公开(公告)号：US20140286497A1

公开(公告)日：2014-09-25

申请号：US14216769

申请日：2014-03-17

Applicant: Broadcom Corporation

Inventor： Jes Thyssen ,  Ashutosh Pandey ,  Bengt J. Borgstrom ,  Daniele Giacobello ,  Juin-Hwey Chen

IPC: G10K11/16 ,  H04R3/00

CPC classification number: H04R3/005 ,  H04R29/006 ,  H04R2203/12 ,  H04R2410/01 ,  H04R2430/21 ,  H04R2430/23 ,  H04R2430/25

Abstract: 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.

Abstract translation: 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：US20140270226A1

公开(公告)日：2014-09-18

申请号：US14210036

申请日：2014-03-13

Applicant: Broadcom Corporation

Inventor： Bengt J. Borgstrom

IPC: G10K11/16

CPC classification number: G10L21/0208 ,  G10L17/00 ,  G10L17/04 ,  G10L25/06

Abstract: Techniques described herein are directed to the enhancement of spectral features of an audio signal via adaptive modulation filtering. The adaptive modulation filtering process is based on observed modulation envelope autocorrelation coefficients obtained from the audio signal. The modulation envelope autocorrelation coefficients are used to determine parameters of an adaptive filter configured to filter the spectral features of the audio signal to provide filtered spectral features. The parameters are updated based on the observed modulation envelope autocorrelation coefficients to adapt to changing acoustic conditions, such as signal-to-noise ratio (SNR) or reverberation time. Accordingly, such acoustic conditions are not required to be estimated explicitly. Techniques described herein also allow for the estimation of useful side information, e.g., signal-to-noise ratios, based on the observed spectral features of the audio signal and the filtered spectral features, which can be used to improve speaker identification algorithms and/or other audio processing algorithms.

Abstract translation: 本文描述的技术涉及通过自适应调制滤波来增强音频信号的频谱特征。 自适应调制滤波处理基于从音频信号获得的观察到的调制包络自相关系数。 调制包络自相关系数用于确定被配置为滤波音频信号的频谱特征以提供滤波的频谱特征的自适应滤波器的参数。 基于观察到的调制包络自相关系数来更新参数，以适应变化的声学条件，例如信噪比（SNR）或混响时间。 因此，不需要明确地估计这样的声学条件。 本文描述的技术还允许基于所观察到的音频信号的频谱特征和滤波的频谱特征来估计有用的侧信息，例如信噪比，其可以用于改善说话者识别算法和/或 其他音频处理算法。

公开(公告)号：US20160189706A1

公开(公告)日：2016-06-30

申请号：US14606588

申请日：2015-01-27

Applicant: Broadcom Corporation

Inventor： Robert W. Zopf ,  Bengt J. Borgstrom

IPC: G10L15/02 ,  G10L15/14 ,  G06F1/32 ,  G10L15/05

CPC classification number: G06F1/3231 ,  G10L15/063 ,  G10L15/144 ,  G10L2015/025 ,  G10L2015/0635 ,  G10L2015/088

Abstract: Methods, systems, and apparatuses are described for isolated word training and detection. Isolated word training devices and systems are provided in which a user may provide a wake-up phrase from 1 to 3 times to train the device or system. A concatenated phoneme model of the user-provided wake-up phrase may be generated based on the provided wake-up phrase and a pre-trained phoneme model database. A word model of the wake-up phrase may be subsequently generated from the concatenated phoneme model and the provided wake-up phrase. Once trained, the user-provided wake-up phrase may be used to unlock the device or system and/or to wake up the device or system from a standby mode of operation. The word model of the user-provided wake-up phrase may be further adapted based on additional provisioning of the wake-up phrase.

Abstract translation: 描述了用于孤立词训练和检测的方法，系统和装置。 提供了隔离词训练装置和系统，其中用户可以提供1到3次的唤醒短语来训练该装置或系统。 可以基于所提供的唤醒短语和预先训练的音素模型数据库来生成用户提供的唤醒短语的级联音素模型。 可以随后从连接的音素模型和所提供的唤醒短语中产生唤醒短语的单词模型。 经过训练后，用户提供的唤醒短语可用于解锁设备或系统和/或使设备或系统从待机操作模式唤醒。 用户提供的唤醒短语的单词模型可以基于唤醒短语的附加提供来进一步调整。

公开(公告)号：US20160241955A1

公开(公告)日：2016-08-18

申请号：US15136708

申请日：2016-04-22

Applicant: Broadcom Corporation

Inventor： Jes Thyssen ,  Ashutosh Pandey ,  Bengt J. Borgstrom ,  Daniele Giacobello ,  Juin-Hwey Chen

IPC: H04R3/00

CPC classification number: H04R3/005 ,  H04R29/006 ,  H04R2203/12 ,  H04R2410/01 ,  H04R2430/21 ,  H04R2430/23 ,  H04R2430/25

Abstract: 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.

