-
公开(公告)号：EP3794587B1
公开(公告)日：2024-07-17
申请号：EP18799630.1
申请日：2018-10-17
IPC分类号： G06F21/32 , G06F21/45 , G06F16/332 , G06F16/9032 , G06F3/16 , G06N3/006 , G06N3/08 , G10L15/18 , G10L17/00 , G06N3/045 , G06N7/01 , G10L15/22
CPC分类号： G06F3/167 , G06F16/3329 , G06F21/32 , G10L17/00 , G06F21/45 , G06F2221/211720130101 , G06N3/006 , G06N3/08 , G06N20/00 , G10L15/1822 , G10L2015/22320130101 , G06N3/045 , G06N7/01
-
-
公开(公告)号：EP4375990A2
公开(公告)日：2024-05-29
申请号：EP23208247.9
申请日：2023-11-07
申请人： Sivantos Pte. Ltd.
摘要： Es wird ein Verfahren zum Training einer Sprechererkennungseinheit (2) eines Hörgeräts (4) eines Nutzers (N) beschrieben, wobei das Hörgerät (4) mit einem Kommunikationsgerät (6) des Nutzers (N) verbunden ist, zur Durchführung eines Ferngesprächs zwischen dem Nutzer (B) des Hörgeräts (4) und einem Gesprächspartner (G) des Nutzers (N), wobei ein Audiosignal (A1) des Gesprächspartners (G) von dem Kommunikationsgerät (6) empfangen wird, zur Ausgabe an den Nutzer (N), wobei dem Gesprächspartner (G) eine Sprecher-ID (10) zugeordnet wird, wobei aus dem Audiosignal (A1) eine Anzahl an Sprachsamples (12) des Gesprächspartners (G) extrahiert wird, wobei die Sprachsamples (12) der Sprecher-ID (10) zugeordnet werden und gemeinsam mit dieser einen Trainingsdatensatz (16) bilden, wobei die Sprechererkennungseinheit (2) des Hörgeräts (4) mit dem Trainingsdatensatz (16) trainiert wird, um zukünftig den Gesprächspartner (G) wiederzuerkennen. Weiter werden ein entsprechendes Hörgerät (4) und eine entsprechendes Kommunikationsgerät (6) beschrieben.
-
公开(公告)号：EP4276817A1
公开(公告)日：2023-11-15
申请号：EP21917605.4
申请日：2021-12-03
发明人： DOI, Misaki
摘要： An identification device (10) includes: an obtainer (11) that obtains voice data; an identifier (12) that obtains, through speaker identification processing, a score indicating a degree of similarity between the voice data obtained by the obtainer (11) and voice data on an utterance of a predetermined speaker; and a corrector (13) that corrects the score to reduce the influence of a degradation in identification performance of the speaker identification processing by the identifier (12) on the score and outputs the score corrected, when determining that the voice data obtained by the obtainer (11) has a feature of reducing the influence.
-
5.发明公开
公开(公告)号：EP4246508A3
公开(公告)日：2023-11-15
申请号：EP23170882.7
申请日：2017-12-27
申请人： Rovi Guides, Inc.
摘要： Systems and methods are disclosed herein for identifying users based on voice data and media consumption data. A media guidance application may generate a voice signature from the user's input and based on that signature identify some demographic characteristics of the user (e.g., age, gender, and other suitable characteristics). The media guidance application may retrieve user data for users that are associated with a household of the user and attempt to identify which of the users spoke the command. If multiple users are identified, based on the demographic characteristics, the media guidance application may use the content of the voice command (e.g., a type of media requested) to identify the user.
-
公开(公告)号：EP3627505B1
公开(公告)日：2023-11-15
申请号：EP18196004.8
申请日：2018-09-21
发明人： DEMUYTERE, Pieter , ROSEZ, Didier
-
公开(公告)号：EP4258258A3
公开(公告)日：2023-11-01
申请号：EP23166354.3
申请日：2023-04-03
发明人： BRUNER, Nathan , BIAN, Zimei , LIN, James
IPC分类号： G10L15/26 , G06F40/117 , G10L17/00
摘要： Computing systems, methods, and non-transitory storage media are provided for obtaining an audio stream, converting the audio stream to an intermediate representation, performing diarization on the audio stream, separating the audio stream into individual speech constructs, performing speech recognition on the individual speech constructs by mapping each of the individual speech constructs, or consecutive individual speech constructs, to entries within a dictionary, to generate a transcription of the audio stream, generating an output indicative of the transcription and a result of the diarization, transforming the output into an object-based representation, and performing one or more operations on the object-based representation
-
公开(公告)号：EP3807875B1
公开(公告)日：2023-11-01
申请号：EP18759811.5
申请日：2018-08-09
发明人： ALTHAUS, Jan , SHARIFI, Matthew
-
公开(公告)号：EP4254979A1
公开(公告)日：2023-10-04
申请号：EP21909336.6
申请日：2021-12-20
发明人： ZHANG, Libin , YUAN, Tingqiu , ZHANG, Huimin
摘要： An active noise cancellation method is provided. The method includes: capturing an ambient sound to determine an ambient audio signal; and determining a working status, determining at least one corresponding wanted signal based on the working status, and then removing the at least one wanted signal from the ambient audio signal, to obtain a reference signal, where the wanted signal includes content of interest. If the method is applied to a headset, a to-be-played signal is determined based on the reference signal, and the to-be-played signal is played, so that the reference signal is superimposed with the ambient sound, the at least one wanted signal is retained, and ambient noise is canceled. If the method is applied to a collaboration device, a to-be-played signal is determined based on the reference signal, and the to-be-played signal is sent to the headset. The content of interest is removed from the reference signal, to ensure that when active noise cancellation is performed, the content of interest is still retained in audio data obtained after noise cancellation.
-
公开(公告)号：EP3895161B1
公开(公告)日：2023-07-26
申请号：EP19709271.1
申请日：2019-02-20
-
-
-
-
-
-
-
-
-
搜索结果
852 条记录 (耗时 0.022 秒)
