Patents by Inventor Yushu Cao
Yushu Cao has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11322138Abstract: A voice awakening method and device are provided. According to an embodiment, the method includes: receiving voice information of a user; obtaining an awakening confidence level corresponding to the voice information based on the voice information; determining, on the basis of the awakening confidence level, whether the voice information is suspected wake-up voice information; and performing, in response to determining the voice information being the suspected wake-up voice information, a secondary determination on the voice information to obtain a secondary determination result, and determining whether to perform a wake-up operation on the basis of the secondary determination result. The embodiment implements a secondary verification on the voice information, thereby reducing the probability that the smart device is mistakenly awakened.Type: GrantFiled: February 6, 2019Date of Patent: May 3, 2022Assignees: Baidu Online Network Technology (Beijing) Co., Ltd., Shanghai Xiaodu Technology Co., Ltd.Inventors: Jun Li, Rui Yang, Lifeng Zhao, Xiaojian Chen, Yushu Cao
-
Patent number: 11282519Abstract: Embodiments of the present disclosure provide a voice interaction method, device, and a computer readable storage medium. Through a conversion of a terminal device from a near-filed voice interaction mode to a far-filed voice interaction mode, the terminal device is configured to perform the following operations when in the far-filed voice interaction mode: obtaining voice information of a user; obtaining, according to the voice information, target information required by the user from a server; and playing the target information in a voice manner, so that the terminal device can be turned into a smart speaker with a screen in the far-field voice interaction mode, and into a common mobile phone or tablet computer in the near-field voice interaction mode. The terminal device provides the user with a flexible and convenient voice service.Type: GrantFiled: July 11, 2019Date of Patent: March 22, 2022Inventors: Yushu Cao, Qing Si, Qinglong He, Xiangdong Xue
-
Patent number: 11127398Abstract: The embodiment of the disclosure provides a method for voice controlling, a terminal device, a cloud server and a system. The method includes: receiving voice information that the user performs voice controlling on a terminal device; transmitting voice information to the cloud server, so that the cloud server determines, according to the voice information, a voice control and a control instruction that match the voice information in the current interface, and generates a corresponding voice control instruction; receiving the voice control instruction transmitted by the cloud server; and controlling, according to the voice control instruction, a corresponding voice control of the terminal device to perform an operation. The method of the embodiments of the present disclosure achieves controlling over the controls in the interface through the voice, which deepens the controlling degree of the voice over the terminal device, and improves the user experience.Type: GrantFiled: December 28, 2018Date of Patent: September 21, 2021Assignees: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD., SHANGHAI XIAODU TECHNOLOGY CO. LTD.Inventors: Lichao Xu, Yushu Cao, Lishang Xiao, Lifeng Zhao, Xiangdong Xue, Ji Zhou
-
Patent number: 10803861Abstract: Embodiments of the present disclosure disclose a method and apparatus for identifying information. One embodiment of the method includes: collecting to-be-processed audio in real-time; performing voice recognition on the to-be-processed audio; performing data-processing on the to-be-processed audio, when the audio is recognized as a wake-up word, the wake-up word is used for instructing performing data-processing on the to-be-processed audio. The embodiment can identify keywords from the to-be-processed audio obtained in real-time and then perform data-processing on the to-be-processed audio, which improves completeness in obtaining the to-be-processed audio and accuracy in performing data-processing on the to-be-processed audio.Type: GrantFiled: December 28, 2017Date of Patent: October 13, 2020Assignee: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.Inventors: Xiaojian Chen, Lifeng Zhao, Jun Li, Yushu Cao
-
Publication number: 20190333513Abstract: Embodiments of the present disclosure provide a voice interaction method, device, and a computer readable storage medium. Through a conversion of a terminal device from a near-filed voice interaction mode to a far-filed voice interaction mode, the terminal device is configured to perform the following operations when in the far-filed voice interaction mode: obtaining voice information of a user; obtaining, according to the voice information, target information required by the user from a server; and playing the target information in a voice manner, so that the terminal device can be turned into a smart speaker with a screen in the far-field voice interaction mode, and into a common mobile phone or tablet computer in the near-field voice interaction mode. The terminal device provides the user with a flexible and convenient voice service.Type: ApplicationFiled: July 11, 2019Publication date: October 31, 2019Inventors: Yushu CAO, Qing SI, Qinglong HE, Xiangdong XUE
