公开(公告)号：WO2019161011A1

公开(公告)日：2019-08-22

申请号：PCT/US2019/017941

申请日：2019-02-14

Applicant: DOLBY LABORATORIES LICENSING CORPORATION

Inventor： ZHOU, Cong ,  HORGAN, Michael Getty ,  KUMAR, Vivek ,  MORALES, Jaime H. ,  VASCO, Cristina Michel

IPC: G06N3/04 ,  G06N3/08 ,  G10L13/033

Abstract: Computer-implemented methods for speech synthesis are provided. A speech synthesizer may be trained to generate synthesized audio data that corresponds to words uttered by a source speaker according to speech characteristics of a target speaker. The speech synthesizer may be trained by time-stamped phoneme sequences, pitch contour data and speaker identification data. The speech synthesizer may include a voice modeling neural network and a conditioning neural network.

公开(公告)号：WO2018017878A1

公开(公告)日：2018-01-25

申请号：PCT/US2017/043152

申请日：2017-07-20

Applicant: DOLBY LABORATORIES LICENSING CORPORATION ,  DOLBY INTERNATIONAL AB

Inventor： NICOL, Philip ,  MATEOS SOLE, Antonio ,  CENGARLE, Giulio ,  VASCO, Cristina Michel

IPC: G10H1/00 ,  G10H1/44 ,  G10H7/00 ,  H04H60/00 ,  H04H60/02

CPC classification number: G10H7/00 ,  G10H1/00 ,  G10H1/0058 ,  G10H1/368 ,  G10H1/44 ,  G10H1/46 ,  G10H2210/305 ,  G10H2220/455 ,  G10H2240/325 ,  H04H60/04

Abstract: Methods, systems, and computer program products for network-based processing and distribution of multimedia content of a live performance are disclosed. In some implementations, recording devices can be configured to record a multimedia event (e.g., a musical performance). The recording devices can provide the recordings to a server while the event is ongoing. The server automatically synchronizes, mixes and masters the recordings. The server performs the automatic mixing and mastering using reference audio data previously captured during a rehearsal. The server streams the mastered recording to multiple end users through the Internet or other public or private network. The streaming can be live streaming.

Abstract translation: 公开了用于基于网络的处理和分发现场表演的多媒体内容的方法，系统和计算机程序产品。 在一些实现中，记录设备可以被配置为记录多媒体事件（例如，音乐演奏）。 记录设备可以在事件正在进行时将记录提供给服务器。 服务器自动同步，混合和控制录音。 服务器使用在排演期间先前捕获的参考音频数据来执行自动混音和母带制作。 服务器通过互联网或其他公共或私人网络将掌握的录制内容传输给多个最终用户。 流媒体可以直播。

公开(公告)号：WO2017116952A1

公开(公告)日：2017-07-06

申请号：PCT/US2016/068221

申请日：2016-12-22

Applicant: DOLBY LABORATORIES LICENSING CORPORATION

Inventor： KUNKEL, Timo ,  VASCO, Cristina Michel ,  DALY, Scott

IPC: G06F3/14 ,  G06T17/05 ,  H04N5/232

CPC classification number: G06F3/14 ,  G06T15/205 ,  G09G2352/00 ,  H04N5/232 ,  H04N5/23238 ,  H04N5/247

Abstract: A spherical image of a spatial environment is received and contains spherically arranged pixel values indexed by a time value. The spherical image is represented in a content creation coordinate system in reference to a spatial position in the spatial environment. The spatial position is indexed by the time value. A spatial relationship is determined between the content creation coordinate system and a spherical image reference coordinate system. Based at least in part on the spatial relationship and the spherically arranged pixel values, spherical distributions of image metadata are determined for the spherical image.

Abstract translation: 接收空间环境的球形图像并且包含由时间值索引的球形排列的像素值。 参考空间环境中的空间位置，在内容创建坐标系统中表示球形图像。 空间位置由时间值索引。 在内容创建坐标系和球形图像参考坐标系之间确定空间关系。 至少部分基于空间关系和球形排列的像素值，为球形图像确定图像元数据的球形分布。