Abstract translation: 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：US20140278417A1

公开(公告)日：2014-09-18

申请号：US13965661

申请日：2013-08-13

Applicant: Broadcom Corporation

Inventor： Juin-Hwey Chen ,  Robert W. Zopf ,  Bengt J. Borgstrom ,  Elias Nemer ,  Ashutosh Pandey ,  Jes Thyssen

IPC: G10L17/06 ,  G10L17/00

CPC classification number: G10L17/00 ,  G10L17/06 ,  G10L21/00

Abstract: 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.

Abstract translation: 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。

公开(公告)号：US20150071461A1

公开(公告)日：2015-03-12

申请号：US14540778

申请日：2014-11-13

Applicant: Broadcom Corporation

Inventor： Jes Thyssen ,  Bengt J. Borgstrom

IPC: H04R3/00

CPC classification number: G10L21/0208 ,  G10L2015/025 ,  H04R3/005

Abstract: 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.

Abstract translation: 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：US20140278418A1

公开(公告)日：2014-09-18

申请号：US14041464

申请日：2013-09-30

Applicant: Broadcom Corporation

Inventor： Juin-Hwey Chen ,  Robert W. Zopf ,  Bengt J. Borgstrom ,  Elias Nemer ,  Ashutosh Pandey ,  Jes Thyssen

IPC: G10L17/00 ,  G10L19/00

CPC classification number: G10L17/00 ,  G10L19/005 ,  G10L21/02

Abstract: 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.

Abstract translation: 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：US09570087B2

公开(公告)日：2017-02-14

申请号：US14540778

申请日：2014-11-13

Applicant: Broadcom Corporation

Inventor： Jes Thyssen ,  Bengt J. Borgstrom

IPC: G10L21/0208 ,  H04R3/00 ,  G10L15/02

CPC classification number: G10L21/0208 ,  G10L2015/025 ,  H04R3/005

Abstract: 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.

Abstract translation: 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：US09520138B2

公开(公告)日：2016-12-13

申请号：US14210036

申请日：2014-03-13

Applicant: Broadcom Corporation

Inventor： Bengt J. Borgstrom

IPC: H03B29/00 ,  G10K11/16 ,  G10L21/0208 ,  G10L17/00 ,  G10L25/06 ,  G10L17/04

CPC classification number: G10L21/0208 ,  G10L17/00 ,  G10L17/04 ,  G10L25/06

Abstract: Techniques described herein are directed to the enhancement of spectral features of an audio signal via adaptive modulation filtering. The adaptive modulation filtering process is based on observed modulation envelope autocorrelation coefficients obtained from the audio signal. The modulation envelope autocorrelation coefficients are used to determine parameters of an adaptive filter configured to filter the spectral features of the audio signal to provide filtered spectral features. The parameters are updated based on the observed modulation envelope autocorrelation coefficients to adapt to changing acoustic conditions, such as signal-to-noise ratio (SNR) or reverberation time. Accordingly, such acoustic conditions are not required to be estimated explicitly. Techniques described herein also allow for the estimation of useful side information, e.g., signal-to-noise ratios, based on the observed spectral features of the audio signal and the filtered spectral features, which can be used to improve speaker identification algorithms and/or other audio processing algorithms.

Abstract translation: 本文描述的技术涉及通过自适应调制滤波来增强音频信号的频谱特征。 自适应调制滤波处理基于从音频信号获得的观察到的调制包络自相关系数。 调制包络自相关系数用于确定被配置为滤波音频信号的频谱特征以提供滤波的频谱特征的自适应滤波器的参数。 基于观察到的调制包络自相关系数来更新参数，以适应变化的声学条件，例如信噪比（SNR）或混响时间。 因此，不需要明确地估计这样的声学条件。 本文描述的技术还允许基于所观察到的音频信号的频谱特征和滤波的频谱特征来估计有用的侧信息，例如信噪比，其可以用于改善说话者识别算法和/或 其他音频处理算法。

公开(公告)号：US09338551B2

公开(公告)日：2016-05-10

申请号：US14216769

申请日：2014-03-17

Applicant: Broadcom Corporation

Inventor： Jes Thyssen ,  Ashutosh Pandey ,  Bengt J. Borgstrom ,  Daniele Giacobello ,  Juin-Hwey Chen

IPC: H04R3/00 ,  G10K11/16 ,  H04R29/00

CPC classification number: H04R3/005 ,  H04R29/006 ,  H04R2203/12 ,  H04R2410/01 ,  H04R2430/21 ,  H04R2430/23 ,  H04R2430/25

Abstract: 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.

Abstract translation: 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。