专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

US09648411B2 Sound processing apparatus and sound processing method 有权
公开(公告)号：US09648411B2
公开(公告)日：2017-05-09
申请号：US14598323
申请日：2015-01-16
申请人： CANON KABUSHIKI KAISHA
发明人： Masanobu Funakoshi
IPC分类号： G10L21/00 , G06F17/00 , H04R1/10 , G10L19/00 , G10L21/02
CPC分类号： H04R1/1083 , G10L19/00 , G10L21/02 , H04R2225/39 , H04R2227/001 , H04R2410/07
摘要： An audio matrix formed from absolute amplitude values of coefficients obtained by frequency-transforming an audio signal is generated. The audio matrix is factorized into a basis spectrum and activity matrices. Bases in the basis spectrum matrix are classified into bases concerning a target sound and bases concerning noise. Bases in the activity matrix are classified into bases concerning the target sound and bases concerning the noise. Bases concerning the target sound are obtained from the bases concerning the noise classified from the basis spectrum matrix. A matrix including frequency amplitude values of the target sound is obtained using the bases concerning the target sound classified from the basis spectrum matrix, the bases concerning the target sound and noise classified from the activity matrix, and the obtained bases. The audio signal of the target sound is generated using the matrix.

32. 发明申请

US20170116883A1 METHOD AND SYSTEM FOR ADJUSTING USER SPEECH IN A COMMUNICATION SESSION 审中-公开
公开(公告)号：US20170116883A1
公开(公告)日：2017-04-27
申请号：US15400506
申请日：2017-01-06
申请人： AT&T INTELLECTUAL PROPERTY I, L.P.
发明人： Randolph Wohlert , AARON BANGOR , MARK STOCKERT
IPC分类号： G09B21/00 , H04L29/08 , G10L13/02 , G10L15/02 , G10L21/0364 , G10L21/10
CPC分类号： G09B21/00 , G09B21/006 , G09B21/009 , G10L13/02 , G10L13/033 , G10L15/00 , G10L15/02 , G10L21/003 , G10L21/02 , G10L21/0364 , G10L21/10 , H04L67/22 , H04L67/306
摘要： A system that incorporates the subject disclosure may include, for example, receive user speech captured at a second end user device during a communication session between the second end user device and a first end user device, apply speech recognition to the user speech, identify an unclear word in the user speech based on the speech recognition, adjust the user speech to generate adjusted user speech by replacing all or a portion of the unclear word with replacement audio content, and provide the adjusted user speech to the first end user device during the communication session. Other embodiments are disclosed.

33. 发明申请

US20170032806A1 ACTIVE NOISE CANCELLATION APPARATUS AND METHOD FOR IMPROVING VOICE RECOGNITION PERFORMANCE 有权
标题翻译：主动噪声消除装置和提高语音识别性能的方法
公开(公告)号：US20170032806A1
公开(公告)日：2017-02-02
申请号：US14812300
申请日：2015-07-29
申请人： Harman International Industries, Inc.
发明人： Srikanth KONJETI , Vallabha Vasant HAMPIHOLI
IPC分类号： G10L25/84 , H04R3/00 , G10K11/178
CPC分类号： G10L25/84 , G10K11/17813 , G10K11/17883 , G10K2210/1082 , G10K2210/1282 , G10K2210/3028 , G10K2210/3044 , G10K2210/3225 , G10L15/20 , G10L21/02 , G10L21/0208 , G10L2021/02165 , H04R3/005 , H04R2410/05
摘要： In at least one embodiment, a vehicle active noise cancellation (ANC) apparatus including an ANC controller is disclosed. The ANC controller is operably coupled to at least one error microphone. The ANC controller is configured to receive a first signal indicative of environmental noise that propagates through a vehicle cabin and that is received at a voice recognition (VR) microphone and to generate a noise cancellation wave to remove the environmental noise, the noise cancellation wave being received at the VR microphone. The ANC controller is configured to receive an audio output from the at least one error microphone that is at least indicative of the environmental noise and the noise cancellation wave received at the VR microphone and to apply at least one correction filter to the audio output to remove the environmental noise and the noise cancellation wave that is received at the VR microphone.
摘要翻译：在至少一个实施例中，公开了包括ANC控制器的车辆有源噪声消除（ANC）装置。 ANC控制器可操作地耦合到至少一个误差麦克风。 ANC控制器被配置为接收指示通过车辆舱传播并且在语音识别（VR）麦克风处接收的环境噪声的第一信号，并且产生噪声消除波以消除环境噪声，噪声消除波为在VR麦克风接收。 ANC控制器被配置为从至少一个错误麦克风接收音频输出，其至少表示在VR麦克风处接收到的环境噪声和噪声消除波，并且将至少一个校正滤波器应用于音频输出以去除在VR麦克风接收的环境噪声和噪声消除波。

