Determining and conveying contextual information for real time text
Aspects relate to machine recognition of human voices in live or recorded audio content, and delivering text derived from such live or recorded content as real time text, with contextual information derived from characteristics of the audio. For example, volume information can be encoded as larger and smaller font sizes. Speaker changes can be detected and indicated through text additions, or color changes to the font. A variety of other context information can be detected and encoded in graphical rendition commands available through RTT, or by extending the information provided with RTT packets, and processing that extended information accordingly for modifying the display of the RTT text content.
1. A computer-implemented method for real time text transmission, comprising:
accessing text output generated from a human audio source and metadata concerning characteristics of the human audio source;
determining control commands to be associated with respective portions of the text output based on the metadata;
forming packets containing the control commands and the associated portions of the text output, wherein the control commands conform to a pre-determined specification;
sending the packets in a real time text session to one or more participant receiving devices.
2. The method of claim 1 , wherein the control commands comprise commands for changing font color, and the method further comprises applying a different font color to all text determined to be a particular speaker detected in the human audio source.
3. The method of claim 1 , wherein the control commands comprise commands for changing font size, and the method further comprises applying a larger font size to portions of text output determined to have been spoken at a comparatively loud volume.
4. The method of claim 1 , wherein the control commands comprise commands for changing font size, and the method further comprises applying a smaller font size to portions of text output determined to have been spoken at a comparatively low volume.
5. The method of claim 1 , further comprising distinguishing between different speakers from the human audio source, generating text information responsive to changes in the identity of the speaker, and inserting the generated text information in the packet proximate portions of text output associated with each speaker.
6. The method of claim 1 , further comprising distinguishing between different speakers from the human audio source, and generating a control command indicative, in the pre-defined specification, of a change in speaker and including that control command in a packet containing the first text from a different speaker.
7. A tangible computer readable medium storing instructions for configuring a process to implement a method of real time text transmission, comprising:
accessing text output generated from a human audio source and metadata concerning characteristics of the human audio source;
determining control commands to be associated with respective portions of the text output based on the metadata;
forming packets containing the control commands and the associated portions of the text output, wherein the control commands conform to a pre-determined specification;
sending the packets in a real time text session to one or more participant receiving devices.
8. The tangible computer readable medium of claim 7 , wherein the control commands comprise commands for changing font color, and the method further comprises applying a different font color to all text determined to be a particular speaker detected in the human audio source.
9. The tangible computer readable medium of claim 7 , wherein the control commands comprise commands for changing font size, and the method further comprises applying a larger font size to portions of text output determined to have been spoken at a comparatively loud volume.
10. The tangible computer readable medium of claim 7 , wherein the control commands comprise commands for changing font size, and the method further comprises applying a smaller font size to portions of text output determined to have been spoken at a comparatively low volume.
11. The tangible computer readable medium of claim 7 , further comprising distinguishing between different speakers from the human audio source, generating text information responsive to changes in the identity of the speaker, and inserting the generated text information in the packet proximate portions of text output associated with each speaker.
12. The tangible computer readable medium of claim 7 , further comprising distinguishing between different speakers from the human audio source, and generating a control code indicative, in the pre-defined specification, of a change in speaker.
13. A mobile device, comprising:
a processor;
a network interface for communicatively coupling with at least one network;
a tangible computer readable medium storing instructions for configuring the processor to perform a method comprising
receiving packets through the network interface;
interpreting data in the packets as portions of text output, and control commands associated with respective portions of the text output, wherein the control commands are identified and interpreted according to a pre-determined specification;
determining text content and graphical modifications to the text content based on the portions of text output and the control commands; and
causing the text content to be rendered with the determined graphical modifications on a display.
14. The mobile device of claim 13 , wherein the control commands comprise commands for changing font color, and the method further comprises applying a different font color to all text associated with a font color change command.
15. The mobile device of claim 13 , wherein the control commands comprise commands for changing font size, and the method further comprises applying a larger font size to portions of text output determined to have been spoken at a comparatively loud volume.
16. The mobile device of claim 13 , wherein the control commands comprise commands for changing font size, and the method further comprises applying a smaller font size to portions of text output determined to have been spoken at a comparatively low volume.
17. The mobile device of claim 13 , wherein the control commands comprise commands for distinguishing between different speakers from the human audio source, and the method further comprises generating text information responsive to changes in the identity of the speaker, and inserting the generated text information in the packet proximate portions of text output associated with each speaker.
18. The mobile device of claim 13 , wherein the control commands comprise commands for distinguishing between different speakers from the human audio source, and the method further comprises generating a control command indicative, in the pre-defined specification, of a change in speaker and including that control command in a packet containing the first text from a different speaker.