公开(公告)号：US20240312454A1

公开(公告)日：2024-09-19

申请号：US18674519

申请日：2024-05-24

申请人： Amazon Technologies, Inc.

发明人： Ty Loren Carlson ,  Rohan Mutagi

IPC分类号： G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L17/00 ,  G10L21/0208 ,  G10L21/0272 ,  G10L25/78 ,  G10L25/84

CPC分类号： G10L15/20 ,  G10L15/22 ,  G10L15/26 ,  G10L17/00 ,  G10L21/0208 ,  G10L21/0272 ,  G10L25/84 ,  G10L2015/223 ,  G10L2021/02087 ,  G10L2025/783

摘要： A system has multiple audio-enabled devices that communicate with one another over an open microphone mode of communication. When a user says a trigger word, the nearest device validates the trigger word and opens a communication channel with another device. As the user talks, the device receives the speech and generates an audio signal representation that includes the user speech and may additionally include other background or interfering sound from the environment. The device transmits the audio signal to the other device as part of a conversation, while continually analyzing the audio signal to detect when the user stops talking. This analysis may include watching for a lack of speech in the audio signal for a period of time, or an abrupt change in context of the speech (indicating the speech is from another source), or canceling noise or other interfering sound to isolate whether the user is still speaking. Once the device confirms that the user has stopped talking, the device transitions from a transmission mode to a reception mode to await a reply in the conversation.

公开(公告)号：US12051422B2

公开(公告)日：2024-07-30

申请号：US17473645

申请日：2021-09-13

申请人： Microsoft Technology Licensing, LLC

发明人： Takuya Yoshioka ,  Andreas Stolcke ,  Zhuo Chen ,  Dimitrios Basile Dimitriadis ,  Nanshan Zeng ,  Lijuan Qin ,  William Isaac Hinthorn ,  Xuedong Huang

IPC分类号： G10L21/0272 ,  G10L15/16 ,  G10L15/30 ,  G10L21/0208 ,  G10L25/30

CPC分类号： G10L15/30 ,  G10L15/16 ,  G10L21/0208 ,  G10L21/0272 ,  G10L2021/02087

摘要： A computer implemented method includes receiving audio signals representative of speech via multiple audio streams transmitted from corresponding multiple distributed devices, performing, via a neural network model, continuous speech separation for one or more of the received audio signals having overlapped speech, and providing the separated speech on a fixed number of separate output audio channels.

公开(公告)号：US12027162B2

公开(公告)日：2024-07-02

申请号：US17190779

申请日：2021-03-03

申请人： GOOGLE LLC

发明人： Hyun Jin Park ,  Pai Zhu ,  Ignacio Lopez Moreno ,  Niranjan Subrahmanya

IPC分类号： G10L15/22 ,  G06F18/24 ,  G10L15/06 ,  G10L15/08 ,  G10L21/0208

CPC分类号： G10L15/22 ,  G06F18/24 ,  G10L15/063 ,  G10L15/08 ,  G10L21/0208 ,  G10L2015/088 ,  G10L2015/223 ,  G10L2021/02082 ,  G10L2021/02087

摘要： Teacher-student learning can be used to train a keyword spotting (KWS) model using augmented training instance(s). Various implementations include aggressively augmenting (e.g., using spectral augmentation) base audio data to generate augmented audio data, where one or more portions of the base instance of audio data can be masked in the augmented instance of audio data (e.g., one or more time frames can be masked, one or more frequencies can be masked, etc.). Many implementations include processing augmented audio data using a KWS teacher model to generate a soft label, and processing the augmented audio data using a KWS student model to generate predicted output. One or more portions of the KWS student model can be updated based on a comparison of the soft label and the generated predicted output.

