Public speaking trainer with 3-D simulation and real-time feedback
A public speaking trainer has a computer system including a display monitor. A microphone is coupled to the computer system. A video capture device is coupled to the computer system. A biometric device is coupled to the computer system. A simulated environment including a simulated audience member is rendered on the display monitor using the computer system. A presentation is recorded onto the computer system using the microphone and video capture device. A first feature of the presentation is extracted based on data from the microphone and video capture device while recording the presentation. A metric is calculated based on the first feature. The simulated audience member is animated in response to a change in the metric. A score is generated based on the metric. The score is displayed on the display monitor of the computer system after recording the presentation. A training video is suggested based on the score.
1. A method of speech training, comprising:
providing a predictive model including a plurality of rating scales for a plurality of presentation features, wherein a first rating scale for a first feature of the plurality of presentation features includes a plurality of thresholds for rating the first feature, and wherein the plurality of thresholds is identified by a machine learning algorithm generating the predictive model;
displaying a simulated audience member;
receiving a presentation by a user;
extracting the first feature from the presentation;
analyzing the presentation by comparing the first feature against the plurality of thresholds on the first rating scale of the predictive model; and
generating a reaction of the simulated audience member based on a result of analyzing the presentation.
2. The method of claim 1 , wherein the first feature is a measurement of an amount and type of hand gestures of the user detected in the presentation.
3. The method of claim 1 , further including displaying a plurality of simulated audience members.
4. The method of claim 3 , wherein the number, ethnicity, gender, clothes, skin tone, voice, profession, domain, and technical expertise of simulated audience members is configurable.
5. The method of claim 1 , wherein the reaction of the simulated audience member depends on the user's performance in real-time and includes facial expressions and built-in animations for motions or gestures.
6. The method of claim 1 , wherein the reaction of the simulated audience member depends on the user's performance in real-time and includes talking, speaking, or asking questions.
7. The method of claim 1 , further including providing an online dashboard for a trainer or instructor at an organization to create and configure training assignments or lessons for user practice including presentation topics, interview questions, or other prompts for the user, wherein online dashboard allows the trainer or instructor to review results data for a plurality of users.
8. The method of claim 1 , further including providing customization options for an environment of the presentation, wherein the environment can be selected from a plurality of possible customization options including auditorium, video conference, and board room.
9. The method of claim 1 , further including recording the presentation using a laptop, personal computer, mobile device, web browser, virtual reality, or augmented reality device.
10. A method of speech training, comprising:
providing a predictive model including,
a first rating scale for a vocalics feature,
a second rating scale for a content feature, and
a third rating scale for a body language feature,
wherein the first rating scale, second rating scale, and third rating scale each includes a plurality of thresholds identified by a machine learning algorithm generating the predictive model;
displaying a simulated audience member;
receiving a presentation by a user;
extracting the vocalics feature, content feature, and body language feature from the presentation;
analyzing the presentation by,
comparing the vocalics feature extracted from the presentation against the plurality of thresholds of the first rating scale,
comparing the content feature extracted from the presentation against the plurality of thresholds of the second rating scale, and
comparing the body language feature extracted from the presentation against the plurality of thresholds of the third rating scale; and
generating a reaction of the simulated audience member based on a result of analyzing the presentation.
11. The method of claim 10 , wherein the vocalics feature includes pitch variability, pace variability, volume variability, pauses, intonation, pace, rhythm, intonation, or intensity.
12. The method of claim 10 , wherein the vocalics feature includes speech emotion recognition to analyze if the user will be perceived as enthusiastic, confident, charismatic, emotional, convincing, positive, negative, or competent.
13. The method of claim 10 , wherein the content feature includes usage of weak language, sentence length, sentence structure, proper usage of domain-specific vocabulary, linguistic complexity, storytelling, clarity, conciseness, structural coherency, use of emotional versus analytical content, audience perception, word choices that match predefined terms expected in the presentation, or presentation slide design.
14. The method of claim 10 , wherein the body language feature includes eye contact, hand gestures, body movement, facial expression, or posture.
15. The method of claim 10 , further including providing an online dashboard for a trainer or instructor at an organization to review results data for a plurality of users.
16. The method of claim 10 , further including recording the presentation using a laptop, personal computer, mobile device, web browser, virtual reality, or augmented reality device.
17. A method of speech training, comprising:
providing a predictive model including a plurality of rating scales for a plurality of presentation features, wherein a first rating scale for a first feature of the plurality of presentation features includes a plurality of thresholds for rating the first feature, and wherein the plurality of thresholds is identified by a machine learning algorithm generating the predictive model;
displaying a simulated audience member;
receiving a presentation by a user;
extracting the first feature from the presentation;
analyzing the presentation by comparing the first feature against the plurality of thresholds on the first rating scale of the predictive model, wherein the first feature is a vocalics feature, a content feature, or a body language feature of the presentation; and
generating a reaction of the simulated audience member based on a result of analyzing the presentation.
18. The method of claim 17 , wherein the vocalics feature includes pitch variability, pace variability, volume variability, pauses, pace, rhythm, intonation, or intensity.
19. The method of claim 17 , wherein the content feature includes usage of weak language, sentence length, sentence structure, proper usage of domain-specific vocabulary, linguistic complexity, storytelling, clarity, conciseness, structural coherency, use of emotional versus analytical content, audience perception, word choices that match predefined terms expected in the presentation based on a technical domain of the presentation, or presentation slide design.
20. The method of claim 17 , wherein the body language feature includes eye contact, hand gestures, posture, body movement, or facial expression.