Adapting a playback of a recording to optimize comprehension

• US 10,158,825 B2
• Filed: 09/02/2015
• Issued: 12/18/2018
• Est. Priority Date: 09/02/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Abou Mahmoud, Alaa, Dracoulis, Gregory P., Stubbs, Peter E., Ulrick, Steven J.
• Primary Examiner(s): Tran, Thai Q
• Assistant Examiner(s): YANG, NIEN
• Application Number:
  US14/843,328
• Publication Number:
  US 20170064244A1
• Time in Patent Office: 1,203 Days
• Field of Search: 386344
• CPC Class Codes: G11B 27/005 Reproducing at a different information rate from the information rate of recording for television signals H04N5/783
• CPC Class Codes: H04N 5/7605 on discs or drums H04N5/781, H04N5/805, H04N5/83, H04N5/85 take precedence
• CPC Class Codes: H04N 5/783 Adaptations for reproducing at a rate different from the recording rate

Abstract

Each of segment of a recording is analyzed for complexity specifying a rate of speech at a normal playback speech. A target rate is selected at which to playback the recording, the target rate specifying a fastest optimal speed at which a particular user listening to the recording is able to comprehend the playback. During playback of the recording, a separate adjusted playback rate is selected for each of the segments to adjust the playback rate of speech from the rate of speech at the normal playback speed to the target rate.

Claims

1. A method, comprising:

analyzing, by a computer, a single instance of a recording using natural language processing to translate one or more spoken words in the single instance of the recording into textual language;

identifying, by the computer, a separate complexity of each translation of each of the one or more spoken words to reflect a rate of speech at a normal playback speed and to reflect a difficulty performing natural language processing to detect each spoken word within the single instance of the recording and translate each spoken word in the single instance of the recording into textual language, each separate complexity specifying a different speed;

analyzing, by the computer, the single instance of the recording to identify a plurality of segments of the recording for each separate complexity, each of the plurality of segments set to a separate length for a separate continuous portion of the one or more spoken words of a same complexity;

selecting, by the computer, a target rate at which to playback the single instance of the recording for access by a particular user from among a plurality of users, the target rate specifying a fastest optimal speed at which the particular user listening to the single instance of the recording is able to comprehend the playback; and

during playback of the single instance of the recording, modifying, by the computer, playback of the single instance of the recording in an interface accessible to the particular user to contiguously be at the target rate, wherein a separate adjusted playback rate is applied to each of the plurality of segments to adjust the playback rate of speech from the separate complexity of the rate of speech at the normal playback speed to the target rate.

2. The method according to claim 1, further comprising:

during playback of the single instance of the recording, monitoring, by the computer, through one or more interfaces selected to detect one or more types of responses by one or more users, for one or more particular responses by the particular user indicative of a comprehension level of the playback of the single instance of the recording by the particular user;

analyzing, by the computer, the one or more particular responses to identify a type of response indicating the comprehension level from among a plurality of types of responses and a recommended action to change the type of response, the plurality of types of responses comprising a first response that the particular user has additional capacity for comprehension, a second response that the particular user is at an optimal capacity for comprehension, and a third response that the particular user is over capacity for comprehension; and

responsive to the comprehension level not evaluated as the second response that the particular user is at the optimal capacity for comprehension, dynamically adjusting, by the computer, the target rate based on the comprehension level.

3. The method according to claim 2, further comprising:

responsive to the comprehension level evaluated as additional capacity for comprehension of the playback at a faster speed, dynamically increasing, by the computer, a speed set in the target rate; and

responsive to the comprehension level evaluated as over capacity for comprehension of the playback at a current speed for the target rate, dynamically decreasing, by the computer, the current speed set in the target rate.

4. The method according to claim 2, wherein during playback of the single instance of the recording, monitoring, by the computer, through one or more interfaces selected to detect one or more types of responses by one or more users, for one or more particular responses by the particular user indicative of a comprehension level of the playback of the single instance of the recording by the particular user further comprises:

detecting, by the computer, a proximity of the particular user to a speaker outputting the playback of the single instance of the recording through the one or more interfaces; and

responsive to detecting the proximity of the particular user to the speaker within a threshold distance of the speaker, evaluating, by the computer, the comprehension level of the particular user as over capacity for comprehension.

5. The method according to claim 2, wherein during playback of the single instance of the recording, monitoring, by the computer, through one or more interfaces selected to detect one or more types of responses by one or more users, for one or more particular responses by the particular user indicative of a comprehension level of the playback of the single instance of the recording by the particular user further comprises:

capturing, by the computer, one or more images of the particular user during the playback of the single instance of the recording;

analyzing, by the computer, the captured one or more images of the particular user to identify one or more facial features associated with one or more expressions;

responsive to the one or more expressions matching one or more specified expressions set as indicating struggling, evaluating, by the computer, the comprehension level of the particular user as over capacity; and

responsive to the one or more expressions matching one or more specified expressions set as indicating distraction, evaluating, by the computer, the comprehension level of the particular user as having additional capacity available.

