-
公开(公告)号：US20150071461A1
公开(公告)日：2015-03-12
申请号：US14540778
申请日：2014-11-13
申请人： Broadcom Corporation
发明人： Jes Thyssen , Bengt J. Borgstrom
IPC分类号： H04R3/00
CPC分类号： G10L21/0208 , G10L2015/025 , H04R3/005
摘要： Techniques described herein are directed to performing back-end single-channel suppression of one or more types of interfering sources (e.g., additive noise) in an uplink path of a communication device. The back-end single-channel suppression techniques may suppress types(s) of additive noise using one or more suppression branches (e.g., a non-spatial (or stationary noise) branch, a spatial (or non-stationary noise) branch, a residual echo suppression branch, etc.). The non-spatial branch may be configured to suppress stationary noise from the single-channel audio signal, the spatial branch may be configured to suppress non-stationary noise from the single-channel audio signal and the residual echo suppression branch may be configured to suppress residual echo from the signal-channel audio signal. The spatial branch may be disabled based on an operational mode (e.g., single-user speakerphone mode or a conference speakerphone mode) of the communication device or based on a determination that spatial information is ambiguous.
摘要翻译： 本文描述的技术涉及在通信设备的上行链路路径中执行一种或多种类型的干扰源（例如，加性噪声）的后端单信道抑制。 后端单通道抑制技术可以使用一个或多个抑制分支来抑制附加噪声的类型（例如，非空间（或固定噪声）分支，空间（或非平稳噪声）分支， 残余回波抑制分支等）。 非空间分支可以被配置为抑制来自单声道音频信号的静止噪声，空间分支可以被配置为抑制来自单声道音频信号的非平稳噪声，并且残留回声抑制分支可以被配置为抑制 来自信号通道音频信号的残留回声。 可以基于通信设备的操作模式（例如，单用户扬声器模式或会议免提电话模式）或基于空间信息不明确的确定来禁用空间分支。
-
2.发明申请SPEAKER-IDENTIFICATION-ASSISTED DOWNLINK SPEECH PROCESSING SYSTEMS AND METHODS 审中-公开语音识别辅助语音处理系统和方法公开(公告)号：US20140278418A1
公开(公告)日：2014-09-18
申请号：US14041464
申请日：2013-09-30
申请人： Broadcom Corporation
发明人： Juin-Hwey Chen , Robert W. Zopf , Bengt J. Borgstrom , Elias Nemer , Ashutosh Pandey , Jes Thyssen
CPC分类号： G10L17/00 , G10L19/005 , G10L21/02
摘要： Methods, systems, and apparatuses are described for performing speaker-identification-assisted speech processing in a downlink path of a communication device. In accordance with certain embodiments, a communication device includes speaker identification (SID) logic that is configured to identify the identity of a far-end speaker participating in a voice call with a user of the communication device. Knowledge of the identity of the far-end speaker is then used to improve the performance of one or more downlink speech processing algorithms implemented on the communication device.
摘要翻译： 描述了用于在通信设备的下行链路路径中执行扬声器识别辅助语音处理的方法，系统和装置。 根据某些实施例，通信设备包括被配置为识别与通信设备的用户参与语音呼叫的远端扬声器的身份的扬声器识别（SID）逻辑。 然后使用对远端扬声器的身份的知识来改善在通信设备上实现的一个或多个下行语音处理算法的性能。
-
公开(公告)号：US20170347190A1
公开(公告)日：2017-11-30
申请号：US15365401
申请日：2016-11-30
申请人： Broadcom Corporation
发明人： Jes Thyssen
CPC分类号： H04R3/007 , G10L21/0232 , H03G3/3005 , H04R3/04 , H04R9/06 , H04R29/001 , H04R29/003 , H04R2499/11
摘要： Systems, devices, and methods are described for providing loudspeaker protection. An upstream loudspeaker model estimation component receives sensed electrical characteristics of a loudspeaker and generates an impedance model from which an excursion model, and associated parameters, of the loudspeaker as well as a gain change parameter may be generated. The impedance components are fitted to features of an estimated impedance, based on the voltage and current sense data, to generate the estimated impedance model that is converted to an excursion model of the loudspeaker. A downstream audio signal processing component, based on the excursion model, or parameters thereof, limits a predicted excursion of the loudspeaker utilizing excursion-constraining processing circuitry that includes a non-linear constraint filter. Processed audio signals associated with the limited excursion are subject to distortion suppression prior to releasing the output audio signals for playback on the loudspeaker.
