Speed podcasting

• US 10,332,522 B2
• Filed: 04/23/2018
• Issued: 06/25/2019
• Est. Priority Date: 07/28/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Allen, Corville O., Chung, Albert A., Truong, Binh C., Yee, Kam K.
• Primary Examiner(s): Sharma, Neeraj
• Application Number:
  US15/960,534
• Publication Number:
  US 20180240462A1
• Time in Patent Office: 428 Days
• Field of Search: None
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Embodiments of the present invention address deficiencies of the art in respect to podcasting and provide a method, system and computer program product for speed podcasting. In an embodiment of the invention, a speed podcasting method can include speech recognizing an audio portion of a podcast, parsing the speech recognized audio portion to identify essential words, and playing back only audio segments and corresponding video segments of the podcast including the essential words while excluding from playback audio segments and corresponding video segments of the podcast including non-essential words.

Claims

1. A speed podcasting method comprising:

receiving a podcast of particular subject matter by a processor of a computer from over a computer communications network;

speech recognizing an audio portion of the received podcast by the processor of the computer into a transcript of both essential and non-essential words, the essential words comprising nouns and verbs directed to the particular subject matter, the non-essential words comprising articles, adverbs and adjectives not essential to the particular subject matter, by identifying a placement of each of the nouns and verbs in the transcript and determining whether or not each of the nouns and verbs is essential based upon an identified placement of a corresponding one of the nouns and verbs in the transcript;

parsing, by the processor of the computer, the words of the transcript, filtering the transcript to exclude non-essential words leaving only essential words comprising nouns and verbs, and comparing the parsed words remaining in the filtered transcript with a set of essential words in a data store so as to identify each of the essential word speech recognized and present in the transcript;

processing each word parsed in the transcript and matched to an essential word in the data store to index a corresponding audio segment of the audio portion of the podcast; and

,

playing back each indexed audio segment corresponding to an essential word in the speech recognized transcript matched to a word in the data store while excluding from playback all audio segments not indexed to an essential word in the speech recognized transcript.

2. The method of claim 1, wherein playing back comprises:

matching words in the speech recognized audio portion to essential words in a data store of essential words;

determining audio segments of the audio portion including the matched words; and

,

playing back the determined audio segments while excluding other audio segments of the audio portion from playback.

3. The method of claim 1, wherein playing back, comprises:

identifying non-essential words in the speech recognized audio portion; and

,

excluding audio segments of the audio portion from playback including the identified non-essential words while playing back other audio segments of the audio portion.

4. The method of claim 2, further comprising:

consulting a thesaurus to retrieve words synonymous with the matched words; and

,

adding the synonymous words to the data store of essential words.

5. The method of claim 2, wherein comprises:

applying a rating to each word in the data store of essential words;

associating a playback speed with each rating;

excluding from the determined audio segments audio segments with essential words associated with a rating inconsistent with a contemporaneously selected playback speed; and

,

playing back only the determined audio segments while excluding other audio segments of the audio portion from playback.

6. A mobile video playback device comprising:

a computer with memory and at least one processor;

an operating system executing in the memory of the computer and configured to playback podcasts stored in the mobile video playback device;

a datastore of essential words;

a speech recognition engine executing in the memory of the computer; and

,

speed podcasting logic executing under management of the operating system in the memory of the computer and comprising program code enabled to receive a podcast of particular subject matter by a processor of a computer from over a computer communications network speech recognize an audio portion of the received podcast by the processor of the computer into a transcript of both essential and non-essential words, the essential words comprising nouns and verbs directed to the particular subject matter, the non-essential words comprising articles, adverbs and adjectives not essential to the particular subject matter, to parse the words of the transcript, by identifying a placement of each of the nouns and verbs in the transcript and determining whether or not each of the nouns and verbs is essential based upon an identified placement of a corresponding one of the nouns and verbs in the transcript, filter the transcript to exclude non-essential words leaving only essential words comprising nouns and verbs, and compare the parsed words remaining in the filtered transcript with a set of essential words in a data store so as to identify each of the essential word speech recognized and present in the transcript, process each word parsed in the transcript and matched to an essential word in the data store to index a corresponding audio segment of the audio portion of the podcast, and to play back each indexed audio segment corresponding to an essential word in the speech recognized transcript matched to a word in the data store while excluding from playback all audio segments not indexed to an essential word in the speech recognized transcript.

7. The device of claim 6, wherein non-essential words comprise articles and pronouns.

8. The device of claim 6, further comprising a thesaurus, the program code being further enabled to locate in the thesaurus words synonymous with the identified words present in the datastore of essential words and to add the synonymous words to the datastore of essential words.

9. A computer program product comprising a non-transitory computer usable medium embodying computer usable program code for speed podcasting, the computer program product comprising:

computer usable program code for speech recognizing an audio portion of the received podcast by the processor of the computer into a transcript of both essential and non-essential words, the essential words comprising nouns and verbs directed to the particular subject matter, the non-essential words comprising articles, adverbs and adjectives not essential to the particular subject matter, by identifying a placement of each of the nouns and verbs in the transcript and determining whether or not each of the nouns and verbs is essential based upon an identified placement of a corresponding one of the nouns and verbs in the transcript;

computer usable program code for receiving a podcast of particular subject matter by a processor of a computer from over a computer communications network;

computer usable program code for parsing the words of the transcript, filtering the transcript to exclude non-essential words leaving only essential words comprising nouns and verbs, and comparing the parsed words remaining in the filtered transcript with a set of essential words in a data store so as to identify each of the essential word speech recognized and present in the transcript;

computer usable program code for processing each word parsed in the transcript and matched to an essential word in the data store to index a corresponding audio segment of the audio portion of the podcast; and

,

computer usable program code for playing back each indexed audio segment corresponding to an essential word in the speech recognized transcript matched to a word in the data store while excluding from playback all audio segments not indexed to an essential word in the speech recognized transcript.

10. The computer program product of claim 9, wherein the computer usable program code for playing back comprises:

computer usable program code for matching words in the speech recognized audio portion to essential words in a data store of essential words;

computer usable program code for determining audio segments of the audio portion including the matched words; and

,

computer usable program code for playing back the determined audio segments while excluding other audio segments of the audio portion from playback.

11. The computer program product of claim 9, wherein the computer usable program code for playing back comprises:

computer usable program code for identifying non-essential words in the speech recognized audio portion; and

,

computer usable program code for excluding audio segments of the audio portion from playback including the identified non-essential words while playing back other audio segments of the audio portion.

12. The computer program product of claim 10, further comprising:

computer usable program code for consulting a thesaurus to retrieve words synonymous with the matched words; and

,

computer usable program code for adding the synonymous words to the data store of essential words.

13. The computer program product of claim 10, wherein the computer usable program code for playing back comprises:

computer usable program code for applying a rating to each word in the data store of essential words;

computer usable program code for associating a playback speed with each rating;

computer usable program code for excluding from the determined audio segments audio segments with essential words associated with a rating inconsistent with a contemporaneously selected playback speed; and

,

computer usable program code for playing back only the determined audio segments while excluding other audio segments of the audio portion from playback.