6. The method according to claim 2, wherein during playback of the single instance of the recording, monitoring, by the computer, through one or more interfaces selected to detect one or more types of responses by one or more users, for one or more particular responses by the particular user indicative of a comprehension level of the playback of the single instance of the recording by the particular user, further comprises:

monitoring, by the computer, a frequency and length of one or more user selections of one or more of forwarding the playback and reversing the playback;

analyzing the frequency and length of the one or more user selections;

responsive to the frequency and length of the one or more user selections of reversing the playback exceeding a reverse threshold setting, evaluating, by the computer, the comprehension level of the particular user as over capacity; and

responsive to the frequency and length of the one or more user selections of forwarding the playback exceeding a forward threshold setting, evaluating, by the computer, the comprehension level of the particular user as comprising additional capacity.

7. The method according to claim 1, wherein analyzing, by a computer, a single instance of a recording using natural language processing to translate one or more spoken words in the single instance of the recording into textual language further comprises:

analyzing the textual language against at least one topic selected by a user to determine if the textual language is relevant to the at least one topic; and

marking at least one portion of the single instance of the recording comprising a selection of textual language that is not relevant to the at least one topic.

8. The method according to claim 1, further comprising:

analyzing, by the computer, each of the plurality of segments of the single instance of the recording for relevance, wherein each separate segment comprising silence is marked as irrelevant; and

during playback of the single instance of the recoding, by the computer, omitting one or more segments marked as irrelevant from among the plurality of segments.

9. A computer system comprising one or more processors, one or more computer-readable memories, one or more computer-readable storage devices, and program instructions, stored on at least one of the one or more storage devices for execution by at least one of the one or more processors via at least one of the one or more memories, the stored program instructions comprising:

program instructions to analyze a single instance of a recording using natural language processing to translate one or more spoken words in the single instance of the recording into textual language;

program instructions to identify a separate complexity of each translation of each of the one or more spoken words to reflect a rate of speech at a normal playback speed and to reflect a difficulty performing natural language processing to detect each spoken word within the single instance of the recording and translate each spoken word in the single instance of the recording into textual language, each separate complexity specifying a different speed;

program instructions to analyze the single instance of the recording to identify a plurality of segments of the recording for each separate complexity, each of the plurality of segments set to a separate length for a separate continuous portion of the one or more spoken words of a same complexity;

program instructions to select a target rate at which to playback the single instance of the recording for access by a particular user from among a plurality of users, the target rate specifying a fastest optimal speed at which the particular user listening to the single instance of the recording is able to comprehend the playback; and

program instructions to, during playback of the single instance of the recording, modify playback of the single instance of the recording in an interface accessible to the particular user to contiguously be at the target rate, wherein a separate adjusted playback rate is applied to each of the plurality of segments to adjust the playback rate of speech from the separate complexity of the rate of speech at the normal playback speed to the target rate.

10. The computer system according to claim 9, the stored program instructions further comprising:

program instructions to, during playback of the single instance of the recording, through one or more interfaces selected to detect one or more types of responses by one or more users, for one or more particular responses by the particular user indicative of a comprehension level of the playback of the single instance of the recording by the particular user;

program instructions to analyze the one or more particular responses to identify a type of response indicating the comprehension level from among a plurality of types of responses and a recommended action to change the type of response, the plurality of types of responses comprising a first response that the particular user has additional capacity for comprehension, a second response that the particular user is at an optimal capacity for comprehension, and a third response that the particular user is over capacity for comprehension; and

program instructions, responsive to the comprehension level not evaluated as the second response that the particular user is at the optimal capacity for comprehension, dynamically adjusting, by the computer, the target rate based on the comprehension level.

11. The computer system according to claim 10, the stored program instructions further comprising:

program instructions, responsive to the comprehension level evaluated as additional capacity for comprehension of the playback at a faster speed, dynamically increasing, by the computer, a speed set in the target rate; and

program instructions, responsive to the comprehension level evaluated as over capacity for comprehension of the playback at a current speed for the target rate, dynamically decreasing, by the computer, the current speed set in the target rate.

12. The computer system according to claim 10, the stored program instructions further comprising:

program instructions to detect a proximity of the particular user to a speaker outputting the playback of the single instance of the recording through the one or more interfaces; and

program instructions, responsive to detecting the proximity of the particular user to the speaker within a threshold distance of the speaker, to evaluate the comprehension level of the particular user as over capacity for comprehension.

