公开(公告)号：US09990936B2

公开(公告)日：2018-06-05

申请号：US15517953

申请日：2015-10-12

Applicant: THOMSON LICENSING

Inventor： Alexey Ozerov ,  Quang Khanh Ngoc Duong ,  Louis Chevallier

IPC: G10L21/028

CPC classification number: G10L21/028

Abstract: A method and an apparatus for separating speech data from background data in an audio communication are suggested. The method comprises: applying a speech model to the audio communication for separating the speech data from the background data of the audio communication; and updating the speech model as a function of the speech data and the background data during the audio communication.

公开(公告)号：US10021395B2

公开(公告)日：2018-07-10

申请号：US14953124

申请日：2015-11-27

Applicant: THOMSON LICENSING

Inventor： Alexey Ozerov ,  Jean-Ronan Vigouroux ,  Frederic Lefebvre

IPC: G06K9/46 ,  H04N19/136 ,  H04N19/94 ,  H04N19/124 ,  H04N19/184 ,  H04N19/44 ,  H04N19/50 ,  H04N19/91

CPC classification number: H04N19/136 ,  H04N19/124 ,  H04N19/184 ,  H04N19/44 ,  H04N19/50 ,  H04N19/91 ,  H04N19/94

Abstract: A particular implementation determines parameters of a generative probabilistic model from visual descriptors extracted from at least one image. The extracted visual descriptors are quantized and encoded using the model-based arithmetic encoding to be stored or for transmission to a decoder. The model parameters are also stored to be available to a decoder, or transmitted directly to a decoder. A decoder uses the stored, or received, model parameters to reconstruct the generative probabilistic model and then to decode the visual descriptors. The visual descriptors are used for image analysis tasks, such as image retrieval or object detection. A particular implementation uses a Gaussian mixture model as a generative probabilistic model.

公开(公告)号：US20170180903A1

公开(公告)日：2017-06-22

申请号：US15366470

申请日：2016-12-01

Applicant: THOMSON LICENSING

Inventor： Alexey Ozerov ,  Marie Guegan ,  Quang Khanh Ngoc Duong

IPC: H04S3/02 ,  G10L19/008 ,  G10L25/21

CPC classification number: H04S3/02 ,  G10L19/008 ,  G10L21/00 ,  G10L21/02 ,  G10L25/21 ,  H04S2400/03 ,  H04S2420/07

Abstract: A method and apparatus for processing audio content is described. The method and apparatus include receiving (510) audio content, the audio content including an input audio signal, a first reference audio signal, and a second reference audio signal, determining (550) a processing function for the input audio signal, the processing function determined based on a cost function between the input audio signal, the first reference audio signal and a second reference audio signal, and processing (560) the input audio signal using the determined processing function in order to produce an output audio signal.

公开(公告)号：US20150332729A1

公开(公告)日：2015-11-19

申请号：US14713117

申请日：2015-05-15

Applicant: Thomson Licensing

Inventor： Philippe Schmouker ,  Louis Chevalier ,  Alexey Ozerov

IPC: G11B27/022 ,  H04N21/81 ,  H04N21/485 ,  H04N5/60 ,  G11B27/34 ,  H04N21/439

CPC classification number: G11B27/022 ,  G11B27/34 ,  H04H20/106 ,  H04H20/26 ,  H04H40/18 ,  H04H60/58 ,  H04H60/65 ,  H04H2201/60 ,  H04N5/607 ,  H04N21/4341 ,  H04N21/439 ,  H04N21/4622 ,  H04N21/4852 ,  H04N21/8106

Abstract: A method and an apparatus for selecting or removing one or more audio component types in an audio source associated with a video source at an electronic device are presented. For example, the present invention allows a user of an electronic device to selectively choose or remove, e.g., speech, music, and/or some other component type of an audio source for a selected video program at a receiver. In another embodiment, the selected audio source may be from another program.

Abstract translation: 提出了一种用于在电子设备处选择或去除与视频源相关联的音频源中的一个或多个音频分量类型的方法和装置。 例如，本发明允许电子设备的用户在接收器处有选择地选择或去除所选择的视频节目的语音，音乐和/或其他组件类型的音频源。 在另一个实施例中，所选择的音频源可以来自另一个程序。

公开(公告)号：US10114891B2

公开(公告)日：2018-10-30

申请号：US14578333

申请日：2014-12-19

Applicant: THOMSON LICENSING

Inventor： Alexey Ozerov ,  Patrick Perez ,  Louis Chevallier ,  Lionel Oisel

IPC: G06F7/00 ,  G06F17/30 ,  G10L21/0272

Abstract: A method and a system of audio retrieval and source separation are described. The method comprises the steps of: receiving a textual query; retrieving a preliminary audio sample from an auxiliary audio database; retrieving a target audio sample from a target audio database; and separating the retrieved target audio sample into a plurality of audio source signals. The corresponding system comprises an input unit, a storing unit and a processing unit to implement the method.

公开(公告)号：US09930466B2

公开(公告)日：2018-03-27

申请号：US15366470

申请日：2016-12-01

Applicant: THOMSON LICENSING

Inventor： Alexey Ozerov ,  Marie Guegan ,  Quang Khanh Ngoc Duong

IPC: H04S3/02 ,  G10L25/21 ,  G10L19/008

CPC classification number: H04S3/02 ,  G10L19/008 ,  G10L21/00 ,  G10L21/02 ,  G10L25/21 ,  H04S2400/03 ,  H04S2420/07

Abstract: A method and apparatus for processing audio content is described. The method and apparatus include receiving (510) audio content, the audio content including an input audio signal, a first reference audio signal, and a second reference audio signal, determining (550) a processing function for the input audio signal, the processing function determined based on a cost function between the input audio signal, the first reference audio signal and a second reference audio signal, and processing (560) the input audio signal using the determined processing function in order to produce an output audio signal.

公开(公告)号：US09734842B2

公开(公告)日：2017-08-15

申请号：US14896382

申请日：2014-06-04

Applicant: THOMSON LICENSING

Inventor： Luc Le Magoarou ,  Alexey Ozerov ,  Quang Khanh Ngoc Duong

IPC: G10L21/028 ,  G10L21/0272 ,  G10L13/10 ,  G10L19/02 ,  G10L19/038 ,  G10L21/0232

CPC classification number: G10L21/028 ,  G10L13/10 ,  G10L19/0212 ,  G10L19/038 ,  G10L21/0232 ,  G10L21/0272

Abstract: Separation of speech and background from an audio mixture by using a speech example, generated from a source associated with a speech component in the audio mixture, to guide the separation process.