公开(公告)号：US11840176B2

公开(公告)日：2023-12-12

申请号：US17862348

申请日：2022-07-11

申请人： Robert D. Pedersen

发明人： Robert D. Pedersen

IPC分类号： B60Q9/00 ,  G10L25/78 ,  H04W4/90 ,  G08G1/048 ,  G10L21/0232 ,  H04R1/40 ,  G08G1/01 ,  G10L15/26 ,  G10L15/22 ,  G08G1/16 ,  G06N5/02 ,  H04W4/80 ,  G08G1/0967 ,  G08G1/00 ,  H04R3/00 ,  H04W4/02 ,  H04W4/40 ,  G06N5/048 ,  H04B5/00 ,  H04M1/72454 ,  H04M1/72463 ,  G06V20/56 ,  G06V20/59 ,  G10L21/0216 ,  H04B7/06

CPC分类号： B60Q9/008 ,  G06N5/02 ,  G06N5/048 ,  G06V20/56 ,  G06V20/597 ,  G08G1/012 ,  G08G1/0116 ,  G08G1/0129 ,  G08G1/0141 ,  G08G1/048 ,  G08G1/096716 ,  G08G1/096741 ,  G08G1/096775 ,  G08G1/096783 ,  G08G1/166 ,  G08G1/167 ,  G08G1/205 ,  G10L15/22 ,  G10L15/26 ,  G10L21/0232 ,  G10L25/78 ,  H04B5/0056 ,  H04B5/0081 ,  H04M1/72454 ,  H04M1/72463 ,  H04R1/406 ,  H04R3/005 ,  H04W4/023 ,  H04W4/40 ,  H04W4/80 ,  H04W4/90 ,  G10L2021/02166 ,  H04B5/0043 ,  H04B7/0617 ,  H04R2201/403 ,  H04R2499/13

摘要： Specifically programmed, integrated motor vehicle dangerous driving warning and control system and methods comprising at least one specialized communication computer machine including electronic artificial intelligence expert system decision making capability further comprising one or more motor vehicle electronic sensors for monitoring the motor vehicle and for monitoring activities of the driver and/or passengers including activities related to the use of cellular telephones and/or other wireless communication devices and further comprising electronic communications transceiver assemblies for communications with external sensor networks for monitoring dangerous driving situations, weather conditions, roadway conditions, pedestrian congestion and motor vehicle traffic congestion conditions to derive warning and/or control signals for warning the driver of dangerous driving situations and/or for controlling the motor vehicle driver use of a cellular telephone and/or other wireless communication devices.

公开(公告)号：US11837228B2

公开(公告)日：2023-12-05

申请号：US17314601

申请日：2021-05-07

申请人： Nuance Communications, Inc.

发明人： Dushyant Sharma ,  Patrick A. Naylor ,  Rong Gong ,  Stanislav Kruchinin ,  Ljubomir Milanovic

IPC分类号： G10L15/22 ,  H04R1/40 ,  H04R3/00 ,  G10L25/84 ,  G10L15/32 ,  G10L15/20 ,  G06F16/65 ,  G06F16/68 ,  G10L17/06 ,  G10L25/78 ,  H04R3/04 ,  H04R5/04 ,  H04S7/00 ,  H04R29/00 ,  G16H15/00 ,  G06N20/00 ,  G10L21/028 ,  G10L15/26 ,  G16H10/60 ,  G16H40/20 ,  G10L21/0216 ,  G10L21/0272

CPC分类号： G10L15/22 ,  G06F16/65 ,  G06F16/686 ,  G06N20/00 ,  G10L15/20 ,  G10L15/32 ,  G10L17/06 ,  G10L21/028 ,  G10L25/78 ,  G10L25/84 ,  G16H15/00 ,  H04R1/406 ,  H04R3/005 ,  H04R3/04 ,  H04R5/04 ,  H04R29/005 ,  H04S7/307 ,  G10L15/26 ,  G10L21/0216 ,  G10L21/0272 ,  G10L2021/02166 ,  G16H10/60 ,  G16H40/20

摘要： A method, computer program product, and computing system for receiving a speech signal from each microphone of a plurality of microphones, thus defining a plurality of signals. One or more noise signals associated with microphone self-noise may be received. One or more self-noise-based augmentations may be performed on the plurality of signals based upon, at least in part, the one or more noise signals associated with microphone self-noise, thus defining one or more self-noise-based augmented signals.

