Synchronizing virtual actor's performances to a speaker's voice
First Claim
1. A method for generating and displaying holographic visual aids, comprising:
- capturing one or more images of a reading object using a mobile device;
identifying the reading object using the one or more images;
detecting at the mobile device that a first phrase of the reading object has been spoken by a particular person;
determining a reading pace corresponding with the first phrase spoken by the particular person;
determining a location of a second phrase different from the first phrase as it appears in the reading object; and
displaying a sequence of character images at a rate corresponding with the reading pace of the first phrase, the sequence of character images includes a sequence of mouth shape images displayed such that a character associated with the location appears to speak the second phrase at the reading pace.
2 Assignments
0 Petitions
Accused Products
Abstract
A system for generating and displaying holographic visual aids associated with a story to an end user of a head-mounted display device while the end user is reading the story or perceiving the story being read aloud is described. The story may be embodied within a reading object (e.g., a book) in which words of the story may be displayed to the end user. The holographic visual aids may include a predefined character animation that is synchronized to a portion of the story corresponding with the character being animated. A reading pace of a portion of the story may be used to control the playback speed of the predefined character animation in real-time such that the character is perceived to be lip-syncing the story being read aloud. In some cases, an existing book without predetermined AR tags may be augmented with holographic visual aids.
32 Citations
20 Claims
-
1. A method for generating and displaying holographic visual aids, comprising:
-
capturing one or more images of a reading object using a mobile device; identifying the reading object using the one or more images; detecting at the mobile device that a first phrase of the reading object has been spoken by a particular person; determining a reading pace corresponding with the first phrase spoken by the particular person; determining a location of a second phrase different from the first phrase as it appears in the reading object; and displaying a sequence of character images at a rate corresponding with the reading pace of the first phrase, the sequence of character images includes a sequence of mouth shape images displayed such that a character associated with the location appears to speak the second phrase at the reading pace. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. One or more storage devices containing processor readable code for programming one or more processors to perform a method for generating and displaying holographic visual aids comprising the steps of:
-
acquiring a user profile associated with an end user of a mobile device, the user profile includes a voice model corresponding with a particular person different from the end user; capturing one or more images of a reading object using the mobile device; identifying the reading object using the one or more images; detecting a first phrase of the reading object spoken by the particular person based on the voice model; determining a reading pace corresponding with the first phrase spoken by the particular person; determining a location of a second phrase different from the first phrase as it appears in the reading object; and displaying a sequence of character images at a rate corresponding with the reading pace of the first phrase, the sequence of character images includes a sequence of mouth shape images displayed such that a character associated with the location appears to speak the second phrase at the reading pace. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16, 17)
-
-
18. An electronic device for generating and displaying holographic visual aids, comprising:
-
a memory, the memory stores a voice model associated with a particular person; one or more processors, the one or more processors identify a reading object, the one or more processors detect that a first phrase of the reading object has been spoken by the particular person using the voice model, the one or more processors determine a reading pace corresponding with the first phrase spoken by the particular person, the one or more processors determine a location of a second phrase different from the first phrase as it appears in the reading object, the one or more processors generate a sequence of character images; and a see-through display, the see-through display displays the sequence of character images at a rate corresponding with the reading pace of the first phrase, the sequence of character images includes a sequence of mouth shape images displayed such that a character associated with the location appears to speak the second phrase at the reading pace. - View Dependent Claims (19, 20)
-
Specification