公开(公告)号：US11954252B2

公开(公告)日：2024-04-09

申请号：US17169315

申请日：2021-02-05

申请人： Aptiv Technologies AG

发明人： Marcin Szelest ,  Pawel Skruch

IPC分类号： G06F3/01 ,  A41D19/00 ,  G01H1/00 ,  G09B5/06 ,  G10L21/0208 ,  G10L25/30 ,  H01R13/64

CPC分类号： G06F3/014 ,  A41D19/0027 ,  G01H1/00 ,  G09B5/065 ,  G10L21/0208 ,  G10L25/30 ,  H01R13/64 ,  G10L2021/02087

摘要： A device for verifying the connection of components by a gripper, wherein connecting two or more components produces a connection sound. The device comprises a plurality of audio sensors, a fastener for securing the plurality of audio sensors at different positions on the gripper, and a controller. The controller comprises an input for receiving the audio signals from the plurality of audio sensors, a neural network for isolating the connection sound from the audio signals received from the plurality of audio sensors using independent component analysis based on training audio data obtained from audio signals received during a plurality of training connections made in a controlled environment; and an output for indicating a desired connection status based on the isolated connection sound.

公开(公告)号：US11875813B2

公开(公告)日：2024-01-16

申请号：US18129469

申请日：2023-03-31

申请人： The Trustees of Columbia University in the City of New York

发明人： Nima Mesgarani ,  Enea Ceolini ,  Cong Han

IPC分类号： G10L21/028 ,  G10L21/0232 ,  G10L21/0208

CPC分类号： G10L21/028 ,  G10L21/0232 ,  G10L2021/02087

摘要： Disclosed are methods, systems, device, and other implementations, including a method (performed by, for example, a hearing aid device) that includes obtaining a combined sound signal for signals combined from multiple sound sources in an area in which a person is located, and obtaining neural signals for the person, with the neural signals being indicative of one or more target sound sources, from the multiple sound sources, the person is attentive to. The method further includes determining a separation filter based, at least in part, on the neural signals obtained for the person, and applying the separation filter to a representation of the combined sound signal to derive a resultant separated signal representation associated with sound from the one or more target sound sources the person is attentive to.

公开(公告)号：US11875812B2

公开(公告)日：2024-01-16

申请号：US17869248

申请日：2022-07-20

申请人： STARKEY LABORATORIES, INC.

发明人： Ritwik Giri ,  Karim Helwani ,  Tao Zhang

IPC分类号： G10L21/0216 ,  G10L17/02 ,  H04R25/00 ,  G10L21/0208 ,  H04R1/10 ,  H04R3/00 ,  H04R5/04 ,  H04R5/033

CPC分类号： G10L21/0216 ,  G10L17/02 ,  G10L21/0208 ,  H04R1/1083 ,  H04R3/002 ,  H04R5/04 ,  H04R25/505 ,  G10L2021/02087 ,  G10L2021/02163 ,  H04R5/033 ,  H04R2460/01

摘要： A system comprises an ear-worn electronic device configured to be worn by a wearer. The ear-worn electronic device comprises a processor and memory coupled to the processor. The memory is configured to store an annoying sound dictionary representative of a plurality of annoying sounds pre-identified by the wearer. A microphone is coupled to the processor and configured to monitor an acoustic environment of the wearer. A speaker or a receiver is coupled to the processor. The processor is configured to identify different background noises present in the acoustic environment, determine which of the background noises correspond to one or more of the plurality of annoying sounds, and attenuate the one or more annoying sounds in an output signal provided to the speaker or receiver.

公开(公告)号：US11804236B2

公开(公告)日：2023-10-31

申请号：US17361445

申请日：2021-06-29

申请人： APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECHNOLOGY CO., LTD.

