Speed podcasting

• US 9,953,651 B2
• Filed: 07/28/2008
• Issued: 04/24/2018
• 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:
  US12/180,906
• Publication Number:
  US 20100023330A1
• Time in Patent Office: 3,557 Days
• Field of Search: 704251, 704254, 704231, 704 9, 704235, 704201, 704 10, 707 3, 707737, 707 4, 707 2, 715202, 715256, 715968, 715700, 370313, 709204
• 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;

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;

selecting a playback speed for speed podcasting the received podcast;

determining a rating corresponding to the selected playback speed; 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 and having a rating higher than the determined rating, while excluding from playback all audio segments not indexed to an essential word in the speech recognized transcript and all audio segments indexed to an essential word having a rating lower than the determined rating.

2. The method of claim 1, further comprising:

consulting, by the processor of the computer, a thesaurus to retrieve words synonymous with the matched word in the data store of essential words; and

,

adding, by the processor of the computer, the synonymous words to the data store of essential words.

7. The method of claim 1, wherein speech recognizing the audio portion of the podcast by the processor of the computer comprises producing a transcript of the audio portion of the podcast.

3. A mobile video playback device comprising:

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

a datastore of essential words;

a speech recognition engine; and

,

speed podcasting logic executing under management of the operating system comprising program code enabled to receive a podcast of particular subject matter, speech recognize an audio portion of the received podcast 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 each word of 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, to 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, to select a playback speed for speed podcasting the received podcast, to determine a rating corresponding to the selected playback speed, 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 and having a rating higher than the determined rating, while excluding from playback all audio segments not indexed to an essential word in the speech recognized transcript and all audio segments indexed to an essential word having a rating lower than the determined rating.

4. The device of claim 3, 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.

8. The device of claim 3, wherein the program code of the speed podcasting logic enabled to speech recognize the audio portion of the selected podcast comprises program code to produce a transcript of the audio portion of the selected podcast.

5. A computer program product comprising a non-transitory computer usable storage medium storing computer usable program code for speed podcasting, the computer program product comprising:

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 speech recognizing an audio portion of the received podcast 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;

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;

computer usable program code for selecting a playback speed for speed podcasting the received podcast;

computer usable program code for determining a rating corresponding to the selected playback speed; 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 and having a rating higher than the determined rating, while excluding from playback all audio segments not indexed to an essential word in the speech recognized transcript and all audio segments indexed to an essential word having a rating lower than the determined rating.

6. The computer program product of claim 5, further comprising:

computer usable program code for consulting a thesaurus to retrieve words synonymous with the matched word in the data store of essential words; and

,

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

9. The computer program product of claim 5, wherein the computer usable program code for speech recognizing the audio portion of the podcast comprises computer usable program code for producing a transcript of the audio portion of the podcast.