System and method for intelligent configuration of an audio channel with background analysis

Patent metadata

Field	Value
Publication number	US-9930085-B2
Application number	US-201514867495-A
Country	US
Kind code	B2
Filing date	Sep 28, 2015
Priority date	Sep 28, 2015
Publication date	Mar 27, 2018
Grant date	Mar 27, 2018

Abstract

Methods, systems and computer program products for configuring an audio channel are provided. Aspects include generating a confidence metric indicative of at least one control cue in a telecommunication audio feed input. Generating the confidence metric can include analyzing the control cue to determine a cue type, assigning a confidence metric value for the control cue based on the cue type, and comparing the confidence metric value to a predetermined threshold value associated with the cue type. Aspects also include updating a context history with the cue type and configuring an audio channel output based on the confidence metric and context history.

First claim

What is claimed is:

1. A method for configuring an audio channel with a processor, the method comprising:
generating a confidence metric indicative of at least one control cue in a telecommunication audio feed, wherein generating the confidence metric comprises:
analyzing the at least one control cue to determine a cue type;
assigning a confidence metric value for the at least one control cue based on the cue type, wherein the cue type comprises both explicit speech to perform an action and muffled voice having a lower amplitude than the average amplitude of other portions of the audio feed;
comparing the confidence metric value to a predetermined threshold value associated with the cue type;
updating a context history with the cue type and the confidence metric value; and
configuring an input of the audio channel based on the confidence metric and the context history.

2. The method of claim 1 , wherein the processor configures the input of the audio channel by one of muting the input and unmuting the input.

3. The method of claim 1 , wherein analyzing the at least one control cue comprises:
identifying at least one word verbalized on the telecommunication audio feed; and
determining a relative context of the conversation based on the at least one word.

4. The method of claim 1 , wherein the at least one control cue comprises one or more of an input volume, an output volume, a spoken word, a series of spoken words having a conversational context, accelerometer data, photoelectric data, and a global positioning system (GPS) data.

5. The method of claim 1 , wherein the cue type is a predetermined time period of high or low volume, wherein the volume is an amplitude measured with respect to an average amplitude.

6. The method of claim 1 , wherein the at least one control cue is a verbalized name of a telecommunication participant in the telecommunication audio feed.

7. The method of claim 1 , wherein the at least one control cue is silence for a predetermined period of time.

8. The method of claim 1 , wherein the at least one control cue is one or more of a low volume word and a combination of words having a predetermined relevance value.

9. The method of claim 8 , wherein the predetermined relevance value is based on a context of a conversation on the telecommunication audio feed.

10. The method of claim 1 , wherein the at least one control cue is a combination of an accelerometer reading and an input volume.

11. The method of claim 1 , wherein creating the context history is indicative of one or more control cues associated with a particular user.

12. The method of claim 1 , wherein the confidence metric comprises a plurality of control cues, and the confidence metric value increases with respect to a greater number of control cues.

13. The method of claim 1 , further comprising outputting an audio cue indicative that the processor has configured the input to the audio channel.

14. The method of claim 1 , wherein the processor prompts for user input regarding a cue sensitivity setting, and the confidence metric value is based in part on the cue sensitivity setting.

15. The method of claim 1 , wherein the processor prompts for user input indicative of a situational context and a preferred response to the situational context.

16. The method of claim 1 , wherein the context history is indicative of a situational context and a user's response to the situational context.

17. The method of claim 16 , wherein the context history is based on a plurality of telecommunication audio feeds.

18. A system for configuring an audio channel, the system comprising an audio input device configured to receive a telecommunication audio feed input; and a processor operatively connected to the audio input device and configured to:
monitor the audio feed input;
generate a confidence metric indicative of at least one control cue in the audio feed;
determine a cue type, wherein the cue type comprises both explicit speech to perform an action and muffled voice having a lower amplitude than the average amplitude of other portions of the audio feed;
assign a confidence metric value for the at least one control cue based on the cue type;
compare the confidence metric value to a predetermined threshold value associated with the cue type;
update a context history with the cue type and the confidence metric value; and
configure an input of the audio channel based on the confidence metric and the context history.

19. A non-transitory computer-readable storage medium storing a computer program product executable to perform a method, the method including:
generating a confidence metric indicative of at least one control cue in a telecommunication audio feed, wherein generating the confidence metric comprises:
analyzing the at least one control cue to determine a cue type;
assigning a confidence metric value for the at least one control cue based on the cue type;
comparing the confidence metric value to a predetermined threshold value associated with the cue type, wherein the cue type comprises both explicit speech to perform an action and muffled voice having a lower amplitude than the average amplitude of other portions of the audio feed;

updating a context history with the cue type and the confidence metric value; and
configuring an input of the audio channel based on the confidence metric and the context history.

Assignees

• IBM

Inventors

• Hockett Hugh E
• Ghosh Rahul
• Quirk Aaron J
• Sun Lin

Classifications

• H04L67/22

  Electricity · mapped topic

• H04L65/601 Primary

  Electricity · mapped topic

• H04L12/1813

  for computer conferences, e.g. chat rooms (instant messaging H04L51/04; protocols for multimedia communication H04L65/1101; arrangements for multi-party communication H04L65/403; telephonic conference arrangements H04M3/56; television conference systems H04N7/15) · CPC title

• H04M3/568

  audio processing specific to telephonic conferencing, e.g. spatial distribution, mixing of participants (echo suppression in two-way loud-speaking telephone systems H04M9/02; sound field processing per se H04S7/30) · CPC title

• H04L65/75

  Media network packet handling · CPC title