公开(公告)号：US20230388704A1

公开(公告)日：2023-11-30

申请号：US18202240

申请日：2023-05-25

申请人： ELNO

发明人： Arthur Henri LACROIX ,  Clément Jean-Baptiste ALBERT ,  Mathieu Clément Nicolas DEXHEIMER ,  Thierry Pierre François GAIFFE

IPC分类号： H04R3/00 ,  H04R1/46 ,  G10L25/78

CPC分类号： H04R3/005 ,  H04R1/46 ,  G10L25/78 ,  H04R2460/13

摘要： The electronic processing device for an acoustic apparatus including a first air conduction microphone and a second bone conduction microphone, configured for being connected to the first and second microphones, for receiving as inputs the first and respectively second analog signals from the first, and respectively second microphones and for delivering as output a corrected signal.
The processing device comprises:



a hybridization module configured for calculating a hybrid signal from the first and second analog signals;
an estimation module configured for estimating noise in the hybrid signal;
a noise reduction module configured for calculating the corrected signal by applying a generalized spectral subtraction algorithm to the hybrid signal and according to the estimated noise.

公开(公告)号：US11830495B2

公开(公告)日：2023-11-28

申请号：US18151619

申请日：2023-01-09

申请人： Sonos, Inc.

发明人： Connor Kristopher Smith ,  Charles Conor Sleith ,  Kurt Thomas Soto

IPC分类号： G10L15/30 ,  G10L15/22 ,  G10L15/08 ,  H04L67/12 ,  G10L25/78 ,  G10L15/04

CPC分类号： G10L15/22 ,  G10L15/08 ,  G10L15/30 ,  G10L15/04 ,  G10L15/083 ,  G10L25/78 ,  G10L2015/088 ,  G10L2015/223 ,  H04L67/12

摘要： In one aspect, a playback deice is configured to identify in an audio stream, via a second wake-word engine, a false wake word for a first wake-word engine that is configured to receive as input sound data based on sound detected by a microphone. The first and second wake-word engines are configured according to different sensitivity levels for false positives of a particular wake word. Based on identifying the false wake word, the playback device is configured to (i) deactivate the first wake-word engine and (ii) cause at least one network microphone device to deactivate a wake-word engine for a particular amount of time. While the first wake-word engine is deactivated, the playback device is configured to cause at least one speaker to output audio based on the audio stream. After a predetermined amount of time has elapsed, the playback device is configured to reactivate the first wake-word engine.

公开(公告)号：US20230368790A1

公开(公告)日：2023-11-16

申请号：US18226524

申请日：2023-07-26

申请人： Samsung Electronics Co., Ltd.

发明人： Changkyu AHN ,  Minkyong KIM ,  Miyoung YOO ,  Hyoungjin LEE

IPC分类号： G10L15/22 ,  H04L12/28 ,  G10L25/87 ,  G10L25/93 ,  G10L25/78

CPC分类号： G10L15/22 ,  H04L12/2803 ,  H04L12/282 ,  G10L2015/223 ,  G10L2015/226 ,  G10L2015/228 ,  G10L25/78 ,  G10L25/87 ,  G10L25/93 ,  H04L12/2816 ,  H04L12/2823 ,  H04L12/2829

摘要： A home appliance is provided. The home appliance includes a sensor, a microphone, a speaker, and a processor. The processor is configured to, based on one of a first event wherein a user action is detected through the sensor or a second event wherein a trigger command for initiating a voice recognition mode is input through the microphone occurring, operate in the voice recognition mode, and control the speaker to output an audio signal corresponding to the event occurred, and the audio signal is an audio signal set differently for each of the first event and the second event.

公开(公告)号：US11817117B2

公开(公告)日：2023-11-14

申请号：US17162907

申请日：2021-01-29

申请人： NVIDIA Corporation

发明人： Utkarsh Vaidya ,  Ravindra Yeshwant Lokhande ,  Viraj Gangadhar Karandikar ,  Niranjan Rajendra Wartikar ,  Sumit Kumar Bhattacharya

IPC分类号： G10L25/78 ,  G10L25/30 ,  G06N3/02

CPC分类号： G10L25/78 ,  G06N3/02 ,  G10L25/30 ,  G10L2025/786

摘要： In various examples, end of speech (EOS) for an audio signal is determined based at least in part on a rate of speech for a speaker. For a segment of the audio signal, EOS is indicated based at least in part on an EOS threshold determined based at least in part on the rate of speech for the speaker.

