公开(公告)号：WO2023037201A1

公开(公告)日：2023-03-16

申请号：PCT/IB2022/058014

申请日：2022-08-26

Applicant: TRUDEAU, Nathan

Inventor： TRUDEAU, Nathan

IPC: G06F21/64 ,  G06F21/62 ,  G06Q30/06 ,  G10L19/018 ,  H04N21/8352

Abstract: A method and a system are disclosed for providing a trackable digital asset. The method comprises obtaining a digital asset, embedding data suitable for identifying the digital asset in the digital asset to generate a trackable digital asset, obtaining at least one indication of at least one one-way cryptographic encryption of at least one portion of the trackable digital asset, encrypting, using a password, at least one portion of the trackable digital asset and providing at least one indication of at least the encrypted trackable digital asset. Authenticity of a given digital asset is determined by comparing the obtained at least one indication of the at least one one-way cryptographic encryption of the at least one portion of the trackable digital asset with at least one indication of at least one one-way cryptographic encryption of at least one portion of the given digital asset.

公开(公告)号：WO2023010028A1

公开(公告)日：2023-02-02

申请号：PCT/US2022/074176

申请日：2022-07-27

Applicant: DIGITAL VOICE SYSTEMS, INC.

Inventor： HARDWICK, John C.

IPC: G10L19/018 ,  H04M11/06 ,  H04H20/28

Abstract: Non-voice data is embedded in a voice bit stream that includes frames of voice bits by selecting a frame of voice bits to carry the non-voice data, placing non-voice identifier bits in a first portion of the voice bits in the selected frame, and placing the non-voice data in a second portion of the voice bits in the selected frame. The non-voice identifier bits are employed to reduce a perceived effect of the non-voice data on audible speech produced from the voice bit stream.

公开(公告)号：WO2022269181A1

公开(公告)日：2022-12-29

申请号：PCT/FR2022/051191

申请日：2022-06-20

Applicant: ORANGE

Inventor： FAURE, Julien ,  LETELLIER, Jean Francois ,  LAURENT, Sonia

IPC: H04M3/56 ,  G10L19/018 ,  H04M3/22 ,  H04M3/2236 ,  H04M3/568

Abstract: La présent invention vise un procédé mis en œuvre par un premier terminal client lors d'une conférence audio et/ou vidéo en coopération avec un serveur de conférence gérant des échanges de flux de données audio, le procédé comprenant : obtention d'un flux de données audio marquées par intégration d'un code de marquage numérique; envoi du flux de données audio marquées au serveur de conférence; réception de données de capacité audio représentatives de si un deuxième terminal client a détecté le code de marquage numérique dans un flux de données audio; et déclenchement à partir des données de capacité audio reçues d'au moins une action de gestion de la conférence audio et/ou vidéo, comprenant une restitution d'informations fonction des données de capacité audio reçues.

公开(公告)号：WO2022146674A1

公开(公告)日：2022-07-07

申请号：PCT/US2021/063300

申请日：2021-12-14

Applicant: GRACENOTE, INC.

Inventor： BERRIAN, Alexander ,  HODGES, Tadd ,  COOVER, Robert ,  WILKINSON, Matthew ,  RAFII, Zafar

IPC: G10L19/018 ,  G06F16/683

Abstract: A method implemented by a computing system comprises generating, by the computing system, a fingerprint comprising a plurality of bin samples associated with audio content. Each bin sample is specified within a frame of the fingerprint and is associated with one of a plurality of non-overlapping frequency ranges and a value indicative of a magnitude of energy associated with a corresponding frequency range. The computing system removes. from the fingerprint, a plurality of bin samples associated with a frequency sweep in the andio content.

公开(公告)号：WO2022140111A1

公开(公告)日：2022-06-30

申请号：PCT/US2021/063282

申请日：2021-12-14

Applicant: INFRARED5, INC.

Inventor： LUCCHI, Davide ,  ALLEN, Chris ,  SOLONSKY, Alexander

IPC: H04N21/8358 ,  G10L19/018 ,  H04N21/2187

Abstract: A live media streaming architecture with real-time live watermarking wherein watermarks are added at a frame or subframe level. The architecture can use a UDP/WebRTC architecture, without requiring a content delivery network, which is not dependent on transmitting media by segments, thus allowing insertion of the watermark at a frame or subframe level. By inserting watermarks at a frame or subframe level, latency is minimized for media delivery to under 500 milliseconds (ms) and for extraction to about five to fifteen seconds.

