Pandora Media, Inc.

Vanderbilt University

Andrew Joseph Asman

Patrick Laughlin Kelly

Shriram Bharath

Christopher Irwin

Richard G Abramsom

Bennett Landman

Ruslan Yesikov

Zhoubing Xu

Mayur Patel

Benjamin K Poulose

Miya Smith

Rebeccah B Baucom

Isaac Hill

Andrew Plassard

A content server uses a form of artificial intelligence such as machine learning to identify audio content with musicological characteristics. The content server obtains an indication of a music item presented by a client device and obtains reference music features describing musicological characteristics of the music item. The content server identifies candidate audio content associated with candidate music features. The candidate music features are determined by analyzing acoustic features of the candidate audio content and mapping the acoustic features to music features according to a music feature model. Acoustic features quantify low-level properties of the candidate audio content. One of the candidate audio content items is selected according to comparisons between the candidate music features of the candidate audio advertisements and the reference music features of the music item. The selected audio content is provided the client device for presentation.

Relating acoustic features to musicological features for selecting audio with similar musical characteristics

A content mediating server receives from a client device a request for a next content item to be selected based on a content event relating to a current content item. The content mediating server generates requests for content from content providing servers providing content of corresponding types, and receives from each content providing server a content table relating content events in a set of content events to content items. For each content event in the set, the content mediating server selects, from the received tables, a content item, generates a composite content table relating each content event in the set to the selected content item, and transmits the composite table to the client device. The client device, in response to an observed content event relating to the current content item, selects the content item in the composite table corresponding to the observed content event as the next content item.

Delivery of personalized digital content in real time

Systems and methods are provided for segmenting tissue within a computed tomography (CT) scan of a region of interest into one of a plurality of tissue classes. A plurality of atlases are registered to the CT scan to produce a plurality of registered atlases. A context model representing respective likelihoods that each voxel of the CT scan is a member of each of the plurality of tissue classes is determined from the CT scan and a set of associated training data. A proper subset of the plurality of registered atlases is selected according to the context model and the registered atlases. The selected proper subset of registered atlases are fused to produce a combined segmentation.

Image segmentation via multi-atlas fusion with context learning

Growing community of inventors

Berkeley, CA, United States of America

Andrew Joseph Asman