公开(公告)号：US20230360652A1

公开(公告)日：2023-11-09

申请号：US18214336

申请日：2023-06-26

申请人： SAS INSTITUTE INC.

发明人： Xiaolong Li ,  Xiaozhuo Cheng ,  Xu Yang

IPC分类号： G10L15/26 ,  G10L25/30 ,  G10L15/04 ,  G10L15/02 ,  G10L25/78

CPC分类号： G10L15/26 ,  G10L25/30 ,  G10L15/04 ,  G10L15/02 ,  G10L25/78 ,  G10L2025/783

摘要： A system, method, and computer-program product includes constructing a transcript correction training data corpus that includes a plurality of labeled audio transcription training data samples, wherein each of the plurality of labeled audio transcription training data samples includes: an incorrect audio transcription of a target piece of audio data; a correct audio transcription of the target piece of audio data; and a transcript correction identifier that, when applied to a model input that includes a likely incorrect audio transcript, defines a text-to-text transformation objective causing an audio transcript correction machine learning model to predict a corrected audio transcript based on the likely incorrect audio transcript; configuring the audio transcript correction machine learning model based on a training of a machine learning text-to-text transformer model using the transcript correction training data corpus; and executing the audio transcript correction machine learning model within a speech-to-text post-processing sequence of a speech-to-text service.

公开(公告)号：US20230352037A1

公开(公告)日：2023-11-02

申请号：US17918822

申请日：2021-04-19

申请人： Indian Motorcycle International, LLC

发明人： Steven B. Elgee ,  Jonathan G. Enz

IPC分类号： G10L21/0208 ,  B62J45/10 ,  H04R1/32 ,  G10L25/78

CPC分类号： G10L21/0208 ,  B62J45/10 ,  G10L25/78 ,  H04R1/326 ,  G10L2021/02166

摘要： Systems and methods for voice reception and detection related to a communication system are disclosed.

公开(公告)号：US20230352035A1

公开(公告)日：2023-11-02

申请号：US18344445

申请日：2023-06-29

申请人： Huawei Technologies Co., Ltd.

发明人： Zhe Wang

IPC分类号： G10L19/22 ,  G10L19/012 ,  G10L19/02 ,  G10L19/26 ,  G10L25/78 ,  G10L25/21

CPC分类号： G10L19/012 ,  G10L19/0204 ,  G10L19/22 ,  G10L19/265 ,  G10L25/21 ,  G10L25/78 ,  G10L19/18

摘要： A method for processing an audio signal includes receiving a bitstream corresponding to the audio signal; obtaining a silence insertion descriptor (SID) type of a current frame of the audio signal by decoding the bitstream; obtaining a low-band parameter of the current frame by decoding the bitstream; obtaining a low-band signal of the current frame based on the low-band parameter; obtaining, based on the SID type of the current frame, a high-band parameter of the current frame; obtaining a high-band signal of the current frame based on the high-band parameter; and obtaining a synthesis signal of the current frame based on the low-band signal and the high-band signal.

公开(公告)号：US11803984B2

公开(公告)日：2023-10-31

申请号：US17310571

申请日：2020-06-04

申请人： PLANTRONICS, INC.

发明人： Yongkang Fan ,  Hai Xu ,  Wenxue He ,  Hailin Song ,  Tianran Wang ,  Xi Lu

IPC分类号： G06T7/70 ,  G10L25/78 ,  H04L65/403

CPC分类号： G06T7/70 ,  G10L25/78 ,  G06T2207/10016 ,  G06T2207/30201 ,  H04L65/403

摘要： A method (1000) for operating cameras (202) in a cascaded network (100), comprising: capturing a first view (1200) with a first lens (326) having a first focal point (328) and a first centroid (352), the first view (1200) depicting a subject (1106); capturing a second view (1202) with a second lens (326) having a second focal point (328) and a second centroid (352); detecting a first location of the subject (1106), relative the first lens (326), wherein detecting the first location of the subject (1106), relative the first lens (326), is based on audio captured by a plurality of microphones (204); estimating a second location of the subject (1106), relative the second lens (326), based on the first location of the subject (1106) relative the first lens (326); selecting a portion (1206) of the second view (1202) as depicting the subject (1106) based on the estimate of the second location of the subject (1106) relative the second lens (326).