13. The computer system according to claim 10, the stored program instructions further comprising:

program instructions to capture one or more images of the particular user during the playback of the single instance of the recording;

program instructions to analyze the captured one or more images of the particular user to identify one or more facial features associated with one or more expressions;

program instructions, responsive to the one or more expressions matching one or more specified expressions set as indicating struggling, to evaluate the comprehension level of the particular user as over capacity; and

program instructions, responsive to the one or more expressions matching one or more specified expressions set as distracted, to evaluate the comprehension level of the particular user as having additional capacity.

14. The computer system according to claim 10, the stored program instructions further comprising:

program instructions to monitor a frequency and length of one or more user selections of one or more of forwarding the playback and reversing the playback;

program instructions to analyze the frequency and length of the one or more user selections;

program instructions, responsive to the frequency and length of the one or more user selections of reversing the playback exceeding a reverse threshold setting, to evaluate the comprehension level of the particular user as over capacity; and

program instructions, responsive to the frequency and length of the one or more user selections of forwarding the playback exceeding a forward threshold setting, to evaluate the comprehension level of the particular user as comprising additional capacity.

15. The computer system according to claim 9, the stored program instructions further comprising:

program instructions to analyze the textual language against at least one topic selected by a user to determine if the textual language is relevant to the at least one topic; and

program instructions to mark at least one portion of the single instance of the recording comprising a selection of textual language that is not relevant to the at least one topic.

16. The computer system according to claim 9, the stored program instructions further comprising:

program instructions to analyze each of the plurality of segments of the single instance of the recording for relevance, wherein each separate segment comprising silence is marked as irrelevant; and

program instructions to, during playback of the single instance of the recoding, omit one or more segments marked as irrelevant from among the plurality of segments.

17. A computer program product comprising one or more computer-readable storage devices and program instructions, stored on at least one of the one or more storage devices, the stored program instructions comprising:

program instructions to analyze a single instance of a recording using natural language processing to translate one or more spoken words in the single instance of the recording into textual language;

program instructions to identify a separate complexity of each translation of each of the one or more spoken words to reflect a rate of speech at a normal playback speed and to reflect a difficulty performing natural language processing to detect each spoken word within the single instance of the recording and translate each spoken word in the single instance of the recording into textual language, each separate complexity specifying a different speed;

program instructions to analyze the single instance of the recording to identify a plurality of segments of the recording for each separate complexity, each of the plurality of segments set to a separate length for a separate continuous portion of the one or more spoken words of a same complexity;

program instructions to select a target rate at which to playback the single instance of the recording for access by a particular user from among a plurality of users, the target rate specifying a fastest optimal speed at which the particular user listening to the single instance of the recording is able to comprehend the playback; and

program instructions to, during playback of the single instance of the recording, modify playback of the single instance of the recording in an interface accessible to the particular user to contiguously be at the target rate, wherein a separate adjusted playback rate is applied to each of the plurality of segments to adjust the playback rate of speech from the separate complexity of the rate of speech at the normal playback speed to the target rate.

18. The computer program product according to claim 17, the stored program instructions further comprising:

program instructions to, during playback of the single instance of the recording, monitor through one or more interfaces selected to detect one or more types of responses by one or more users, for one or more particular responses by the particular user indicative of a comprehension level of the playback of the single instance of the recording by the particular user;

program instructions to analyze the one or more particular responses to identify a type of response indicating the comprehension level from among a plurality of types of responses and a recommended action to change the type of response, the plurality of types of responses comprising a first response that the particular user has additional capacity for comprehension, a second response that the particular user is at an optimal capacity for comprehension, and a third response that the particular user is over capacity for comprehension; and

program instructions, responsive to the comprehension level not evaluated as the second response that the particular user is at the optimal capacity for comprehension, dynamically adjusting, by the computer, the target rate based on the comprehension level.

19. The computer program product according to claim 18, the stored program instructions further comprising:

program instructions, responsive to the comprehension level evaluated as additional capacity for comprehension of the playback at a faster speed, dynamically increasing, by the computer, a speed set in the target rate; and

program instructions, responsive to the comprehension level evaluated as over capacity for comprehension of the playback at a current speed for the target rate, dynamically decreasing, by the computer, the current speed set in the target rate.

20. The computer program product according to claim 18, the stored program instructions further comprising:

program instructions to detect a proximity of the particular user to a speaker outputting the playback of the single instance of the recording through the one or more interfaces; and

program instructions, responsive to detecting the proximity of the particular user to the speaker within a threshold distance of the speaker, to evaluate the comprehension level of the particular user as over capacity for comprehension.