发明人： Tengfei Zhang

IPC分类号： G10L21/034 ,  G10L21/0208 ,  G10L21/0232 ,  G06F11/30 ,  G06F11/36

CPC分类号： G10L21/0232 ,  G06F11/3075 ,  G06F11/3656 ,  G10L21/034 ,  G10L2021/02087

摘要： The application discloses a debugging method for a noise elimination algorithm, an apparatus and an electronic device, which relate to the technical fields of voice, automatic driving and intelligent transportation. An implementation scheme is: when the noise elimination algorithm is debugged, acquiring multiple voice control signals from a vehicle to be debugged, modifying a weight of a configuration parameter of the noise elimination algorithm in a digital signal processing to obtain an updated noise elimination algorithm; then adopting the updated noise elimination algorithm to perform noise elimination processing on the multiple voice control signals; if control results of noise-eliminated voice control signals on the vehicle to be debugged do not meet a preset condition, continuing to modify the weight of the configuration parameter until the preset condition is met, and then sending a noise elimination algorithm that meets the preset condition to the vehicle to be debugged.

公开(公告)号：US20230267942A1

公开(公告)日：2023-08-24

申请号：US17601042

申请日：2020-10-01

申请人： Google LLC

发明人： Anatoly Efros ,  Noam Etzion-Rosenberg ,  Tal Remez ,  Oran Lang ,  Inbar Mosseri ,  Israel Or Weinstein ,  Benjamin Schlesinger ,  Michael Rubinstein ,  Ariel Ephrat ,  Yukun Zhu ,  Stella Laurenzo ,  Amit Pitaru ,  Yossi Matias

IPC分类号： G10L21/0208 ,  G10L25/57

CPC分类号： G10L21/0208 ,  G10L25/57 ,  G10L2021/02087

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio-visual speech separation. A method includes: receiving, by a user device, a first indication of one or more first speakers visible in a current view recorded by a camera of the user device, in response, generating a respective isolated speech signal for each of the one or more first speakers that isolates speech of the first speaker in the current view and sending the isolated speech signals for each of the one or more first speakers to a listening device operatively coupled to the user device, receiving, by the user device, a second indication of one or more second speakers visible in the current view recorded by the camera of the user device, and in response generating and sending a respective isolated speech signal for each of the one or more second speakers to the listening device.

公开(公告)号：US20230178090A1

公开(公告)日：2023-06-08

申请号：US18075843

申请日：2022-12-06

申请人： Nokia Technologies Oy

发明人： Lasse Juhani Laaksonen ,  Miikka Tapani VILERMO ,  Arto Juhani LEHTINIEMI

IPC分类号： G10L21/0208 ,  G10L25/84 ,  H04L65/403

CPC分类号： G10L21/0208 ,  G10L25/84 ,  H04L65/403 ,  G10L2021/02087

摘要： An apparatus including circuitry configured to: enable a conversational service between a first user of the apparatus and a second user of a remote apparatus wherein the conversational service is a duplex service including simultaneous voice communication from the first user to the second user and voice communication from the second user to the first user; and enable synchronization of a switch to using an active noise cancellation mode at the apparatus for the conversational service and at the remote apparatus for the conversational service, wherein the switch to using the noise cancellation mode is synchronized between the first and second users.

公开(公告)号：US20190251983A1

公开(公告)日：2019-08-15

申请号：US16026078

申请日：2018-07-03

申请人： Merry Electronics(Shenzhen) Co., Ltd.

发明人： Hung-Chi Lin ,  Mao-Hung Lin ,  Syue-Yu Jhang ,  Yi-Lin Hsieh

IPC分类号： G10L21/0208 ,  H04R1/22 ,  H04R3/00

CPC分类号： G10L21/0208 ,  G10L2021/02087 ,  G10L2021/02166 ,  H04R1/222 ,  H04R3/005

摘要： An audio processing apparatus and an audio processing method are provided. The audio processing apparatus includes a microphone array, a processor, and an audio signal processor. The microphone array is configured to provide an external audio signal having a first sampling frequency. The external audio signal includes a first audio signal and a second audio signal. The processor provides a first setting command and a second setting command according to the external audio signal and the second audio signal. The audio signal processor generates the second audio signal having a second sampling frequency according to the first setting command, adjusts the second sampling frequency of the second audio signal to the first sampling frequency according to the second setting command, and separates the first audio signal in the external audio signal according to the second audio signal having the first sampling frequency.