Augmented reality speech balloon system
Disclosed is an augmented reality system to generate and cause display of an augmented reality interface at a client device. Various embodiments may detect speech, identify a source of the speech, transcribe the speech to a text string, generate a speech bubble based on properties of the speech and that includes a presentation of the text string, and cause display of the speech bubble at a location in the augmented reality interface based on the source of the speech.
1. A system comprising:
a memory; and
at least one hardware processor coupled to the memory and comprising instructions that causes the system to perform operations comprising:
causing display at a client device, of a presentation of a space, the presentation of the space including at least a first person;
detecting, by the client device, speech that includes speech properties;
identifying the first person as a source of the speech;
transcribing the speech to a text string based on the speech properties;
determining an emotional effect of the speech based on the speech properties;
selecting a speech bubble from a speech bubble library based on the emotional effect of the speech; and
causing display of the speech bubble at a position adjacent to the first person within the presentation of the space in response to the identifying the first person as the source of the speech, the speech bubble containing a display of the text string.
2. The system of claim 1 wherein the determining the emotional effect of the speech includes: parsing the text string to a set of words; determining a definition of each word among the set of words; comparing the definition of each word to an emotional effect library; and selecting the emotional effect from the emotional effect library based on the comparison.
3. The system of claim 1 wherein the first person has a set of facial landmarks, and wherein the determining the emotional effect of the speech includes: capturing an image of the first person in response to identifying the first person as the source of the speech; extracting the set of facial landmarks from the image of the first person; and determining the emotional effect based on the set of facial landmarks.
4. The system of claim 1 wherein the speech properties include at least a volume, and wherein the determining the emotional effect of the speech includes: determining the volume of the speech based on the speech properties; and determining the emotional effect based on the volume.
5. The system of claim 1 , wherein the instructions cause the system to perform operations further comprising:
detecting a non-verbal sound;
comparing the non-verbal sound to an onomatopoeia library in response to the detecting the non-verbal sound;
identifying an onomatopoeia from the onomatopoeia library based on the non-verbal sound; and
causing display of a graphical element based on the onomatopoeia within the presentation of the space.
6. The system of claim 1 , wherein the instructions cause the system to perform operations further comprising:
detecting movement of a mouth of the first person; and
identifying the first person as the source of the speech in response to the detecting the movement of the mouth.
7. The system of claim 1 , wherein the instructions cause the system to perform operations further comprising:
identifying a first language of the speech based on the speech properties; and
wherein the transcribing the speech to the text string includes translating the speech from the first language to at least a second language.
8. The system of claim 7 , wherein the instructions cause the system to perform operations further comprising:
accessing a user profile of a first user associated with the client device in response to the detecting the speech, wherein the user profile includes a language preference, the language preference specifying the second language.
9. The system of claim 1 , wherein the text string has a length based on the speech properties, and wherein the generating the speech bubble includes:
determining a size of the speech bubble based on the length of the text string.
10. A method including:
causing display at a client device, of a presentation of a space, the presentation of the space including at least a first person;
detecting, by the client device, speech that includes speech properties;
identifying the first person as a source of the speech;
transcribing the speech to a text string based on the speech properties;
determining an emotional effect of the speech based on the speech properties;
selecting a speech bubble from a speech bubble library based on the emotional effect of the speech; and
causing display of the speech bubble at a position adjacent to the first person within the presentation of the space in response to the identifying the first person as the source of the speech, the speech bubble containing a display of the text string.
11. The method of claim 10 , wherein the determining the emotional effect of the speech includes:
parsing the text string to a set of words;
determining a definition of each word among the set of words;
comparing the definition of each word to an emotional effect library; and
selecting the emotional effect from the emotional effect library based on the comparison.
12. The method of claim 10 wherein the first person has a set of facial landmarks, and wherein the determining the emotional effect of the speech includes: capturing an image of the first person in response to identifying the first person as the source of the speech; extracting the set of facial landmarks from the image of the first person; and determining the emotional effect based on the set of facial landmarks.
13. The method of claim 10 wherein the speech properties include at least a volume, and wherein the determining the emotional effect of the speech includes: determining the volume of the speech based on the speech properties; and determining the emotional effect based on the volume.
14. The method of claim 10 , further comprising:
detecting a non-verbal sound;
comparing the non-verbal sound to an onomatopoeia library in response to the detecting the non-verbal sound;
identifying an onomatopoeia from the onomatopoeia library based on the non-verbal sound; and
causing display of a graphical element based on the onomatopoeia within the presentation of the space.
15. The method of claim 10 , further comprising:
detecting movement of a mouth of the first person; and
identifying the first person as the source of the speech in response to the detecting the movement of the mouth.
16. The method of claim 10 , further comprising:
identifying a first language of the speech based on the speech properties; and
wherein the transcribing the speech to the text string includes translating the speech from the first language to at least a second language.
17. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations including:
causing display at a client device, of a presentation of a space, the presentation of the space including at least a first person;
detecting, by the client device, speech that includes speech properties;
identifying the first person as a source of the speech;
transcribing the speech to a text string based on the speech properties;
determining an emotional effect of the speech based on the speech properties;
selecting a speech bubble from a speech bubble library based on the emotional effect of the speech; and
causing display of the speech bubble at a position adjacent to the first person within the presentation of the space in response to the identifying the first person as the source of the speech, the speech bubble containing a display of the text string.