METHOD APPARATUS AND COMPUTER PROGRAM PRODUCT FOR PROSODIC TAGGING

• US 20130311185A1
• Filed: 01/19/2012
• Published: 11/21/2013
• Est. Priority Date: 02/15/2011
• Status: Abandoned Application

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Atri, Rohit, Patil, Sidharth
• Application Number:
  US13/983,413
• Publication Number:
  US 20130311185A1
• Time in Patent Office: Days
• US Class Current: 704/250
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 25/03 characterised by the type of extracted parameters
• CPC Class Codes: G10L 25/90 Pitch determination of speech signals

Abstract

In accordance with an example embodiment a method and apparatus are provided. The method comprises identifying at least one subject voice in one or more media files. The method also comprises determining at least one prosodic feature of the at least one subject voice. The method also comprises determining at least one prosodic tag for the at least one subject voice based on the at least one prosodic feature.

Claims

1-43. -43. (canceled)

44. A method comprising:

identifying at least one subject voice in one or more media files;

determining at least one prosodic feature of the at least one subject voice; and

determining at least one prosodic tag for the at least one subject voice based on the at least one prosodic feature.

45. The method as claimed in claim 44, further comprising:

facilitating storing of the at least one prosodic tag for the at least one subject voice.

46. The method as claimed in claim 45, wherein facilitating storing of a prosodic tag comprises:

receiving name of a subject corresponding to the prosodic tag; and

facilitating storing of the prosodic tag corresponding to the name of the subject in a database.

47. The method as claimed in claim 44, further comprising:

tagging the one or more media files based on the at least one prosodic tag, wherein tagging a media file comprises enlisting one or more prosodic tags corresponding to one or more subject voices present in the media file.

48. The method as claimed in claim 44 further comprising:

clustering the one or more media files in one or more clusters of media files corresponding to prosodic tags, wherein a cluster of media files corresponding to a prosodic tag comprises media files tagged by the prosodic tag.

49. The method as claimed in claim 44 further comprising:

receiving a query for accessing media files corresponding to a set of subjects voices; and

clustering the one or more media files in a set of clusters of media files corresponding to prosodic tags for the set of subject voices, wherein a cluster of media files corresponding to a prosodic tag comprises media files tagged by the prosodic tag.

50. The method as claimed in claim 44, wherein the at least one subject voice comprises voice of at least one person.

51. The method as claimed in claim 44, wherein the at least one subject voice comprises voice of at least one of one or more non-human creatures, one or more manmade machines, or one or more natural objects.

52. An apparatus comprising:

at least one processor; and

at least one memory comprising computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform;

identify at least one subject voice in one or more media files;

determine at least one prosodic feature of the at least one subject voice; and

determine at least one prosodic tag for the at least one subject voice based on the at least one prosodic feature.

53. The apparatus as claimed in claim 52, wherein the apparatus is further caused, at least in part, to facilitate to store of the at least one prosodic tag for the at least one subject voice.

54. The apparatus as claimed in claim 53, wherein, to facilitate to store prosodic tag, the apparatus is further caused, at least in part, to perform:

receive name of a subject corresponding to the prosodic tag; and

facilitate storing of the prosodic tag corresponding to the name of the subject in a database.

55. The apparatus as claimed in claim 52, wherein the apparatus is further caused, at least in part, to tag the one or more media files based on the at least one prosodic tag, wherein tagging a media file comprises enlisting one or more prosodic tags corresponding to one or more subject voices present in the media file.

56. The apparatus as claimed in claim 52, wherein the apparatus is further caused, at least in part, to perform cluster the one or more media files in one or more clusters of media files corresponding to prosodic tags, wherein a cluster of media files corresponding to a prosodic tag comprises media files tagged by the prosodic tag.

57. The apparatus as claimed in claim 52, wherein the apparatus is further caused, at least in part, to perform:

receive a query for accessing media files corresponding to a set of subjects voices; and

cluster the one or more media files in a set of clusters of media files corresponding to prosodic tags for the set of subject voices, wherein a cluster of media files corresponding to a prosodic tag comprises media files tagged by the prosodic tag.

58. The apparatus as claimed in claim 52, wherein the at least one subject voice comprises voice of at least one person.

59. The apparatus as claimed in claim 52, wherein the at least one subject voice comprises voice of at least one of one or more non-human creatures, one or more manmade machines, or one or more natural objects.

60. A computer program product comprising a set of computer program instructions, which, when executed by one or more processors, cause an apparatus at least to perform:

identify at least one subject voice in one or more media files;

determine at least one prosodic feature of the at least one subject voice; and

determine at least one prosodic tag for the at least one subject voice based on the at least one prosodic feature.

61. The computer program as claimed in claim 60, wherein the apparatus is further caused, at least in part, to facilitate to store of the at least one prosodic tag for the at least one subject voice.

62. The computer program as claimed in claim 61, wherein, to store the prosodic tag, the apparatus is further caused, at least in part, to perform:

receive name of a subject corresponding to the prosodic tag; and

facilitate storing of the prosodic tag corresponding to the name of the subject in a database.

63. The computer program as claimed in claim 60, wherein the apparatus is further caused, at least in part, to tag the one or more media files based on the at least one prosodic tag, wherein tagging a media file comprises enlisting one or more prosodic tags corresponding to one or more subject voices present in the media file.