User driven audio content navigation

• US 9,710,552 B2
• Filed: 08/28/2012
• Issued: 07/18/2017
• Est. Priority Date: 06/24/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Deshmukh, Om D., Rajput, Nitendra
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US13/596,313
• Publication Number:
  US 20120324356A1
• Time in Patent Office: 1,785 Days
• Field of Search: 704 9, 704500, 704201, 704211, 704275, 704258, 704270, 379 8801, 379 8804, 379 8808
• CPC Class Codes: G06F 16/64 Browsing; Visualisation therefor generation of a list or set of audio data G06F16/638
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 21/043 by changing speed
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

Systems and associated methods configured to provide user-driven audio content navigation for the spoken web are described. Embodiments allow users to skim audio for content that seems to be of relevance to the user, similar to visual skimming of standard web pages, and mark point of interest within the audio. Embodiments provide techniques for navigating audio content while interacting with information systems in a client-server environment, where the client device can be a simple, standard telephone.

Claims

1. A method comprising:

receiving, at a voice-driven application hosted on a telecom network, one or more audio browsing commands, wherein the one or more audio browsing commands comprises a change in audio speed command;

responsive to the one or more audio browsing commands, saving an application state corresponding to a current point of user interaction with audio contained at a node of the voice-driven application;

cutting the audio until the current point of user interaction associated with the receipt of the one or more audio browsing commands;

generating a marker corresponding to the cut position in the audio;

subtracting an additional time from the audio from the current point of user interaction;

re-synthesizing the audio to produce a portion of the audio having an altered playback speed according to the one or more audio browsing commands, wherein the re-synthesized audio comprises audio having an overlap between a time where the receipt of the one or more audio browsing commands was received and where the speed change starts based upon the additional time subtracted from the audio; and

storing a marker location and number corresponding to the generated marker along with the speed change associated with the audio speed command.

2. The method according to claim 1, wherein the one or more audio browsing commands includes a retrieve command.

3. The method according to claim 2, further comprising, responsive to the retrieve command, returning to the marked position in the audio.

4. The method according to claim 3, wherein the marked position in the audio is offset to accommodate delay in generating the marker.

5. The method of claim 1, further comprising using the application state to return audio beginning a point corresponding to user interaction with the audio at a time the one or more audio browsing commands were received.

6. The method according to claim 1, wherein the one or more audio browsing commands includes a speed up command.

7. The method according to claim 6, further comprising, responsive to the speed up command, re-synthesizing at least a portion of the audio to produce a portion of the audio having increased playback speed.

8. The method according to claim 7, wherein re-synthesizing at least a portion of the audio to produce a portion of the audio having increased playback speed further comprises performing non-uniform dropping of frames within the audio.

9. The method according to claim 8, wherein performing non-uniform dropping of frames within the audio further comprises one or more of:

identifying one or more steady regions and one or more transient regions within the audio, wherein said transient regions are maintained; and

identifying prosody regions within the audio to be retained for maintaining prosody, wherein said prosody regions are maintained within the audio.