US 10,535,330 B2Granted

System and method for movie karaoke

AssigneeCrackle, Inc.

InventorRobert Kushner

Life of this patent

Estimating the term…

Loading patent…

Abstract

While watching a movie, a user speaks lines of dialogue. The system records the speech, compares with the dialogue in the movie, and reports a score to the user. The system can share scores through an online service to create a community experience. In particular, the systems and methods disclosed implement a technique for matching user input to media content. A computer system receives audio input from a user (speech) and compares the received speech to dialogue in a movie or television program. For example, the computer system may convert the received speech to text and may compare the converted text against dialogue text using closed captioning or subtitle data. Alternatively, waveform data may be compared. The computer system generates a score for the speech based on how closely the speech matches the dialogue, and reports the score to the user through a user interface.

Claims21

Dependent claims

A method for operating a karaoke environment, comprising:

a. playing back video with corresponding audio on a display;
b. receiving speech as a user audio segment using a microphone, and buffering or caching the received speech as a first audio waveform;
c. marking the user audio segment with a timestamp;
d. retrieving a second audio waveform for the displayed video based on the timestamp, wherein the second audio waveform for the displayed video is determined by analyzing the audio corresponding to the video, and buffering a certain portion of the analyzed audio corresponding to the video;
e. waiting for a comparable portion of the first audio waveform to appear or become available in the buffered analyzed audio corresponding to the video, and then, using a processor, comparing the first audio waveform of the user audio segment marked with the timestamp to the comparable portion of the second audio waveform for the displayed video on a basis of pitch and intonation as deduced from the first and second audio waveforms, the comparable portion having another timestamp associated therewith, and wherein the comparing is further on the basis of the timestamp and the another timestamp;
and
f. generating a score based on a result of the comparing between the first and second audio waveforms.

4 more elements

A method for operating a karaoke environment, comprising:

a. arranging at least two media players to be in network communication, each media player configured to perform steps of:
i. playing back video with corresponding audio on a display;
ii. receiving a selection of a character portrayed on the displayed video;
iii. receiving speech as a user audio segment using a microphone, and buffering or caching the received speech as a first audio waveform;
iv. marking the user audio segment with a timestamp;
v. retrieving a second audio waveform for the displayed video based on the timestamp, wherein the second audio waveform for the displayed video is determined by analyzing audio corresponding to the video, and buffering a certain portion of the analyzed audio corresponding to the video;
vi. waiting for a comparable portion of the first audio waveform to appear or become available in the buffered analyzed audio corresponding to the video, and then, using a processor, comparing the first audio waveform of the user audio segment marked with the timestamp to the comparable portion of the second audio waveform for the displayed video on a basis of pitch and intonation as deduced from the first and second audio waveforms, the comparable portion having another timestamp associated therewith, and wherein the comparing is further on the basis of the timestamp and the another timestamp;
and
vii. generating a score based on a result of the comparing between the first and second audio waveforms;
and
viii. transmitting each user audio segment from the receiving media player to the other media player or players for playback.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application: 14/452,456Filed 5 Aug 2014 · us provisional application
Priority: 5 Aug 2013
Published: US 2015/0037777 A15 Feb 2015
Granted: 14 Jan 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification22 codes

G10H 1/361
Accompaniment arrangements: recording/reproducing of accompaniment for use with an external source, e.g. karaoke systems
A63F 13/00
Video games, i.e. games using an electronically generated display having two or
A63F 13/215
Characterised by their sensors, purposes or types: comprising means for detecting acoustic signals, e.g. using a microphone
A63F 13/424
By mapping the input signals into game commands, e.g. mapping the displacement of a stylus on a touch screen to the steering angle of a virtual…:…