Method and system for measuring communication skills of crew members

• US 10,152,899 B2
• Filed: 07/31/2014
• Issued: 12/11/2018
• Est. Priority Date: 08/01/2013
• Status: Active Grant

• Current Assignee: Crewfactors Limited
• Original Assignee: Crewfactors Limited
• Inventors: Vaughan, Brian, De Looze, Celine
• Primary Examiner(s): Skaarup, Jason
• Application Number:
  US14/909,044
• Publication Number:
  US 20160189562A1
• Time in Patent Office: 1,594 Days
• CPC Class Codes: G09B 19/00 Teaching not covered by other main groups of this subclass teaching or practice apparatus for gun-aiming or gun-laying F41G3/26
• CPC Class Codes: G09B 5/04 with audible presentation of the material to be studied sound recording or reproducing G11B

Abstract

A training tool, method and a system for measuring crew member communication skills are disclosed, wherein an audio data processing terminal interfaced with a crew training apparatus, typically a crew-operated vehicle simulator. Audio data corresponding to a conversation between at least two crew members is recording during a training session and stored. Respective audio data of each crew member is extracted from the stored audio data, and a series of measures for at least one prosodic parameter in each respective audio data extracted is computed. A correlation coefficient of the series of measures is then computed, wherein the correlation coefficient is indicative of a level of prosodic accommodation between the at least two crew members. Specific communication skills in addition to prosodic accommodation performance can the be determined inferred.

Claims

1. A method of measuring crew member communication skills with an audio data processing terminal interfaced with a crew training apparatus, comprising the steps of:

recording and storing audio data corresponding to a conversation between at least two crew members during a training session-;

extracting respective audio data of each crew member from the stored audio data;

computing a series of measures for at least one prosodic parameter in each respective audio data extracted;

computing a correlation coefficient of the series of measures, wherein the correlation coefficient is indicative of a level of prosodic accommodation between the at least two crew members; and

computing an objective rating of a level of communication skills based on the previous computed metrics, using statistical modelling techniques;

wherein the step of computing the series of measures comprises the further step of periodically sampling the respective audio data in a moving time window, which default length is extended to include the speech utterance of each crew member in its entirety.

2. The method according to claim 1, wherein the at least one prosodic parameter is selected from the group comprising crew member voice pitch level, crew member voice span, crew member voice intensity level, crew member voice intensity span, time spent talking, silent and overlapping.

3. The method according to claim 2, wherein a voice pitch level of each crew member is extracted by calculating an] F0 median of the respective audio data.

4. The method according to claim 2, wherein a voice span of each crew member is extracted by calculating a log 2 (F0 max−

F0 min) of the respective audio data.

5. The method according to claim 2, wherein a voice intensity level and span of each crew member is extracted by calculating a root mean square amplitude and standard deviation of the respective audio data.

6. The method according to claim 2, wherein the number and duration of conversation pauses is extracted by calculating number and duration silences within one speaker'"'"'s speech and wherein the minimum duration threshold for silent duration is defined at 200 ms.

7. The method according to claim 1, wherein the time spent talking versus silent is extracted by calculating amount of silent versus speech periods based on a Binary Voice Activity Detection method.

8. The method according to claim 1, comprising the further step of normalising the respective audio data by a log operation and an additional z-score transformation.

9. The method according to claim 1, comprising the further step of triggering at least one simulated event in the crew training apparatus for causing event-related conversation between the at least two crew members.

10. A system for measuring crew member communication skills, comprising:

a crew training apparatus having audio capturing means;

a data processing terminal interfaced with at least the audio capturing means and further comprising;

audio signal processing means for recording and storing audio data corresponding to a conversation between at least two crew members during a training session;

means for extracting respective audio data of each crew member from the stored audio data, for computing a series of measures for at least one prosodic parameter in each respective audio data extracted, for computing a correlation coefficient of the series of measures, wherein the correlation coefficient is indicative of a level of prosodic accommodation between the at least two crew members; and

for computing an objective rating of a level of communication skills based on the previous computed metrics, using statistical modelling techniques;

wherein the computing the series of measures comprises periodically sampling the respective audio data in a moving time window, which default length is extended to include the speech utterance of each crew member in its entirety.

11. The system according to claim 10, further comprising a network over which the crew training apparatus and the data processing terminal are connected to one another.

12. The system according to claim 10, wherein the at least one prosodic parameter is selected from the group comprising crew member voice pitch level, crew member voice span, crew member voice intensity level, crew member voice intensity span, number of conversation pauses, duration of conversation pauses, time spent talking and time spent silent.

13. The system according to claim 10, further comprising a user interface adapted to trigger at least one simulated event in the crew training apparatus for causing event related conversation between the at least two crew members.

14. A set of instructions recorded on a non-transitory data carrying medium which, when read from the medium and processed by a data processing terminal having audio means, configures the terminal to measure crew member communication skills by performing the data processing steps of recording and storing audio data corresponding to a conversation between at least two crew members during a training session;

extracting respective audio data of each crew member from the stored audio data;

computing a series of measures for at least one prosodic parameter in each respective audio data extracted;

computing a correlation coefficient of the series of measures, wherein the correlation coefficient is indicative of a level of prosodic accommodation between the at least two crew members; and

computing an objective rating of a level of communication skills based on the previous computed metrics, using statistical modelling techniques;

wherein the step of computing the series of measures comprises the further step of periodically sampling the respective audio data in a moving time window, which default length is extended to include the speech utterance of each crew member in its entirety.

15. A method of measuring crew member communication skills with an audio data processing terminal interfaced with a crew training apparatus, comprising the steps of:

recording and storing audio data corresponding to a conversation between at least two crew members during a training session;

extracting respective audio data of each crew member from the stored audio data;

infering levels of communication skills between the at least two crew members by computing a series of measures for at least one prosodic parameter in each respective audio data extracted, for computing a correlation coefficient of the series of measures, wherein the correlation coefficient is indicative of a level of prosodic accommodation between the at least two crew members; and

computing an objective rating of a level of communication skills based on the previous computed metrics, using statistical modelling techniques, wherein the step of computing the series of measures comprises the further step of periodically sampling the respective audio data in a moving time window, which default length is extended to include the speech utterance of each crew member in its entirety.

16. A simulator, comprising:

a simulation-based or operational environment including a user interface;

a crew training apparatus configured to trigger a simulated event at the user interface for causing an event-related conversation between at least two crew members in the environment;

an audio capturing device; and

a data processing terminal interfaced with the audio capturing device, the data processing terminal comprising;

an audio signal processing module configured to record and store audio data corresponding to the event-related conversation between the at least two crew members;

an audio data extraction module configured to;

extract respective audio data of each crew member from the stored audio data,

compute a series of measures of at least one prosodic parameter in each respective audio data extracted,

compute a correlation coefficient of the series of measures, wherein the correlation coefficient is indicative of a level of prosodic accommodation between the at least two crew members, and

compute an objective rating of a level of communication skills based on the previous computed metrics.