-
公开(公告)号：US12238488B2
公开(公告)日：2025-02-25
申请号：US18206021
申请日：2023-06-05
Applicant: GOOGLE TECHNOLOGY HOLDINGS LLC
Inventor： Adrian M. Schuster , Prabhu Annabathula , Kevin J. Bastyr , Andrew K. Wells , Wen Hao Zhang
Abstract: Embodiments are provided for receiving a request to output audio at a first speaker and a second speaker of an electronic device, determining that the electronic device is oriented in a portrait orientation or a landscape orientation, identifying, based on the determined orientation, a first equalization setting for the first speaker and a second equalization setting for the second speaker, providing, for output at the first speaker, a first audio signal with the first equalization setting, and providing, for output at the second speaker, a second audio signal with the second equalization setting.
-
2.发明申请公开(公告)号：US20210125607A1
公开(公告)日：2021-04-29
申请号：US17143472
申请日：2021-01-07
Applicant: Google Technology Holdings LLC
Inventor： Plamen A. Ivanov , Kevin J. Bastyr , Joel A. Clark , Mark A. Jasiuk , Tenkasi V. Ramabadran , Jincheng Wu
IPC: G10L15/20 , G10L15/28 , G10L21/0364
Abstract: A disclosed method includes monitoring an audio signal energy level while having a noise suppressor deactivated to conserve battery power, buffering the audio signal in response to a detected increase in the audio energy level, activating and running a voice activity detector on the audio signal in response to the detected increase in the audio energy level and activating and running a noise estimator in response to voice being detected in the audio signal by the voice activity detector. The method may further include activating and running the noise suppressor only if the noise estimator determines that noise suppression is required. The method activates and runs a noise type classifier to determine the noise type based on information received from the noise estimator and selects a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.
-
公开(公告)号：US10405113B2
公开(公告)日：2019-09-03
申请号：US15818444
申请日：2017-11-20
Applicant: Google Technology Holdings LLC
Inventor： Adrian M. Schuster , Kevin J. Bastyr , Prabhu Anabathula , Andrew K. Wells , Wen Hao Zhang
Abstract: Embodiments are provided for equalizing audio data for output by a speaker of an electronic device based on a local position or orientation of the electronic device. According to certain aspects, the electronic device can determine (858, 868) its local position based on various sensor data, and identify (870, 872) an appropriate equalization setting. In some cases, the electronic device can modify (876, 880) the equalization setting based on acoustic and/or optical data. The electronic device can apply (882) the modified or unmodified equalization setting to an audio signal and cause the speaker to output (886) the audio signal with the applied equalization setting.
-
公开(公告)号：US20180098166A1
公开(公告)日：2018-04-05
申请号：US15818444
申请日：2017-11-20
Applicant: Google Technology Holdings LLC
Inventor： Adrian M. Schuster , Kevin J. Bastyr , Prabhu Anabathula , Andrew K. Wells , Wen Hao Zhang
CPC classification number: H04R29/001 , G06F3/011 , G06F3/0304 , G06F3/0346 , G06F3/0414 , G06F3/16 , G06F3/165 , G06F2203/04108 , H03G5/165 , H04R3/04
Abstract: Embodiments are provided for equalizing audio data for output by a speaker of an electronic device based on a local position or orientation of the electronic device. According to certain aspects, the electronic device can determine (858, 868) its local position based on various sensor data, and identify (870, 872) an appropriate equalization setting. In some cases, the electronic device can modify (876, 880) the equalization setting based on acoustic and/or optical data. The electronic device can apply (882) the modified or unmodified equalization setting to an audio signal and cause the speaker to output (886) the audio signal with the applied equalization setting.
-
公开(公告)号：US20150172816A1
公开(公告)日：2015-06-18
申请号：US14566281
申请日：2014-12-10
Applicant: Google Technology Holdings LLC
Inventor： Plamen A. Ivanov , Scott A. Mehrens , Kevin J. Bastyr , Joel Anthony Clark
CPC classification number: H04R3/04 , H04R1/08 , H04R3/005 , H04R2410/07
Abstract: A method and apparatus for detecting microphone interference includes first and second built-in microphones producing first and second microphone signals. A first filter bank creates first high-frequency-band and first low frequency-band signals from the first microphone signal. A second filter bank creates second high-frequency-band and second low-frequency-hand signals from the second microphone signal. A first measurement calculator determines a high-frequency-band energy value from the first high-frequency-band signal and the second high-frequency-hand signal when the first and second high-frequency-band signals' magnitudes exceeds predetermined thresholds. A second measurement calculator calculates a low-frequency-band energy value from the first low-frequency-band signal and the second low-frequency-band signal when the first and second low-frequency-band signals' magnitudes exceed predetermined thresholds. A logic control block, coupled to the first measurement calculator and the second measurement calculator, detects microphone interference and produces an output signal indicating microphone occlusion or wind noise.
