-
公开(公告)号：US11468892B2
公开(公告)日：2022-10-11
申请号：US17004474
申请日：2020-08-27
发明人： Hyeontaek Lim , Sejin Kwak , Youngjin Kim
IPC分类号： G10L15/22 , G10L13/00 , G10L15/183 , G10L21/0232 , G10L15/18 , G10L15/24 , G06F3/16 , G06V20/10 , G06V40/10 , G10L15/08
摘要： An electronic apparatus and a control method thereof are provided. The electronic apparatus includes a microphone, a camera, a memory storing an instruction, and a processor configured to control the electronic apparatus coupled with the microphone, the camera and the memory, and the processor is configured to, by executing the instruction, obtain a user image by photographing a user through the camera, obtain the user information based on the user image, and based on a user speech being input from the user through the microphone, recognize the user speech by using a speech recognition model corresponding to the user information among a plurality of speech recognition models.
-
公开(公告)号：US11380326B2
公开(公告)日：2022-07-05
申请号：US16875236
申请日：2020-05-15
发明人： Changwoo Han , Minkyu Shin , Jonguk Yoo , Dokyun Lee , Kangseok Choi , Jaewon Lee , Hyeontaek Lim
IPC分类号： G10L15/00 , G10L15/22 , G10L15/02 , G10L19/008 , G10L15/16 , G10L15/08 , G10L21/0208
摘要： A speech recognition method includes receiving a first multi-channel audio signal; obtaining at least one of a speech signal characteristic or a noise signal characteristic for at least one frequency band of frequency bands corresponding to channel audio signals included in the first multi-channel audio signal; generating a signal with an enhanced speech component by performing beamforming on the first multi-channel audio signal based on the speech signal characteristic, a speech signal characteristic obtained for a previous frame that was obtained before a certain time that the first multi-channel audio signal was obtained, and the noise signal characteristic; determining whether the enhanced speech component includes a wake word; and based on determining that the enhanced speech component includes the wake word: activating a speech recognition operation based on the signal with the enhanced speech component.
-
公开(公告)号：US12008988B2
公开(公告)日：2024-06-11
申请号：US17065027
申请日：2020-10-07
发明人： Hyeontaek Lim , Sejin Kwak , Youngjin Kim
摘要： An electronic apparatus and a controlling method thereof are provided. The electronic apparatus includes a microphone, a camera, a memory configured to store at least one command, and at least one processor configured to, based on a first user voice being input from a user, provide a response to the first user voice, based on an audio signal including a voice being input while the response to the first user voice is provided, analyze an image captured by the camera and determine whether there is a second user voice uttered by the user in the audio signal, and based on determining that there is the second user voice uttered by the user in the audio signal, stop providing the response to the first user voice and obtain and provide a response to the second user voice.
-
公开(公告)号：US11769492B2
公开(公告)日：2023-09-26
申请号：US17040746
申请日：2019-03-26
发明人： Changhan Kim , Bowon Kim , Jinsuk Lee , Hyeontaek Lim , Yangwook Kim , Guiwon Seo , Jonghwa Lee
IPC分类号： G10L15/16
CPC分类号： G10L15/16
摘要： The present invention relates to a voice conversation analysis apparatus and a method therefor and, more specifically, to: a voice conversation analysis apparatus categorizing voices generated during a voice conversation so as to predict required functions and further analyzing the voices so as to provide proper functions; and a method therefor. In addition, disclosed are: an artificial intelligence (AI) system for simulating the functions of recognition, decision-making, and the like of the human brain by using a machine learning algorithm; and an application thereof. According to one embodiment, disclosed in an electronic device control method for performing an operation through a suitable operating mode by using an AI learning model so as to analyze a voice conversation, comprising the steps of: receiving a voice and acquiring information on the voice; acquiring category information on the voice on the basis of the information on the voice so as to determine at least one operating mode corresponding to the category information; and performing an operation related to the operating mode by using an AI model corresponding to the determined operating mode.
-
-
-
搜索结果
4 条记录 (耗时 0.019 秒)