-
Publication number: 20190318736Abstract: The embodiment of the disclosure provides a method for voice controlling, a terminal device, a cloud server and a system. The method includes: receiving voice information that the user performs voice controlling on a terminal device; transmitting voice information to the cloud server, so that the cloud server determines, according to the voice information, a voice control and a control instruction that match the voice information in the current interface, and generates a corresponding voice control instruction; receiving the voice control instruction transmitted by the cloud server; and controlling, according to the voice control instruction, a corresponding voice control of the terminal device to perform an operation. The method of the embodiments of the present disclosure achieves controlling over the controls in the interface through the voice, which deepens the controlling degree of the voice over the terminal device, and improves the user experience.Type: ApplicationFiled: December 28, 2018Publication date: October 17, 2019Inventors: LICHAO XU, YUSHU CAO, LISHANG XIAO, LIFENG ZHAO, XIANGDONG XUE, JI ZHOU
-
Publication number: 20190251963Abstract: A voice awakening method and device are provided. According to an embodiment, the method includes: receiving voice information of a user; obtaining an awakening confidence level corresponding to the voice information based on the voice information; determining, on the basis of the awakening confidence level, whether the voice information is suspected wake-up voice information; and performing, in response to determining the voice information being the suspected wake-up voice information, a secondary determination on the voice information to obtain a secondary determination result, and determining whether to perform a wake-up operation on the basis of the secondary determination result. The embodiment implements a secondary verification on the voice information, thereby reducing the probability that the smart device is mistakenly awakened.Type: ApplicationFiled: February 6, 2019Publication date: August 15, 2019Inventors: Jun Li, Rui Yang, Lifeng Zhao, Xiaojian Chen, Yushu Cao
-
Publication number: 20190147860Abstract: Embodiments of the present disclosure disclose a method and apparatus for identifying information. One embodiment of the method includes: collecting to-be-processed audio in real-time; performing voice recognition on the to-be-processed audio; performing data-processing on the to-be-processed audio, when the audio is recognized as a wake-up word, the wake-up word is used for instructing performing data-processing on the to-be-processed audio. The embodiment can identify keywords from the to-be-processed audio obtained in real-time and then perform data-processing on the to-be-processed audio, which improves completeness in obtaining the to-be-processed audio and accuracy in performing data-processing on the to-be-processed audio.Type: ApplicationFiled: December 28, 2017Publication date: May 16, 2019Inventors: Xiaojian CHEN, Lifeng ZHAO, Jun LI, Yushu CAO
-
Patent number: 10275426Abstract: Systems, methods, and computer-readable media are disclosed for dynamic kerning pair reduction for digital font rendering. Example methods may include receiving a first font file comprising glyph data and a first set of kerning pairs, determining a first kerning pair of the first set of kerning pairs that comprises a kerning adjustment value below a kerning adjustment threshold, removing the first kerning pair from the first set of kerning pairs to generate a second set of kerning pairs, and generating a second font file comprising the glyph data and the second set of kerning pairs.Type: GrantFiled: September 22, 2015Date of Patent: April 30, 2019Assignee: Amazon Technologies, Inc.Inventors: Yushu Cao, Sivarangini Ragavan, Michael Patrick Bacus
-
Patent number: 9620086Abstract: Systems, methods, and computer-readable media are disclosed for dynamic contrast adjustment for glyph rendering. Example methods may include rendering a first glyph associated with a font in a first font size, increasing a first contrast of the first glyph in the first font size by adjusting a first grayscale value associated with the first glyph in the first font size to generate an adjusted first grayscale value, and storing the adjusted first grayscale value in a grayscale mapping table associated with the font, the grayscale mapping table comprising a default grayscale value for the first glyph in a second font size. Example methods may include generating a font file comprising the first glyph and the grayscale mapping table.Type: GrantFiled: June 26, 2015Date of Patent: April 11, 2017Assignee: Amazon Technologies, Inc.Inventors: Lokesh Joshi, Yushu Cao, Hao Hu