公开(公告)号：WO2021244409A1

公开(公告)日：2021-12-09

申请号：PCT/CN2021/096619

申请日：2021-05-28

Applicant: 北京声连网信息科技有限公司

Inventor： 唐鸿

IPC: G10L19/02 ,  G10L19/018 ,  G10L19/00 ,  G10L19/032

Abstract: 一种声波信息的解码方法及装置，其中，该解码方法包括：从基于子带编码的音频压缩数据流的子带数据中选取与声波信号的音频频率相近的子带数据（S10）；其中，该声波信号是预先叠加在原始音频文件中的标识信号，该原始音频文件通过音频量化处理以生成该音频压缩数据流；将选取的子带数据还原成局部频带的原始数字音频信号流（S11）；其中，局部频带是与声波信号的音频频率相同或保持在一定差异范围内的频带；对原始数字音频信号流进行傅里叶变换处理（S12）；以及对经过傅里叶变换处理的音频信号流进行声波信号的解析，以获得对应的声波信号（S13）。该方法及装置能够显著提高解释型语言对音频量化压缩数据流进行声波解码的运算速度。

公开(公告)号：WO2021067289A1

公开(公告)日：2021-04-08

申请号：PCT/US2020/053301

申请日：2020-09-29

Applicant: THE NIELSEN COMPANY (US), LLC

Inventor： DAVIS, Jeremey M. ,  WRIGHT, David H. ,  TOPCHY, Alexander ,  PONRAJ, Cherisse ,  CURTIS, Chris ,  CHAZEN, Jonathan ,  CREMER, Markus Kurt ,  GUPTA, Sharmishtha ,  SCOTT, Jeffrey

IPC: G10L19/018 ,  G10L19/008 ,  H04N21/8358

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed for affiliate interrupt detection. An example method disclosed herein includes determining whether a first time period of a first audio signal corresponds to a first affiliate interrupt period based on whether (1) a first type of watermark is detected in the first time period of the first audio signal, and (2) a second type of watermark is detected in the first audio signal outside the first time period but not in the first time period of the first audio signal, and determining whether the first time period of the first audio signal corresponds to the first affiliate interrupt period when watermarks are not detected in the first time period of the first audio signal based on comparison of first signatures with second signatures representing a corresponding first time period of a reference audio signal.

公开(公告)号：WO2021061484A1

公开(公告)日：2021-04-01

申请号：PCT/US2020/051234

申请日：2020-09-17

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： CHICOTE, Roberto Barra ,  AGGARWAL, Vatsal ,  BREEN, Andrew Paul ,  HERNANDEZ, Javier Gonzalez ,  PRATEEK, Nishant

IPC: G10L13/033 ,  G06N3/02 ,  G10L13/08 ,  G10L25/30 ,  G10L15/18 ,  G10L21/00 ,  G10L25/48 ,  G10L19/018

Abstract: During text-to-speech processing, a speech model creates synthesized speech that corresponds to input data. The speech model may include an encoder for encoding the input data into a context vector and a decoder for decoding the context vector into spectrogram data. The speech model may further include a voice decoder that receives vocal characteristic data representing a desired vocal characteristic of synthesized speech. The voice decoder may process the vocal characteristic data to determine configuration data, such as weights, for use by the speech decoder.

公开(公告)号：WO2019159679A1

公开(公告)日：2019-08-22

申请号：PCT/JP2019/002872

申请日：2019-01-29

Applicant: ヤマハ株式会社

Inventor： 瀬戸　優樹

IPC: G10L19/018 ,  G06F3/048 ,  G06Q30/02 ,  G10L19/00

Abstract: 端末装置は、放音装置から放音された音響の収音により収音装置が生成した音響信号から放音装置の場所を示す識別情報を抽出する情報抽出部と、識別情報に対応した情報を再生装置に再生させる再生制御部とを具備する。

公开(公告)号：WO2018208997A1

公开(公告)日：2018-11-15

申请号：PCT/US2018/031912

申请日：2018-05-09

Applicant: VERIMATRIX, INC.

Inventor： THORWIRTH, Niels, J.

IPC: G06F21/10 ,  H04L9/32 ,  G06T1/00 ,  G10L19/018

Abstract: Systems and methods for encoding multiple video streams with digital watermarking for adaptive bitrate streaming in accordance with embodiments of the invention are disclosed. In one embodiment, a method for preprocessing multimedia content into streams with watermark information includes receiving a source content media stream, generating at least two variant preprocessed streams for each received source content media stream, where each variant preprocessed stream includes different watermark information in the same locations as the other variant preprocessed streams and where marked locations are spaced apart at least a distance equal to a predetermined maximum segment size, generating a set of embed location information describing marked locations in the variant preprocessed streams, generating at least one variant output stream from each variant preprocessed stream using video compression, partitioning each variant output stream into a set of segments, where each segment is no longer than the predetermined maximum segment size and contains at most one copy of the watermark information, generating a set of segment boundary information describing the boundaries of segments within the variant output streams and the boundaries are the same between variant output streams, and generating a segment selection list using the set of embed location information and the set of segment boundary information, where the segment selection list includes only one variant segment for each segment according to a watermark sequence and the digits of the watermark sequence correspond to the watermark information applied to each variant preprocessed stream.