System and method for multimodal interactive speech and language training

• US 5,885,083 A
• Filed: 06/19/1997
• Issued: 03/23/1999
• Est. Priority Date: 04/09/1996
• Status: Expired due to Term

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Ferrell, Joe G.
• Primary Examiner(s): Apley, Richard J.
• Assistant Examiner(s): ROVNAK, JOHN EDMUND
• Application Number:
  US08/878,685
• Time in Patent Office: 642 Days
• Field of Search: 434/156, 434/157, 434/167, 434/169, 434/185, 434/323
• US Class Current: 434/156
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04
• CPC Class Codes: G09B 5/065 Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems

Abstract

A system and method for multimodal interactive speech training include selecting a modality (10) corresponding to various sensory stimuli to present non-native vocabulary elements (12) to an individual to train the individual to immediately respond (16) to a presented word, situation, or data without performing a time-consuming literal translation or other complex cognitive process. The system and method include speech synthesis, speech recognition, and visual representations of non-native vocabulary elements to promote rapid comprehension through neuro-linguistic programming of the individual.

Claims

1. A method for training an individual to recognize and respond to at least one unfamiliar vocabulary element, the method comprising:

selecting the at least one unfamiliar vocabulary element from a plurality of new and previously presented unfamiliar vocabulary elements;

automatically presenting a lesson for the at least one unfamiliar vocabulary element using a plurality of modalities corresponding to different sensory stimuli to present the at least one unfamiliar vocabulary element to the individual, the lesson including a preview exercise indicating a number of vocabulary elements to be presented, a comprehension exercise including a contextual presentation with the unfamiliar vocabulary element omitted, and a recall exercise including repeated presentation of vocabulary elements until a correct response is provided for each;

for each exercise;

pausing for a time sufficient for the individual to respond to the at least one unfamiliar vocabulary element;

receiving a response from the individual based on the at least one unfamiliar vocabulary element;

evaluating the response based on a predetermined desired response criteria; and

providing visual and audio feedback to the individual indicating correctness of the response, the visual feedback including an icon and the audio feedback including a synthesized voice.

2. The method of claim 1 wherein the plurality of modalities comprises audio, textual, and graphical representations of the at least one unfamiliar vocabulary element.

3. The method of claim 1 wherein providing feedback comprises generating a speech signal which includes a name of the individual.

4. The method of claim 1 wherein presenting comprises presenting an audio stimulus including a synthesized utterance and a visual representation of the at least one unfamiliar vocabulary element.

5. The method of claim 4 wherein presenting a visual representation comprises presenting a textual representation of the at least one unfamiliar vocabulary element.

6. The method of claim 4 wherein presenting a visual representation comprises presenting a graphical representation of the at least one unfamiliar vocabulary element.

7. The method of claim 1 wherein receiving comprises:

receiving a request from the individual indicative of difficulty in understanding the at least one unfamiliar vocabulary element; and

presenting the at least one unfamiliar vocabulary element in a context of familiar vocabulary elements.

8. The method of claim 1 wherein the step of receiving includes receiving a verbal response from the individual.

9. The method of claim 1 wherein presenting comprises presenting contextual information absent the at least one unfamiliar vocabulary element during the comprehension exercise and the recall exercise.

10. The method of claim 1 wherein the step of automatically presenting comprises:

randomly presenting each of the at least one unfamiliar vocabulary elements.

18. The method of claim 1 wherein the step of selecting comprises selecting at least one unfamiliar vocabulary element for every third lesson only from those previously presented.

19. The method of claim 1 wherein the step of presenting comprises presenting the at least one unfamiliar vocabulary element aurally and visually followed by a pause to allow a recited utterance from the user during the preview exercise.

11. A system for training an individual to recognize and respond to at least one unfamiliar vocabulary element, the system comprising:

a display device for providing a visual representation of the at least one unfamiliar vocabulary element;

a speech synthesizer for providing an audio representation of the at least one unfamiliar vocabulary element;

at least one input device for generating a signal indicative of a response of the individual to the at least one unfamiliar vocabulary element; and

control logic in communication with the display device, the speech synthesizer and the at least one input device for selecting the at least one unfamiliar vocabulary element from a plurality of new and previously presented unfamiliar vocabulary elements, automatically presenting a lesson for the at least one unfamiliar vocabulary element using both the display device and the speech synthesizer, the lesson including a preview exercise indicating a quantity of vocabulary elements to be presented, a comprehension exercise including presentation of contextual information absent the unfamiliar vocabulary element, and a recall exercise, for each exercise pausing for a time sufficient for the individual to generate a response to the at least one unfamiliar vocabulary element, evaluating the response based on at least one desired response criterion, and providing visual and audio feedback to the individual using the display device and the speech synthesizer.

12. The system of claim 11 wherein the at least one input device comprises a microphone and wherein the control logic implements speech recognition to evaluate the response based on the at least one desired response criterion.

13. The system of claim 12 wherein the at least one input device comprises a microphone, a pointing device, and a keyboard.

14. The system of claim 11 wherein the control logic provides feedback by generating a speech signal using the speech synthesizer, the speech synthesizer generating an audio signal representing a name of the individual.

15. The system of claim 14 wherein the control logic communicates with the speech synthesizer and the display device to present an audio stimulus to the individual including a synthesized utterance and a visual representation of the at least one unfamiliar vocabulary element.

16. The system of claim 11 wherein the at least one input device is operative to receive a request from the individual indicative of difficulty in understanding the at least one unfamiliar vocabulary element and wherein the control logic communicates with the speech synthesizer to present the at least one unfamiliar vocabulary element to the individual in a context of familiar vocabulary elements.

17. A system for rapidly training an individual to recognize and respond to at least one unfamiliar vocabulary element without requiring complex cognitive tasks, the system comprising:

a display device for providing a visual representation of the at least one unfamiliar vocabulary element;

a speech synthesizer for providing an audio representation of the at least one unfamiliar vocabulary element;

a keyboard for generating a signal indicative of a response of the individual to the at least one unfamiliar vocabulary element;

a pointing device for generating a signal indicative of a response of the individual to the at least one unfamiliar vocabulary element;

a microphone for converting audio responses of the individual to corresponding electrical speech signals;

a speech recognition device in communication with the microphone for mapping the electrical signal to a predetermined vocabulary library; and

a computer in communication with the display device, the speech synthesizer, the keyboard, the pointing device, the microphone, and the speech recognition device for presenting the at least one unfamiliar vocabulary element to the individual using both the display device and the speech synthesizer in a series of exercises defining a lesson, the exercises including a preview exercise which presents a graphic indicative of a quantity of unfamiliar vocabulary elements to be presented, a comprehension exercise, and a recall exercise wherein each exercise includes pausing for a time sufficient for the individual to generate a response to the at least one unfamiliar vocabulary element, evaluating the response based on a desired response criteria, and providing feedback to the individual using both the display device and the speech synthesizer.