-
公开(公告)号：US20210281946A1
公开(公告)日：2021-09-09
申请号：US17327743
申请日：2021-05-23
发明人： Takeo Matsukawa , Jaekwon Yoo
摘要： An audio converter system is provided. The system comprises an audio input configured to receive a source audio, an audio output configured to couple to a hybrid speaker comprising at least two nondirectional speakers and a directional speaker, and a processor configured to generate an output audio for the hybrid speaker based on the source audio by: identifying a specific sound in the source audio, isolating the specific sound from the source audio, generating a directional speaker output for the directional speaker of the hybrid speaker based on the specific sound, and generating at least two channels of nondirectional speaker output for the at least two nondirectional speakers of the hybrid speaker.
-
公开(公告)号：US20210065731A1
公开(公告)日：2021-03-04
申请号：US16556215
申请日：2019-08-29
发明人： Takeo Matsukawa , Jaekwon Yoo
IPC分类号： G10L21/0232 , H04R1/32 , G10K11/178 , G06N20/00
摘要： A method includes receiving a signal that includes noise, generating a reference signal that comprises an estimate of the noise included in the received signal, and using the reference signal to remove at least part of the noise from the received signal. The reference signal is generated by a model built using machine learning. A system includes a first apparatus that carries a signal that includes noise, and a processor based apparatus configured to execute steps including receiving the signal that includes the noise, generating a reference signal that comprises an estimate of the noise included in the received signal, and using the reference signal to remove at least part of the noise from the received signal. A storage medium storing one or more computer programs is also provided.
-
3.发明公开公开(公告)号：US20240338552A1
公开(公告)日：2024-10-10
申请号：US18296926
申请日：2023-04-06
发明人： Ruxin Chen , Min-Hung Chen , Jaekwon Yoo , Xiaoyu Liu
摘要： A domain adaptation module is used to optimize a first domain derived from a second domain using respective outputs from respective parallel hidden layers of the domains.
-
公开(公告)号：US11832071B2
公开(公告)日：2023-11-28
申请号：US17327743
申请日：2021-05-23
发明人： Takeo Matsukawa , Jaekwon Yoo
摘要： An audio converter system is provided. The system comprises an audio input configured to receive a source audio, an audio output configured to couple to a hybrid speaker comprising at least two nondirectional speakers and a directional speaker, and a processor configured to generate an output audio for the hybrid speaker based on the source audio by: identifying a specific sound in the source audio, isolating the specific sound from the source audio, generating a directional speaker output for the directional speaker of the hybrid speaker based on the specific sound, and generating at least two channels of nondirectional speaker output for the at least two nondirectional speakers of the hybrid speaker.
-
公开(公告)号：US11568265B2
公开(公告)日：2023-01-31
申请号：US15684830
申请日：2017-08-23
摘要： An autonomous personal companion executing a method including capturing data related to user behavior. Patterns of user behavior are identified in the data and classified using predefined patterns associated with corresponding predefined tags to generate a collected set of one or more tags. The collected set is compared to sets of predefined tags of a plurality of scenarios, each to one or more predefined patterns of user behavior and a corresponding set of predefined tags. A weight is assigned to each of the sets of predefined tags, wherein each weight defines a corresponding match quality between the collected set of tags and a corresponding set of predefined tags. The sets of predefined tags are sorted by weight in descending order. A matched scenario is selected for the collected set of tags that is associated with a matched set of predefined tags having a corresponding weight having the highest match quality.
-
公开(公告)号：US20190065960A1
公开(公告)日：2019-02-28
申请号：US15684830
申请日：2017-08-23
IPC分类号： G06N3/08
摘要： An autonomous personal companion executing a method including capturing data related to user behavior. Patterns of user behavior are identified in the data and classified using predefined patterns associated with corresponding predefined tags to generate a collected set of one or more tags. The collected set is compared to sets of predefined tags of a plurality of scenarios, each to one or more predefined patterns of user behavior and a corresponding set of predefined tags. A weight is assigned to each of the sets of predefined tags, wherein each weight defines a corresponding match quality between the collected set of tags and a corresponding set of predefined tags. The sets of predefined tags are sorted by weight in descending order. A matched scenario is selected for the collected set of tags that is associated with a matched set of predefined tags having a corresponding weight having the highest match quality.
-
公开(公告)号：US20230325663A1
公开(公告)日：2023-10-12
申请号：US18145967
申请日：2022-12-23
发明人： Ruxin Chen , Min-Hung Chen , Jaekwon Yoo , Xiaoyu Liu
摘要： A domain adaptation module is used to optimize a first domain derived from a second domain using respective outputs from respective parallel hidden layers of the domains.
-
公开(公告)号：US20220067385A1
公开(公告)日：2022-03-03
申请号：US17412134
申请日：2021-08-25
发明人： Lakshmish Kaushik , Saket Kumar , Jaekwon Yoo , Kevin Zhang , Soheil Khorram , Sharath Rao , Ravi Sundaram
摘要： Video and audio from a computer simulation are processed by a machine learning engine to identify candidate segments of the simulation for use in a video summary of the simulation. Text input is then used to reinforce whether a candidate segment should be included in the video summary. Metadata can be added to the summary showing game summary information.
-
公开(公告)号：US11026021B2
公开(公告)日：2021-06-01
申请号：US16279896
申请日：2019-02-19
发明人： Takeo Matsukawa , Jaekwon Yoo
摘要： An audio converter system is provided. The system comprises an audio input configured to receive a source audio, an audio output configured to couple to a hybrid speaker comprising at least two nondirectional speakers and a directional speaker, and a processor configured to generate an output audio for the hybrid speaker based on the source audio by: identifying a specific sound in the source audio, isolating the specific sound from the source audio, generating a directional speaker output for the directional speaker of the hybrid speaker based on the specific sound, and generating at least two channels of nondirectional speaker output for the at least two nondirectional speakers of the hybrid speaker.
-
10.发明授权公开(公告)号：US11640519B2
公开(公告)日：2023-05-02
申请号：US16176949
申请日：2018-10-31
发明人： Ruxin Chen , Min-Hung Chen , Jaekwon Yoo , Xiaoyu Liu
摘要： A domain adaptation module is used to optimize a first domain derived from a second domain using respective outputs from respective parallel hidden layers of the domains.
-
-
-
-
-
-
-
-
-
搜索结果
14 条记录 (耗时 0.018 秒)