Abstract translation: 用于检测麦克风干扰的方法和装置包括产生第一和第二麦克风信号的第一和第二内置麦克风。 第一滤波器组从第一麦克风信号创建第一高频带和第一低频带信号。 第二滤波器组从第二麦克风信号产生第二高频带和第二低频手信号。 当第一和第二高频带信号的幅度超过预定阈值时，第一测量计算器确定来自第一高频带信号和第二高频手信号的高频带能量值。 当第一和第二低频带信号的幅度超过预定阈值时，第二测量计算器从第一低频带信号和第二低频带信号计算低频带能量值。 耦合到第一测量计算器和第二测量计算器的逻辑控制块检测麦克风干扰并产生指示麦克风闭塞或风噪声的输出信号。
-
Patent Agency Ranking
公开(公告)号：US20230328468A1
公开(公告)日：2023-10-12
申请号：US18206021
申请日：2023-06-05
Applicant: GOOGLE TECHNOLOGY HOLDINGS LLC
Inventor： Adrian M. Schuster , Prabhu Annabathula , Kevin J. Bastyr , Andrew K. Wells , Wen Hao Zhang
CPC classification number: H04R29/001 , G06F3/011 , G06F3/0304 , G06F3/0346 , G06F3/16 , G06F3/165 , H03G5/165 , H04R3/04 , G06F2203/04108
Abstract: Embodiments are provided for receiving a request to output audio at a first speaker and a second speaker of an electronic device, determining that the electronic device is oriented in a portrait orientation or a landscape orientation, identifying, based on the determined orientation, a first equalization setting for the first speaker and a second equalization setting for the second speaker, providing, for output at the first speaker, a first audio signal with the first equalization setting, and providing, for output at the second speaker, a second audio signal with the second equalization setting.
-
7.发明授权公开(公告)号：US10909977B2
公开(公告)日：2021-02-02
申请号：US15977397
申请日：2018-05-11
Applicant: Google Technology Holdings LLC
Inventor： Plamen A. Ivanov , Kevin J. Bastyr , Joel A. Clark , Mark A. Jasiuk , Tenkasi V. Ramabadran , Jincheng Wu
IPC: G10L15/20 , G10L21/0364 , G10L21/0216 , G10L15/28 , G10L21/02 , G10L25/21
Abstract: A disclosed method includes monitoring an audio signal energy level while having a plurality of signal processing components deactivated and activating at least one signal processing component in response to a detected change in the audio signal energy level. The method may include activating and running a voice activity detector on the audio signal in response to the detected change where the voice activity detector is the at least one signal processing component. The method may further include activating and running the noise suppressor only if a noise estimator determines that noise suppression is required. The method may activate and runs a noise type classifier to determine the noise type based on information received from the noise estimator and may select a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.
-
公开(公告)号：US10229697B2
公开(公告)日：2019-03-12
申请号：US13955723
申请日：2013-07-31
Applicant: Google Technology Holdings LLC
Inventor： Kevin J. Bastyr , Giles T Davis , Plamen A Ivanov , Rivanaldo S Oliveira , Tenkasi V Ramabadran , Snehitha Singaraju
IPC: G10L15/20 , G10L21/0208 , H04R3/00 , G10L25/78 , G10L15/01 , G10L21/0216
Abstract: One method of operation includes beamforming a plurality of microphone outputs to obtain a plurality of virtual microphone audio channels. Each virtual microphone audio channel corresponds to a beamform. The virtual microphone audio channels include at least one voice channel and at least one noise channel. The method includes performing voice activity detection on the at least one voice channel and adjusting a corresponding voice beamform until voice activity detection indicates that voice is present on the at least one voice channel. Another method beamforms the plurality of microphone outputs to obtain a plurality of virtual microphone audio channels, where each virtual microphone audio channel corresponds to a beamform, and with at least one voice channel and at least one noise channel. The method performs voice recognition on the at least one voice channel and adjusts the corresponding voice beamform to improve a voice recognition confidence metric.
-
公开(公告)号：US09854374B2
公开(公告)日：2017-12-26
申请号：US15341798
申请日：2016-11-02
Applicant: Google Technology Holdings LLC
Inventor： Adrian M. Schuster , Kevin J. Bastyr , Prabhu Annabathula , Andrew K. Wells , Wen Hao Zhang
CPC classification number: H04R29/001 , G06F3/011 , G06F3/0304 , G06F3/0346 , G06F3/0414 , G06F3/16 , G06F3/165 , G06F2203/04108 , H03G5/165 , H04R3/04
Abstract: Embodiments are provided for equalizing audio data for output by a speaker of an electronic device based on a local position or orientation of the electronic device. According to certain aspects, the electronic device can determine (858, 868) its local position based on various sensor data, and identify (870, 872) an appropriate equalization setting. In some cases, the electronic device can modify (876, 880) the equalization setting based on acoustic and/or optical data. The electronic device can apply (882) the modified or unmodified equalization setting to an audio signal and cause the speaker to output (886) the audio signal with the applied equalization setting.
-
10.发明授权公开(公告)号：US11735175B2
公开(公告)日：2023-08-22
申请号：US17143472
申请日：2021-01-07
Applicant: Google Technology Holdings LLC
Inventor： Plamen A. Ivanov , Kevin J. Bastyr , Joel A. Clark , Mark A. Jasiuk , Tenkasi V. Ramabadran , Jincheng Wu
IPC: G10L15/20 , G10L15/28 , G10L21/0364 , G10L21/02 , G10L25/78 , G10L21/0272 , G10L15/22 , G10L25/84 , G10L21/0216 , G10L25/21
CPC classification number: G10L15/20 , G10L15/22 , G10L15/28 , G10L21/02 , G10L21/0272 , G10L21/0364 , G10L25/78 , G10L25/84 , G10L21/0216 , G10L25/21 , G10L2021/02161 , G10L2025/783
Abstract: A disclosed method includes monitoring an audio signal energy level while having a noise suppressor deactivated to conserve battery power, buffering the audio signal in response to a detected increase in the audio energy level, activating and running a voice activity detector on the audio signal in response to the detected increase in the audio energy level and activating and running a noise estimator in response to voice being detected in the audio signal by the voice activity detector. The method may further include activating and running the noise suppressor only if the noise estimator determines that noise suppression is required. The method activates and runs a noise type classifier to determine the noise type based on information received from the noise estimator and selects a noise suppressor algorithm, from a group of available noise suppressor algorithms, where the selected noise suppressor algorithm is the most power consumption efficient.
-
-
-
-
-
-
-
-
-
Search Results
17
records
(took 0.034 seconds)