34. 发明授权

US09558760B2 Real-time remodeling of user voice in an immersive visualization system 有权
标题翻译：在沉浸式可视化系统中实时重构用户声音
公开(公告)号：US09558760B2
公开(公告)日：2017-01-31
申请号：US14641174
申请日：2015-03-06
申请人： Microsoft Technology Licensing, LLC
发明人： Andrew Frederick Muehlhausen , Matthew Johnston , Kasson Crooker
IPC分类号： G06F3/00 , G06F3/048 , G10L21/034 , G06T19/00 , G02B27/01 , G06F3/01 , G10L21/003
CPC分类号： G10L21/0202 , A63F13/215 , A63F13/54 , G02B27/017 , G02B27/0172 , G02B2027/0138 , G02B2027/014 , G02B2027/0178 , G06F3/011 , G06F3/012 , G06T17/05 , G06T19/006 , G10L21/003 , G10L21/02 , G10L21/034 , H04S7/304 , H04S2400/15 , H04S2420/01
摘要： A visualization system with audio capability includes one or more display devices, one or more microphones, one or more speakers, and audio processing circuitry. While a display device displays a holographic image to a user, a microphone inputs an utterance of the user, or a sound from the user's environment, and provides it to the audio processing circuitry. The audio processing circuitry processes the utterance (or other sound) in real-time to add an audio effect associated with the image to increase realism, and outputs the processed utterance (or other sound) to the user via the speaker in real-time, with very low latency.
摘要翻译：具有音频功能的可视化系统包括一个或多个显示设备，一个或多个麦克风，一个或多个扬声器和音频处理电路。当显示设备向用户显示全息图像时，麦克风输入用户的话语或来自用户环境的声音，并将其提供给音频处理电路。音频处理电路实时地处理话音（或其他声音）以添加与图像相关联的音频效果以增加现实感，并且经由扬声器实时地将处理的话语（或其他声音）输出给用户，具有非常低的延迟。

35. 发明授权

US09558755B1 Noise suppression assisted automatic speech recognition 有权
标题翻译：噪声抑制辅助自动语音识别
公开(公告)号：US09558755B1
公开(公告)日：2017-01-31
申请号：US12962519
申请日：2010-12-07
申请人： Jean Laroche , Carlo Murgia
发明人： Jean Laroche , Carlo Murgia
IPC分类号： G10L21/02 , G10L21/00
CPC分类号： G10L21/02 , G10L15/20 , G10L21/00 , G10L21/0232 , G10L25/78 , G10L2021/02165
摘要： Noise suppression information is used to optimize or improve automatic speech recognition performed for a signal. Noise suppression can be performed on a noisy speech signal using a gain value. The gain to apply to the noisy speech signal is selected to optimize speech recognition analysis of the resulting signal. The gain may be selected based on one or more features for a current sub band and time frame, as well as one or more features for other sub bands and/or time frames. Noise suppression information can be provided to a speech recognition module to improve the robustness of the speech recognition analysis. Noise suppression information can also be used to encode and identify speech.
摘要翻译：噪声抑制信息用于优化或改善对信号执行的自动语音识别。噪声抑制可以使用增益值对噪声语音信号进行。选择应用于噪声语音信号的增益以优化所得信号的语音识别分析。可以基于用于当前子带和时间帧的一个或多个特征以及用于其他子带和/或时间帧的一个或多个特征来选择增益。噪声抑制信息可以提供给语音识别模块，以提高语音识别分析的鲁棒性。噪声抑制信息也可用于编码和识别语音。