-
公开(公告)号：US09570087B2
公开(公告)日：2017-02-14
申请号：US14540778
申请日：2014-11-13
申请人： Broadcom Corporation
发明人： Jes Thyssen , Bengt J. Borgstrom
IPC分类号： G10L21/0208 , H04R3/00 , G10L15/02
CPC分类号： G10L21/0208 , G10L2015/025 , H04R3/005
摘要： Techniques described herein are directed to performing back-end single-channel suppression of one or more types of interfering sources (e.g., additive noise) in an uplink path of a communication device. The back-end single-channel suppression techniques may suppress types(s) of additive noise using one or more suppression branches (e.g., a non-spatial (or stationary noise) branch, a spatial (or non-stationary noise) branch, a residual echo suppression branch, etc.). The non-spatial branch may be configured to suppress stationary noise from the single-channel audio signal, the spatial branch may be configured to suppress non-stationary noise from the single-channel audio signal and the residual echo suppression branch may be configured to suppress residual echo from the signal-channel audio signal. The spatial branch may be disabled based on an operational mode (e.g., single-user speakerphone mode or a conference speakerphone mode) of the communication device or based on a determination that spatial information is ambiguous.
摘要翻译： 本文描述的技术涉及在通信设备的上行链路路径中执行一种或多种类型的干扰源（例如，加性噪声）的后端单信道抑制。 后端单通道抑制技术可以使用一个或多个抑制分支来抑制附加噪声的类型（例如，非空间（或固定噪声）分支，空间（或非平稳噪声）分支， 残余回波抑制分支等）。 非空间分支可以被配置为抑制来自单声道音频信号的静止噪声，空间分支可以被配置为抑制来自单声道音频信号的非平稳噪声，并且残留回声抑制分支可以被配置为抑制 来自信号通道音频信号的残留回声。 可以基于通信设备的操作模式（例如，单用户扬声器模式或会议免提电话模式）或基于空间信息不明确的确定来禁用空间分支。
-
公开(公告)号：US09338551B2
公开(公告)日：2016-05-10
申请号：US14216769
申请日：2014-03-17
申请人： Broadcom Corporation
CPC分类号： H04R3/005 , H04R29/006 , H04R2203/12 , H04R2410/01 , H04R2430/21 , H04R2430/23 , H04R2430/25
摘要： Methods, systems, and apparatuses are described for improved multi-microphone source tracking and noise suppression. In multi-microphone devices and systems, frequency domain acoustic echo cancellation is performed on each microphone input, and microphone levels and sensitivity are normalized. Methods, systems, and apparatuses are also described for improved acoustic scene analysis and source tracking using steered null error transforms, on-line adaptive acoustic scene modeling, and speaker-dependent information. Switched super-directive beamforming reinforces desired audio sources and closed-form blocking matrices suppress desired audio sources based on spatial information derived from microphone pairings. Underlying statistics are tracked and used to updated filters and models. Automatic detection of single-user and multi-user scenarios, and single-channel suppression using spatial information, non-spatial information, and residual echo are also described.
摘要翻译： 描述了改进的多麦克风源跟踪和噪声抑制的方法，系统和装置。 在多麦克风设备和系统中，在每个麦克风输入端执行频域声学回声消除，并对麦克风电平和灵敏度进行归一化。 还描述了用于改进的声场分析和源跟踪的方法，系统和装置，其使用转向零误差变换，在线自适应声场建模和与扬声器相关的信息。 开关超方向波束成形加强了所需的音频源，并且封闭形式的阻塞矩阵基于从麦克风配对得到的空间信息来抑制所需音频源。 跟踪统计信息，并用于更新过滤器和模型。 还描述了单用户和多用户场景的自动检测，以及使用空间信息，非空间信息和残余回声的单信道抑制。
-
公开(公告)号：US09293140B2
公开(公告)日：2016-03-22
申请号：US13965661
申请日：2013-08-13
申请人： Broadcom Corporation
发明人： Juin-Hwey Chen , Robert W. Zopf , Bengt J. Borgstrom , Elias Nemer , Ashutosh Pandey , Jes Thyssen
摘要： Methods, systems, and apparatuses are described for performing speaker-identification-assisted speech processing. In accordance with certain embodiments, a communication device includes speaker identification (SID) logic that is configured to identify a user of the communication device and/or the identity of a far-end speaker participating in a voice call with a user of the communication device. Knowledge of the identity of the user and/or far-end speaker is then used to improve the performance of one or more speech processing algorithms implemented on the communication device.
