZES EINES SPRECHENDEN 有权
标题翻译：评估讲话语音互换质量的方法
公开(公告)号：EP3291234A1
公开(公告)日：2018-03-07
申请号：EP16186498.8
申请日：2016-08-31
申请人： Digithep GmbH
发明人： Hönig, Florian
IPC分类号： G10L25/60 , G10L25/66 , G10L25/21
CPC分类号： G10L21/0205 , G10L15/20 , G10L21/0224 , G10L21/0232 , G10L25/21 , G10L25/60 , G10L25/66
摘要： Offenbart wird ein Verfahren zum Beurteilen einer Qualität eines Stimmeinsatzes eines Sprechenden, wobei ein akustisches Sprachsignal des Sprechenden erfasst und in ein digitales Sprachsignal gewandelt wird, wobei das digitale Sprachsignal in seinem zeitlichen Verlauf analysiert wird, um
a. In dem zeitlichen Verlauf des digitalen Sprachsignals einen Zeitpunkt des Stimmeinsatzes des Sprechenden zu bestimmen,
b. eine Grundfrequenz des Sprachsignals zum Zeitpunkt des Stimmeinsatzes zu ermitteln,
c. aus dem digitalen Sprachsignal in einem vorgegebenen Zeitintervall ab dem Zeitpunkt des Stimmeinsatzes zeitlich aufgelöst den Verlauf der bei der Grundfrequenz in dem Sprachsignal enthaltenen Energie zu ermitteln;
d. aus dem digitalen Sprachsignal in dem vorgegebenen Zeitintervall zeitlich aufgelöst den Verlauf der bei wenigstens einem harmonischen Vielfachen der Grundfrequenz in dem Sprachsignal enthaltenen Energie zu ermitteln;
e. den zeitlichen Verlauf des Verhältnisses der in Schritten c und d ermittelten Energien zu bestimmen,
wobei auf einen weichen Stimmeinsatz geschlossen wird, wenn in dem Zeitintervall das gemäß vorstehenden Schritt e. ermittelte Verhältnis der Energien zunächst von der Energie bei der Grundfrequenz dominiert wird, erst im weiteren Verlauf des vorgegebenen Zeitintervalls in einer Zeitspanne Δt das Verhältnis der Energien sich zugunsten der Energie(n) bei der/den harmonischen Vielfachen der Grundfrequenz verschiebt.
Weiterhin offenbart werden ein Datenverarbeitungsprogramm für die rechnergestützte, automatisierte Beurteilung einer Qualität eines Stimmeinsatzes eines Sprechenden, das ein solches Verfahren umsetzt, sowie ein rechnergestütztes Datenverarbeitungsgerät mit einem solchen Datenverarbeitungsprogramm.
Mit der Erfindung lässt sich die Qualität eines Stimmeinsatzes eines Sprechenden sehr viel besser und genauer automatisiert beurteilen, als dies nach dem Stand der Technik möglich war.
摘要翻译：公开的是判断语音使用的扬声器，其特征在于，被检测并转换成数字语音信号的扬声器的声学语音信号的质量的方法，所述数字语音信号在它的时间特性的分析。在数字语音信号的时间过程中确定讲话者的语音使用时间，b。确定语音应用时语音信号的基频，c。从语音以时间分辨形式使用的时间起在预定时间间隔内从数字语音信号中确定包含在语音信号中的基频中的能量的进程; d。从在预定的时间间隔，以确定包含在语音信号中的基本频率中的至少一个谐波倍数的能量的时间分辨文件，与数字语音信号; 即确定在步骤c和d中确定的能量比率的时间进程，其中如果在该时间间隔内进行上述步骤e，则得出使用软语音的结论。能量的确定的比率最初由能量在基频为主，只在预定的时间间隔的剩余部分在一段时间.DELTA.t的能量的有利于在基本频率偏移的/谐波倍数的能量（或多个）的比率。进一步公开了一种用于使用语音的扬声器，它转换这样的方法，和一种基于计算机的数据处理装置与这样的数据处理程序中的质量的计算机辅助，自动评估的数据处理程序。通过本发明，与现有技术相比，可以评估讲话者语音使用的质量好得多且更精确的自动化。

19. 发明公开

EP3161825A1 TEMPORAL GAIN ADJUSTMENT BASED ON HIGH-BAND SIGNAL CHARACTERISTIC 有权
公开(公告)号：EP3161825A1
公开(公告)日：2017-05-03
申请号：EP15731780.1
申请日：2015-06-05
申请人： Qualcomm Incorporated
发明人： ATTI, Venkatraman S. , KRISHNAN, Venkatesh , RAJENDRAN, Vivek , CHEBIYYAM, Venkata Subrahmanyam Chandra Sekhar , SUBASINGHA, Subasingha Shaminda
IPC分类号： G10L21/038 , G10L19/24 , G10L19/02 , G10L19/06
CPC分类号： G10L19/12 , G10L19/0204 , G10L19/032 , G10L19/06 , G10L19/24 , G10L21/0224 , G10L21/038 , G10L25/12 , G10L2019/0016
摘要： The present disclosure provides techniques for adjusting a temporal gain parameter and for adjusting linear prediction coefficients. A value of the temporal gain parameter may be based on a comparison of a synthesized high-band portion of an audio signal to a high-band portion of the audio signal. If a signal characteristic of an upper frequency range of the high-band portion satisfies a first threshold, the temporal gain parameter may be adjusted. A linear prediction (LP) gain may be determined based on an LP gain operation that uses a first value for an LP order. The LP gain may be associated with an energy level of an LP synthesis filter. The LP order may be reduced if the LP gain satisfies a second threshold.

20. 发明公开

EP2954513A1 AMBIENT NOISE ROOT MEAN SQUARE (RMS) DETECTOR 有权
标题翻译：探测器方形环境噪声的方式
公开(公告)号：EP2954513A1
公开(公告)日：2015-12-16
申请号：EP13783126.9
申请日：2013-07-04
申请人： Cirrus Logic, Inc.
发明人： MILANI, Ali, Abdollahzadeh
IPC分类号： G10K11/178 , G10L21/0224
CPC分类号： H04R29/00 , G10K11/178 , G10K2210/108 , G10K2210/3023 , G10L21/0216 , G10L21/0224 , G10L2021/02165 , H04R29/004
摘要： An RMS detector uses the concept of the k-NN (classifying using nearest neighbors)—algorithm in order to obtain RMS values. A rms detector using first-order regressor with a variable smoothing factor is modified to penalize samples from center of data in order to obtain RMS values. Samples which vary greatly from the background noise levels, such as speech, scratch, wind and other noise spikes, are dampened in the RMS calculation. When background noise changes, the system will track the changes in background noise and include the changes in the calculation of the corrected RMS value. A minimum tracker runs more often (e.g. two or three times) than the rate as in prior art detectors and methods, tracks the minimum rms value, which is to compute a normalized distance value, which in turn is used to normalize the smoothing factor. From this data, a corrected or revised RMS value is determined as the function of the previous RMS value multiplied by one minus the smoothing factor plus the smooth factor times the minimum rms value to output the corrected RMS for the present invention. The rms value is used to generate a reset signal for the minimum tracker and is used to avoid deadlock in the tracker, for example, when the background signal increases/decreases over time.

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