36. 发明授权

US09549266B2 Method of controlling a hearing instrument 有权
标题翻译：控制听力仪器的方法
公开(公告)号：US09549266B2
公开(公告)日：2017-01-17
申请号：US14396442
申请日：2012-04-24
申请人： Manuela Feilner , Martin Kuster
发明人： Manuela Feilner , Martin Kuster
IPC分类号： H04R25/00 , G10L21/02
CPC分类号： H04R25/50 , G10L21/02 , H04R25/407 , H04R25/552 , H04R2225/41 , H04R2225/43 , H04R2410/01
摘要： Method of controlling a hearing instrument comprising at least one hearing device, the method comprising determination of an acoustic environment at least partially by means of calculating the complex coherence of signals from either a pressure microphone and a particle velocity transducer; a pair of pressure microphones in a single hearing device; or a pair of pressure microphones, one situated in each of a pair of hearing devices. This enables finer determination of acoustic environments, thus improving the hearing experience for the wearer of the hearing instrument.The invention further relates to a corresponding hearing instrument.
摘要翻译：本发明还涉及相应的听力仪器。

37. 发明授权

US09525958B2 Multidimensional virtual learning system and method 有权
公开(公告)号：US09525958B2
公开(公告)日：2016-12-20
申请号：US14921828
申请日：2015-10-23
申请人： GLEIM CONFERENCING, LLC
发明人： Garrett William Gleim
IPC分类号： H04R5/00 , H04S7/00 , H04M3/56 , H04B3/46 , H04S5/00 , G10L21/02 , G10L21/034 , G10L21/10 , G10L25/72 , H04R5/02
CPC分类号： H04S7/304 , G10L21/02 , G10L21/0202 , G10L21/034 , G10L21/10 , G10L25/72 , H04B3/46 , H04M3/568 , H04R5/02 , H04S5/00 , H04S7/30 , H04S7/302 , H04S7/305 , H04S7/40 , H04S2400/01 , H04S2400/11 , H04S2400/13 , H04S2420/01
摘要： A process and system for generating three dimensional sound conferencing includes generating a virtual map with a plurality of positions, each participant selecting one of the positions, determining a direction from each position to each other position on the map, determining a distance from each position to each other position on the map, receiving sound from each participant, mixing the received sound, transforming the mixed sound into binaural audio, and directing the binaural audio sound to each participant via a speaker associated with the virtual position of the speaking participant. The result is a clarified sound that gives to the listening participant a sense of where the speaking participant is positioned relative to the listening participant.

38. 发明授权

US09514763B2 Noise reduction via tuned acoustic echo cancellation 有权
标题翻译：通过调谐回音消除降噪
公开(公告)号：US09514763B2
公开(公告)日：2016-12-06
申请号：US13894507
申请日：2013-05-15
申请人： Lenovo (Singapore) Pte. Ltd.
发明人： Robert James Kapinos
IPC分类号： H04B3/20 , G10L21/02 , G10L21/0208
CPC分类号： G10L21/02 , G10L2021/02082
摘要： An embodiment provides a method, including: accessing a tuned corrective mask stored in a memory device; forming, using a processor, a tuned acoustic echo cancellation mask utilizing the tuned-corrective mask; applying, using a processor, the tuned acoustic echo cancellation mask to a digital audio signal; and outputting an echo-cancelled audio signal. Other aspects are described and claimed.
摘要翻译：实施例提供了一种方法，包括：访问存储在存储设备中的调谐校正掩码; 使用处理器来形成利用调谐校正掩模的调谐回声消除掩模; 使用处理器将调谐的声学回波消除掩模应用于数字音频信号; 并输出回波消除音频信号。描述和要求保护其他方面。

