公开(公告)号：US20200043492A1

公开(公告)日：2020-02-06

申请号：US16598906

申请日：2019-10-10

Applicant: LG ELECTRONICS INC.

Inventor： Ye Jin KIM ,  Ye Kyung KIM ,  Gyeong Hun KIM

IPC: G10L15/22 ,  G10L15/08 ,  G10L15/30

Abstract: Disclosed are a speech recognition apparatus for speech recognition, and a method therefor. A speech recognition method for speech recognition includes detecting an event during a first spoken utterance, transmitting a suspension request signal requesting suspension of signal processing for the first spoken utterance at the point in time when the event is detected, and waiting for recognition of a second spoken utterance. According to the present disclosure, by canceling an erroneously spoken utterance through 5G network service and AI algorithm, a speech recognition process can proceed rapidly.

公开(公告)号：US20190387344A1

公开(公告)日：2019-12-19

申请号：US16551990

申请日：2019-08-27

Applicant: LG Electronics Inc.

Inventor： Ye Jin KIM ,  Byeong Ha KIM ,  Ye Kyung KIM

IPC: H04S7/00 ,  H04R3/12 ,  H04R5/02 ,  H04R5/04 ,  H04S3/00

Abstract: A multi-channel surround audio signal providing method is performed by one or more of an audio device and a mobile terminal in electronic devices including speakers capable of receiving an audio signal in a 5G environment connected for Internet of Things. The method includes searching for electronic devices capable of receiving a multi-channel surround audio signal, designating two or more of the electronic devices as a surround speaker sound channel, transmitting a test audio signal generated to synchronize a level of the sound of the surround speaker sound channel to the electronic devices, receiving a signal of the output feedback audio from a microphone, and adjusting a level of an audio output by the electronic devices, based on the feedback audio signal to synchronize the level of the sound of the surround speaker sound channel. The method operates between an audio device and a wireless speaker by 5G communication.

公开(公告)号：US20210118449A1

公开(公告)日：2021-04-22

申请号：US16704988

申请日：2019-12-05

Applicant: LG ELECTRONICS INC.

Inventor： Ye Jin KIM ,  Hyun YU ,  Byeong Ha KIM

IPC: G10L15/32 ,  G10L15/22

Abstract: Disclosed are a speech processing method and a speech processing apparatus in a 5G communication environment through speech processing by executing embedded artificial intelligence (AI) algorithms and/or machine learning algorithms. The speech processing method includes determining a temporary pause of reception of a first spoken utterance, outputting a first spoken response utterance as a result of speech recognition processing of a second spoken utterance received after the temporary pause, determining, as an extension of the first spoken utterance, a third spoken utterance that is received after outputting the first spoken response utterance, deleting, using a deep neural network model, a duplicate utterance part from a fourth spoken utterance that is obtained by combining the first and the third spoken utterance, and outputting a second spoken response utterance as a result of speech recognition processing of the fourth spoken utterance from which the duplicate utterance part has been deleted.

公开(公告)号：US20210097990A1

公开(公告)日：2021-04-01

申请号：US16698649

申请日：2019-11-27

Applicant: LG ELECTRONICS INC.

Inventor： Ye Jin KIM ,  Hyun YU ,  Byeong Ha KIM

IPC: G10L15/22 ,  G10L15/187 ,  G10L25/78

Abstract: Disclosed are a speech processing method and apparatus therefor which execute an installed artificial intelligence algorithm and/or machine learning algorithm to perform speech processing in a 5G communication environment. The speech processing method may include determining a temporary pause of reception of a first spoken utterance, outputting a first spoken response utterance as a result of speech recognition processing of a second spoken utterance received after the temporary pause, determining, as an extension of the first spoken utterance, a third spoken utterance received after outputting the first spoken response utterance, deleting a duplicate utterance part from a fourth spoken utterance that is obtained by combining the first and the third spoken utterance, when performing speech recognition processing on the fourth spoken utterance, and outputting a second spoken response utterance as a result of speech recognition processing of the fourth spoken utterance from which the duplicate utterance part has been deleted.