Differential dynamic content delivery with text display in dependence upon sound level

• US 8,954,844 B2
• Filed: 08/14/2007
• Issued: 02/10/2015
• Est. Priority Date: 01/13/2004
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Bodin, William Kress, Burkhart, Michael John, Eisenhauer, Daniel G., Schumacher, Daniel Mark, Watson, Thomas J.
• Primary Examiner(s): TAPP, AMELIA L
• Application Number:
  US11/838,610
• Publication Number:
  US 20090048829A1
• Time in Patent Office: 2,737 Days
• Field of Search: 715/255
• US Class Current: 715/255
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Differential dynamic content delivery including providing a session document for a presentation, where the session document includes a session grammar and a session structured document; selecting from the session structured document a classified structural element in dependence upon user classifications of a user participant in the presentation; presenting the selected structural element to the user; streaming speech to the user from one or more users participating in the presentation; converting the speech to text; detecting a total sound level for the user; and determining whether to display the text in dependence upon the total sound level for the user.

Claims

1. A method comprising:

providing session data for a presentation, wherein the session data includes a session grammar and a session structured document;

selecting from the session structured document a classified structural element in dependence upon user classifications of a user participant in the presentation;

presenting the selected structural element to the user;

streaming speech to the user from one or more users participating in the presentation;

detecting a total sound level for the user; and

displaying a textual transcription of the speech to the user based upon the total sound level detected, wherein the total sound level comprises the streaming speech plus ambient noise, and wherein displaying the textual transcription of the speech further comprises displaying the textual transcription of the speech if a ratio of the total sound level to the ambient noise level is less than a predetermined value.

2. The method of claim 1 wherein the total sound level for the user includes ambient noise and the method includes detecting an ambient noise level for the user.

3. The method of claim 2 wherein detecting an ambient noise level for the user further comprises temporarily interrupting the speech streaming to the user and measuring a sound level on a voice channel associated with the user during the interruption and while the user is not speaking.

4. The method of claim 2 wherein displaying the textual transcription of the speech further comprises displaying the textual transcription of the speech to the user if the ambient noise level is above a predetermined threshold.

5. The method of claim 1, wherein displaying the textual transcription of the speech comprises displaying the textual transcription of the speech to the user if the total sound level exceeds a threshold value.

6. The method of claim 1 wherein selecting a classified structural element further comprises selecting a classified structural element having an associated classification identifier that corresponds to the user classifications.

7. The method of claim 1 further comprising creating the session data from a presentation document, including:

identifying a presentation document for a presentation, the presentation document including a presentation grammar and a structured document having structural elements classified with classification identifiers;

identifying the user participant for the presentation, the user having a user profile comprising user classifications; and

filtering the structured document in dependence upon the user classifications and the classification identifiers.

8. The method of claim 7 further comprising filtering the presentation grammar, in dependence upon the extracted structural elements, into a session grammar for inclusion in the session data.

9. A system for differential dynamic content delivery for a presentation, the system comprising:

at least one processor configured to;

identify a preexisting presentation document for the presentation, the presentation document including a presentation grammar and a structured document having a plurality of structural elements, including a first structural element classified with a first classification identifier and a second structural element classified with a second classification identifier;

identify user participants for the presentation, the user participants each having a user profile comprising a user classification, the user participants including at least one user in a first user classification and at least one user in a second user classification;

filter the presentation document based upon the user classifications of the user participants and the classification identifiers to generate session data targeted for the participants of the presentation, wherein the filtering comprises;

presenting first session data targeted to the at least one user in the first user classification, the first session data comprising the first structural element, but not the second structural element; and

presenting second session data targeted to the at least one user in the second user classification, the second session data comprising both the first and second structural elements;

stream speech to a user participant of the user participants;

detect a total sound level for the user participant, wherein the total sound level comprises the streaming speech plus ambient noise; and

display a textual transcription of the speech to the user participant if a ratio of the total sound level to the ambient noise level is less than a predetermined value.

10. The system of claim 9, wherein the at least one processor is configured to present a structural element from the session data responsive to speech input by a user participant.

11. The system of claim 9, wherein the at least one processor is further configured to display the textual transcription of the speech to the user participant if the total sound level exceeds a threshold value.

12. The system of claim 9, wherein the at least one processor is further configured to:

temporarily interrupt the speech streaming to the user participant and measure an ambient sound level on a voice channel associated with the user participant during the interruption and while the user participant is not speaking; and

display the textual transcription of the speech to the user participant if the ambient noise level is above a predetermined threshold.

13. At least one computer readable medium comprising instructions that, when executed by at least one processor, perform a method comprising acts of:

identifying a preexisting presentation document for the presentation, the presentation document including a presentation grammar and a structured document having a plurality of structural elements, including a first structural element classified with a first classification identifier and a second structural element classified with a second classification identifier;

identifying user participants for the presentation, the user participants each having a user profile comprising a user classification, the user participants including at least one user in a first user classification and at least one user in a second user classification;

filtering the presentation document based upon the user classifications of the user participants and the classification identifiers to generate session data targeted for the participants of the presentation, wherein the filtering comprises;

presenting first session data targeted to the at least one user in the first user classification, the first session data comprising the first structural element, but not the second structural element; and

presenting second session data targeted to the at least one user in the second user classification, the second session data comprising both the first and second structural elements;

presenting a structural element from the session data structure responsive to speech input by a user participant of the user participants;

streaming speech to the user participant from one or more user participants;

detecting a total sound level for the user participant;

detecting an ambient noise level component of the total sound level; and

displaying a textual transcription of the speech to the user participant if a ratio of the total sound level to the ambient noise level is less than a predetermined value.

14. The at least one computer readable medium of claim 13, wherein the method further comprises displaying the textual transcription of the speech to the user participant if the total sound level exceeds a threshold value.

15. The at least one computer readable medium of claim 13, wherein the method further comprises:

temporarily interrupting the speech streaming to the user participant and measuring an ambient sound level on a voice channel associated with the user participant during the interruption and while the user participant is not speaking; and

displaying the textual transcription of the speech to the user participant if the ambient noise level is above a predetermined threshold.