39. 发明申请

US20160293179A1 EXTRACTION OF REVERBERANT SOUND USING MICROPHONE ARRAYS 有权
标题翻译：使用麦克风阵列提取复音声音
公开(公告)号：US20160293179A1
公开(公告)日：2016-10-06
申请号：US15178530
申请日：2016-06-09
申请人： Fraunhofer-Gesellschaft zur Foerderung der angewandten Forschung e.V.
发明人： Oliver THIERGART , Emanuel HABETS
IPC分类号： G10L21/0264 , H04R3/00
CPC分类号： G10L21/0264 , G10L19/26 , G10L21/02 , G10L21/0208 , G10L2021/02082 , G10L2021/02166 , G11B2020/10601 , H04R3/005 , H04R5/027 , H04S2400/15 , H04S2420/01
摘要： A method includes estimating a spatial coherence between a first diffuse sound portion in a first microphone signal and a second diffuse sound portion in a second microphone signal. The first microphone signal is captured by a first microphone and the second microphone signal is captured by a second microphone which is spaced apart from the first microphone in a known manner. The method further includes defining a linear constraint for filter coefficients of a diffuse sound filter, the linear constraint being based on the spatial coherence. The method also includes calculating at least one of signal statistics and noise statistics over the first microphone signal and the second microphone signal. The method also includes determining the filter coefficients of the diffuse sound filter by solving an optimization problem concerning at least one of the signal statistics and noise statistics while considering the linear constraint for the filter coefficients.
摘要翻译：一种方法包括估计第一麦克风信号中的第一扩散声部分和第二麦克风信号中的第二扩散声部分之间的空间相干性。第一麦克风信号由第一麦克风捕获，并且第二麦克风信号由以已知方式与第一麦克风间隔开的第二麦克风捕获。该方法还包括为扩散声音滤波器的滤波器系数定义线性约束，线性约束基于空间相干性。该方法还包括通过第一麦克风信号和第二麦克风信号来计算信号统计和噪声统计中的至少一个。该方法还包括通过在考虑滤波器系数的线性约束的同时解决关于信号统计和噪声统计中的至少一个的优化问题来确定漫反射滤波器的滤波器系数。

40. 发明授权

US09460729B2 Layered approach to spatial audio coding 有权
标题翻译：分层方法进行空间音频编码
公开(公告)号：US09460729B2
公开(公告)日：2016-10-04
申请号：US14427589
申请日：2013-09-10
申请人： DOLBY LABORATORIES LICENSING CORPORATION , DOLBY INTERNATIONAL AB
发明人： Glenn Dickins , Heiko Purnhagen , Leif Jonas Samuelsson
IPC分类号： G10L19/02 , G10L19/012 , H04M3/56 , G10L21/0208 , G10L19/008 , G10L21/0216
CPC分类号： G10L19/012 , G10L19/008 , G10L19/02 , G10L19/0208 , G10L19/032 , G10L19/22 , G10L19/24 , G10L21/02 , G10L21/0208 , G10L21/0216 , H04M3/56
摘要： The invention provides a layered audio coding format with a monophonic layer and at least one sound field layer. A plurality of audio signals is decomposed, in accordance with decomposition parameters controlling the quantitative properties of an orthogonal energy-compacting transform, into rotated audio signals. Further, a time-variable gain profile specifying constructively how the rotated audio signals may be processed to attenuate undesired audio content is derived. The monophonic layer may comprise one of the rotated signals and the gain profile. The sound field layer may comprise the rotated signals and the decomposition parameters. In one embodiment, the gain profile comprises a cleaning gain profile with the main purpose of eliminating non-speech components and/or noise. The gain profile may also comprise mutually independent broadband gains. Because signals in the audio coding format can be mixed with a limited computational effort, the invention may advantageously be applied in a tele-conferencing application.
摘要翻译：本发明提供了具有单声道层和至少一个声场层的分层音频编码格式。根据控制正交能量压缩变换的定量特性的分解参数将多个音频信号分解成旋转音频信号。此外，推导出时间变量增益曲线，其具体地指定旋转的音频信号如何被处理以衰减不需要的音频内容。单声道层可以包括旋转的信号之一和增益分布。声场层可以包括旋转的信号和分解参数。在一个实施例中，增益分布包括清除增益曲线，其主要目的是消除非语音分量和/或噪声。增益曲线也可以包括相互独立的宽带增益。因为音频编码格式的信号可以以有限的计算量来混合，所以本发明可以有利地应用于远程会议应用中。

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