摘要翻译： 描述了用于执行说话者识别辅助语音处理的方法，系统和装置。 根据某些实施例，通信设备包括说话人标识（SID）逻辑，其被配置为识别通信设备的用户和/或与通信设备的用户参与语音呼叫的远端扬声器的身份 。 然后使用对用户和/或远端扬声器的身份的知识来改善在通信设备上实现的一个或多个语音处理算法的性能。
-
7.发明授权公开(公告)号：US09269368B2
公开(公告)日：2016-02-23
申请号：US14069124
申请日：2013-10-31
申请人： Broadcom Corporation
发明人： Juin-Hwey Chen , Jes Thyssen , Elias Nemer , Bengt J. Borgstrom , Ashutosh Pandey , Robert W. Zopf
CPC分类号： G10L21/02
摘要： Methods, systems, and apparatuses are described for performing speaker-identification-assisted speech processing in an uplink path of a communication device. In accordance with certain embodiments, a communication device includes speaker identification (SID) logic that is configured to identify the identity of a near-end speaker. Knowledge of the identity of the near-end speaker is then used to improve the performance of one or more uplink speech processing algorithms implemented on the communication device.
摘要翻译： 描述了用于在通信设备的上行链路路径中执行扬声器识别辅助语音处理的方法，系统和装置。 根据某些实施例，通信设备包括被配置为识别近端扬声器的身份的扬声器识别（SID）逻辑。 然后使用对近端扬声器的身份的知识来改善在通信设备上实现的一个或多个上行链路语音处理算法的性能。
-
公开(公告)号：US20140278397A1
公开(公告)日：2014-09-18
申请号：US14069124
申请日：2013-10-31
申请人： Broadcom Corporation
发明人： Juin-Hwey Chen , Jes Thyssen , Elias Nemer , Bengt J. Borgstrom , Ashutosh Pandey , Robert W. Zopf
CPC分类号： G10L21/02
摘要： Methods, systems, and apparatuses are described for performing speaker-identification-assisted speech processing in an uplink path of a communication device. In accordance with certain embodiments, a communication device includes speaker identification (SID) logic that is configured to identify the identity of a near-end speaker. Knowledge of the identity of the near-end speaker is then used to improve the performance of one or more uplink speech processing algorithms implemented on the communication device.
摘要翻译： 描述了用于在通信设备的上行链路路径中执行扬声器识别辅助语音处理的方法，系统和装置。 根据某些实施例，通信设备包括被配置为识别近端扬声器的身份的扬声器识别（SID）逻辑。 然后使用对近端扬声器的身份的知识来改善在通信设备上实现的一个或多个上行链路语音处理算法的性能。
-
公开(公告)号：US20170347189A1
公开(公告)日：2017-11-30
申请号：US15365375
申请日：2016-11-30
申请人： Broadcom Corporation
发明人： Jes Thyssen
CPC分类号： H04R3/007 , G10L21/0232 , H03G3/3005 , H04R3/04 , H04R9/06 , H04R29/001 , H04R29/003 , H04R2499/11
摘要： Systems, devices, and methods are described for providing loudspeaker protection. An upstream loudspeaker model estimation component receives sensed electrical characteristics of a loudspeaker and generates an impedance model from which an excursion model, and associated parameters, of the loudspeaker as well as a gain change parameter may be generated. The impedance components are fitted to features of an estimated impedance, based on the voltage and current sense data, to generate the estimated impedance model of the loudspeaker by combining the fitted impedance components. The resulting estimated impedance model is converted to an excursion model of the loudspeaker. A downstream audio signal processing component utilizes the excursion model, or parameters thereof, to limit a predicted excursion of the loudspeaker. Processed audio signals associated with the limited excursion are subject to distortion suppression prior to releasing the output audio signals for playback on the loudspeaker.
-
公开(公告)号：US20170347188A1
公开(公告)日：2017-11-30
申请号：US15365336
申请日：2016-11-30
申请人： Broadcom Corporation
发明人： Jes Thyssen
IPC分类号： H04R3/00 , H03G3/30 , G10L21/0232 , H04R9/06 , H04R29/00
CPC分类号： H04R3/007 , G10L21/0232 , H03G3/3005 , H04R3/04 , H04R9/06 , H04R29/001 , H04R29/003 , H04R2499/11
摘要： Systems, devices, and methods are described for providing loudspeaker protection. An upstream loudspeaker model estimation component receives sensed electrical characteristics of a loudspeaker, estimates the impedance of the loudspeaker, fits an impedance model to the estimated impedance, and generates an excursion model of the loudspeaker and a gain change parameter from the estimated parameters of the impedance model. A downstream audio signal processing component utilizes the gain change parameter and the excursion model, or parameters thereof, to constrain the temperature of a voice coil of the loudspeaker and to limit a predicted excursion of the loudspeaker. The downstream audio signal processing component also utilizes processed signals associated with the constrained temperature and the limited excursion to suppress unwanted distortion for an output audio signal to be played back by the loudspeaker.
-
-
-
-
-
-
-
-
-
搜索结果
21 条记录 (耗时 0.023 秒)
