白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Computerized intelligent assistant for conferences

專利號
US10867610B2
公開日期
2020-12-15
申請人
Microsoft Technology Licensing, LLC(US WA Redmond)
發(fā)明人
Adi Diamant; Karen Master Ben-Dor; Eyal Krupka; Raz Halaly; Yoni Smolin; Ilya Gurvich; Aviv Hurvitz; Lijuan Qin; Wei Xiong; Shixiong Zhang; Lingfeng Wu; Xiong Xiao; Ido Leichter; Moshe David; Xuedong Huang; Amit Kumar Agarwal
IPC分類
H04N7/14; G10L15/26; H04N7/15; G06K9/00; G10L17/00
技術(shù)領(lǐng)域
conference,transcript,assistant,or,may,in,speech,machine,e.g,remote
地域: WA WA Redmond

摘要

A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.

說明書

At 204, determining participant identities includes determining a pre-registered signature for each participant, where such pre-registered signature may be useable to computer-recognize an identity of the participant (e.g., based on audiovisual data captured by computerized intelligent assistant 1300). For example, such signature for a conference participant may include a computer-readable representation of one or more exemplary audiovisual data, e.g., face photos, voice audio samples, and/or biometric data (e.g., fingerprint data). In some examples, the computer-readable representation may include the one or more exemplary audiovisual data directly (e.g., a face photo). In some examples, the computer-readable representation may include one or more identified features associated with the exemplary audiovisual data (e.g., visual markers indicating a shape and/or position of a facial feature). In some examples, a pre-registered signature for a conference participant may include an associated companion device (e.g., a MAC address of a mobile phone). In some examples, a signature for a conference participant may include an associated user account (e.g., an account in a meeting program running on a mobile phone communicatively coupled to backend server 1320 and/or computerized intelligent assistant 1300). In some examples, a pre-registered signature may be available for only a subset of conference participants, or a pre-registered signature may not be available for any conference participants. In some examples, the computerized intelligent assistant 1300 may include an identity machine configured to determine participant identities for a plurality of conference participants including a set of remote participants and a set of local participants. Determining a participant identity for a participant of the plurality of conference participants may include recognizing a pre-registered signature for the participant, wherein the pre-registered signature is useable to computer-recognize an identity of the participant. In some examples, one or more local and/or remote conference participants may be recognized by a face identification machine based on digital video received from a local and/or remote computing device (e.g., a companion device of a conference participant), for example, by operating the face identification machine to recognize one or more faces of one or more remote conference participants featured in a digital video captured by a remote companion device of the remote conference participant.

權(quán)利要求

1
微信群二維碼
意見反饋