IP Library Granted Patent US 10,290,027
Granted Patent B2
US 10,290,027 · App. 14/500,777 · Granted May 14, 2019

Dynamically selected background music for personalized audio advertisement

Inventors: Shriram Bharath (Oakland, CA); Jacek Adam Krawczyk (San Francisco, CA); Christopher Irwin (Los Altos, CA)
Assignee: Pandora Media, LLC
G06Q30/0276G06Q30/0269H04L65/602
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,290,027
App. No.
14/500,777
Granted
May 14, 2019
Kind
B2
Abstract

A content server system provides a client device with content including an audio advertisement with personalized background music. The content server selects a vocal advertisement received from an advertiser for presentation to a user of a client device. The content server obtains content data describing audio content provided to the client device as part of the stream of audio content. The content server obtains content data describing audio content provided to the client device as part of the stream of audio content. The content server identifies candidate background music items and selects background music from the candidate background music items based on the obtained content data. The client device is provided with the selected background music and the selected vocal advertisement. The client device plays an audio advertisement comprising the background music played concurrently with the vocal advertisement.

Claims (58)

1. A computer-implemented method for providing an audio message with background music, the method comprising:

selecting a vocal message for presentation to a user of a client device playing a stream of audio content;

selecting background music to accompany the vocal message, wherein selecting the background music comprises:

retrieving selection criteria associated with the vocal message, the selection criteria indicating preferences for features of background music to be played with the vocal message;

obtaining content data describing audio content provided to the client device as part of the stream;

obtaining a content reference coordinate representing audio features of the audio content described by the content data;

identifying reference music fulfilling the selection criteria;

obtaining an audio reference coordinate representing audio features of the reference music fulfilling the selection criteria;

determining a combined reference coordinate by combining the content reference coordinate and the audio reference coordinate according relative weights specified by the selection criteria;

selecting the background music from among candidate background music items based on comparisons between the combined reference coordinate and the candidate background music items; and

providing, to the client device, the selected background music and the selected vocal message, the client device configured to play an audio message comprising the background music played concurrently with the vocal message.

2. The method of claim 1 , wherein selecting the background music further comprises:

obtaining a candidate coordinate representing audio features of a candidate background music item;

determining a score for the candidate background music item based on a measure of similarity between the combined reference coordinate and the candidate coordinate; and

selecting the candidate background music item as the background music responsive to the score for the candidate background music item.

3. The method of claim 1 , wherein selecting the background music further comprises:

obtaining a user reference coordinate representing audio features of music preferred by the user of the client device; and

selecting the background music based on comparisons between the combined reference coordinate, the user reference coordinate, and the candidate background music items.

4. A non-transitory computer-readable storage medium comprising computer program instructions executable by a processor, the instructions for:

selecting a vocal message for presentation to a user of a client device playing a stream of audio content;

selecting background music to accompany the vocal message, wherein selecting the background music comprises:

retrieving selection criteria associated with the vocal message, the selection criteria indicating preferences for features of background music to be played with the vocal message;

obtaining content data describing audio content provided to the client device as part of the stream;

obtaining a content reference coordinate representing audio features of the audio content described by the content data;

identifying reference music fulfilling the selection criteria;

obtaining an audio reference coordinate representing audio features of the reference music fulfilling the selection criteria;

determining a combined reference coordinate by combining the content reference coordinate and the audio reference coordinate according relative weights specified by the selection criteria;

selecting the background music from among candidate background music items based on comparisons between the combined reference coordinate and the candidate background music items; and

providing, to the client device, the selected background music and the selected vocal message, the client device configured to play an audio message comprising the background music played concurrently with the vocal message.

5. The computer-readable medium of claim 4 , wherein selecting the background music further comprises:

obtaining a candidate coordinate representing audio features of a candidate background music item;

determining a score for the candidate background music item based on a measure of similarity between the combined reference coordinate and the candidate coordinate; and

selecting the candidate background music item as the background music responsive to the score for the candidate background music item.

6. The computer-readable medium of claim 4 , wherein selecting the background music further comprises:

obtaining a user reference coordinate representing audio features of music preferred by the user of the client device; and

selecting the background music based on comparisons between the combined reference coordinate, the user reference coordinate, and the candidate background music items.

7. A system for generating an audio message with background music, the system comprising:

a processor; and

a non-transitory computer-readable storage medium comprising computer program instructions executable by the processor, the instructions for:

selecting a vocal message for presentation to a user of a client device playing a stream of audio content;

selecting background music to accompany the vocal message, wherein selecting the background music comprises:

retrieving selection criteria associated with the vocal message, the selection criteria indicating preferences for features of background music to be played with the vocal message;

obtaining content data describing audio content provided to the client device as part of the stream;

obtaining a content reference coordinate representing audio features of the audio content described by the content data;

identifying reference music fulfilling the selection criteria;

obtaining an audio reference coordinate representing audio features of the reference music fulfilling the selection criteria;

determining a combined reference coordinate by combining the content reference coordinate and the audio reference coordinate according relative weights specified by the selection criteria;

selecting the background music from among candidate background music items based on comparisons between the combined reference coordinate and the candidate background music items; and

providing, to the client device, the selected background music and the selected vocal message, the client device configured to play an audio message comprising the background music played concurrently with the vocal message.

8. The system of claim 7 , wherein selecting the background music further comprises:

obtaining a candidate coordinate representing audio features of a candidate background music item;

determining a score for the candidate background music item based on a measure of similarity between the combined reference coordinate and the candidate coordinate; and

selecting the candidate background music item as the background music responsive to the score for the candidate background music item.

9. The system of claim 7 , wherein selecting the background music further comprises:

obtaining a user reference coordinate representing audio features of music preferred by the user of the client device; and

selecting the background music based on comparisons between the combined reference coordinate, the user reference coordinate, and the candidate background music.

10. The method of claim 1 , wherein the features of background music to be played with the vocal message comprise audio features.

11. The method of claim 1 , wherein the selection criteria further comprise bibliographic information of the reference music.

Assignments (5)
SECURITY INTEREST Recorded Nov 26, 2025
From: PANDORA MEDIA, LLC
To: JPMORGAN CHASE BANK, N.A., AS ADMINISTRATIVE AGENT
Reel/Frame 073043/0142 →
CHANGE OF NAME Recorded Mar 29, 2019
From: PANDORA MEDIA, INC.
To: PANDORA MEDIA, LLC
Reel/Frame 048748/0255 →
RELEASE OF SECURITY INTEREST Recorded Feb 1, 2019
From: WELLS FARGO BANK, NATIONAL ASSOCIATION
To: PANDORA MEDIA CALIFORNIA, LLC; ADSWIZ INC.
Reel/Frame 048209/0925 →
SECURITY INTEREST Recorded Dec 29, 2017
From: PANDORA MEDIA, INC.; PANDORA MEDIA CALIFORNIA, LLC
To: WELLS FARGO BANK, NATIONAL ASSOCIATION
Reel/Frame 044985/0009 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 12, 2014
From: BHARATH, SHRIRAM; KRAWCZYK, JACEK ADAM; IRWIN, CHRISTOPHER
To: PANDORA MEDIA, INC.
Reel/Frame 034159/0641 →
Continuity (1)
Related Publication 20160092936A1 · Mar 31, 2016