Creating, rendering and interacting with a multi-faceted audio cloud

Patent metadata

Field	Value
Publication number	US-10007724-B2
Application number	US-201213538988-A
Country	US
Kind code	B2
Filing date	Jun 29, 2012
Priority date	Jun 29, 2012
Publication date	Jun 26, 2018
Grant date	Jun 26, 2018

Abstract

Methods and arrangements for effecting a cloud representation of audio content. An audio cloud is created and rendered, and user interaction with at least a clip portion of the audio cloud is afforded.

First claim

What is claimed is:

1. An apparatus comprising:
at least one processor; and
a non-transitory computer readable storage medium having computer readable program code embodied therewith and executable by the at least one processor, the computer readable program code comprising:
computer readable program code configured to segment audio provided in a first language not having available automatic speech recognition capabilities into speech units, wherein to segment comprises employing a language sub-word recognition technique selected from the group consisting of: a statistical system for sub-word unit recognition; a voice-activity-detection technique; and a syllable segmentation technique, wherein the language sub-word recognition technique comprises utilizing a sub-word recognition technique of a second language having available automatic speech recognition capabilities and different from the first language of the audio;
computer readable program code configured to identify prominent speech units, wherein to identify comprises detecting a repeated speech unit by identifying speech patterns within the audio and using a language agnostic speech unit comparison technique, wherein the language agnostic speech unit comparison technique comprises a technique where a language associated with the speech unit is disregarded;
wherein to identify further comprises determining a frequency of occurrence of a speech unit and wherein a prominent speech unit comprises a speech unit that exceeds a predetermined frequency of occurrence threshold;
computer readable program code configured to create an audio cloud comprising audio signals of the prominent speech units, wherein each of the audio signals comprise a playable audio unit that when played provides an audible output from the audio of the corresponding prominent speech unit;
computer readable program code configured to render the audio cloud, wherein the audio cloud comprises a visual representation of the audio signals, wherein the audio signals are arranged in order of decreasing frequency of occurrence and wherein a volume of the audio signals is based upon the frequency of occurrence; and
computer readable program code configured to afford user interaction with at least a clip portion of the audio cloud.

2. A non-transitory computer program storage device comprising:
a non-transitory computer readable storage device having computer readable program code embodied therewith, the computer readable program code comprising:
computer readable program code configured to segment audio provided in a first language not having available automatic speech recognition capabilities into speech units, wherein to segment comprises employing a language sub-word recognition technique selected from the group consisting of: a statistical system for sub-word unit recognition; a voice-activity-detection technique; and a syllable segmentation technique, wherein the language sub-word recognition technique comprises utilizing a sub-word recognition technique of a second language having available automatic speech recognition capabilities and different from the first language of the audio;
computer readable program code configured to identify prominent speech units, wherein to identify comprises detecting a repeated speech unit by identifying speech patterns within the audio and using a language agnostic speech unit comparison technique, wherein the language agnostic speech unit comparison technique comprises a technique where a language associated with the speech unit is disregarded;
wherein to identify further comprises determining a frequency of occurrence of a speech unit and wherein a prominent speech unit comprises a speech unit that exceeds a predetermined frequency of occurrence threshold;
computer readable program code configured to create an audio cloud comprising audio signals of the prominent speech units, wherein each of the audio signals comprise a playable audio unit that when played provides an audible output from the audio of the corresponding prominent speech unit;
computer readable program code configured to render the audio cloud, wherein the audio cloud comprises a visual representation of the audio signals, wherein the audio signals are arranged in order of decreasing frequency of occurrence and wherein a volume of the audio signals is based upon the frequency of occurrence; and
computer readable program code configured to afford user interaction with at least a clip portion of the audio cloud.

3. The non-transitory computer program storage device according to claim 2 , comprising computer readable program code configured to detect speech units.

4. The non-transitory computer program storage device according to claim 2 , wherein said computer readable program code is configured to render the audio cloud via at least one member selected from the group consisting of: audio-based rendering; and visual-display-based rendering.

5. The non-transitory computer program storage device according to claim 2 , wherein said computer readable program code is configured to afford the creating and rendering of the audio cloud as interactive based on user input.

6. The non-transitory computer program storage device according to claim 2 , wherein a language sub-word recognition technique comprises a speech analysis technique where accuracy of the technique is not dependant on the language and language characteristics of the speaker.

7. The non-transitory computer program storage device according to claim 2 , wherein the audio cloud comprises a plurality of audio segments.

8. The non-transitory computer program storage device according to claim 2 , wherein the prominent speech units within the rendered audio cloud are presented in an order based upon the prominence of the speech unit.

9. A non-transitory computer program storage device comprising:
a non-transitory computer readable storage device having computer readable program code embodied therewith and executable by the at least one processor, the computer readable program code comprising:
computer readable program code configured to segment audio provided in a first language not having available automatic speech recognition capabilities into speech units;
wherein to segment comprises employing a language sub-word recognition technique selected from the group consisting of: a statistical system for sub-word unit recognition; a voice-activity-detection technique; and a syllable segmentation technique, wherein the language sub-word recognition technique comprises utilizing a sub-word recognition technique of a second language having available automatic speech recognition capabilities and different from the first language of the audio;
computer readable program code configured to identify, by detecting a repeated speech unit by identifying speech patterns within the audio and via employing a language-agnostic speech unit comparison technique, prominent speech units within the audio, wherein the language agnostic speech unit comparison technique comprises a technique where a language associated with the speech unit is disregarded;
wherein to identify further comprises determining a frequency of occurrence of a speech unit and wherein a prominent speech unit comprises a speech unit that exceeds a predetermined frequency of occurrence threshold;
computer readable program code configured to create an audio cloud comprising audio signals of the identified prominent speech units, wherein each of the audio signals comprise a playable audio unit that when played provides an audible output from the audio of the corresponding prominent speech unit;
computer readable program code configured to render the audio cloud, wherein the audio cloud comprises a visual representati

Assignees

• Ajmera Jitendra
• Deshmukh Om Dadaji
• Jain Anupam
• Nanavati Amit Anil
• Rajput Nitendra
• IBM

Inventors

• Ajmera Jitendra
• Deshmukh Om Dadaji
• Jain Anupam
• Nanavati Amit Anil
• Rajput Nitendra

Classifications

• G06F16/64 Primary

  Browsing; Visualisation therefor (generation of a list or set of audio data G06F16/638) · CPC title

• G10L15/04

  Segmentation; Word boundary detection · CPC title

• G06F17/30775 Primary

  Physics · mapped topic