EMOTIVE TEXT-TO-SPEECH SYSTEM AND METHOD

• US 20090063154A1
• Filed: 11/05/2008
• Published: 03/05/2009
• Est. Priority Date: 04/26/2007
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Gusikhin, Oleg Yurievitch, Theisen, Kacie Alane, Filev, Dimitar Petrov, MacNeille, Perry Robinson, Klampfl, Erica, Chen, Yifan, Tonshal, Basavaraj
• Granted Patent: US 9,495,787 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: A61B 5/163 by tracking eye movement, gaze, or pupil change
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/4803 Speech analysis specially adapted for diagnostic purposes
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/744 Displaying an avatar, e.g. an animated cartoon character
• CPC Class Codes: B60W 2040/089 Driver voice
• CPC Class Codes: B60W 50/10 Interpretation of driver requests or demands
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G06F 2203/011 Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06T 13/205 driven by audio data
• CPC Class Codes: G06T 13/40 of characters, e.g. humans, animals or virtual beings
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

Information about a device may be emotively conveyed to a user of the device. Input indicative of an operating state of the device may be received. The input may be transformed into data representing a simulated emotional state. Data representing an avatar that expresses the simulated emotional state may be generated and displayed. A query from the user regarding the simulated emotional state expressed by the avatar may be received. The query may be responded to.

Claims

1. An emotive text-to-speech system comprising:

a computer configured to

receive data representing a text stream;

receive data representing a simulated emotion to be expressed by an audio output;

selectively embed at least a portion of the data representing the simulated emotion in the data representing the text stream to form data representing an emotive text stream, the emotive text stream representing a spoken phrase having simulated emotional content; and

output the data representing the emotive text stream for play by the audio output.

2. The system of claim 1 wherein the computer is further configured to parse the data representing the text stream into data representing parsed words.

3. The system of claim 2 wherein the computer is further configured to determine which of the data representing the parsed words are data representing emotive words.

4. The system of claim 3 wherein determining which of the data representing the parsed words are data representing emotive words includes comparing the data representing each of the parsed words with data representing a predetermined set of emotive words.

5. The system of claim 4 wherein the data representing each of the predetermined set of emotive words is linked with data representing at least one emotion.

6. A method of performing emotive text-to-speech synthesis comprising:

receiving data representing a text stream;

parsing at least a portion of the data representing the text stream into data representing parsed words;

identifying data representing at least one of the parsed words to be tagged with data representing an emotional marker; and

tagging the identified data representing at least one of the parsed words with the data representing the emotional marker to form data representing an emotively tagged text stream for playback.

7. The method of claim 6 wherein identifying data representing at least one of the parsed words to be tagged with data representing an emotional marker includes comparing the data representing each of the parsed words with data representing a plurality of emotive words.

8. The method of claim 6 further comprising receiving data representing an emotion to be expressed by an output.

9. The method of claim 8 wherein the data representing each of the plurality of emotive words is linked with data representing at least one emotion.

10. The method of claim 9 wherein identifying data representing at least one of the parsed words to be tagged with data representing an emotional marker includes comparing the data representing the emotion to be expressed by the output with the data representing the at least one emotion.

11. The method of claim 6 further comprising playing the data representing the emotively tagged text stream.

12. A method of performing emotive text-to-speech synthesis comprising:

receiving data representing a text stream;

receiving data representing an emotion to be expressed by an avatar;

parsing at least a portion of the data representing the text stream into data representing parsed words;

determining whether the data representing each of the parsed words matches data representing at least one of a predetermined set of emotive words, the data representing each of the predetermined set of emotive words being linked with data representing at least one emotion; and

assigning at least a portion of the data representing the emotion to be expressed by the avatar to the data representing at least one of the parsed words to form data representing an emotive text stream for playback.

13. The method of claim 12 further comprising determining whether the data representing the emotion to be expressed by the avatar matches the data representing the at least one emotion.

14. An emotive text-to-speech system comprising:

a computer configured to

receive data representing a stream of text;

edit the data representing the stream of text with data representing emotional tags to form data representing a stream of emotively tagged text; and

output the data representing the stream of emotively tagged text for playback, the stream of emotively tagged text representing a spoken phrase having simulated emotional content.

15. The system of claim 14 wherein the computer is further configured to receive data representing an emotion to be expressed by an audio output.

16. The system of claim 15 wherein the computer is further configured to select the data representing the emotional tags based on the data representing the emotion to be expressed by the audio output.

17. The system of claim 14 wherein the computer is further configured to parse the data representing the stream of text into data representing parsed words.

18. The system of claim 17 wherein editing the data representing the stream of text with data representing emotional tags to form data representing a stream of emotively tagged text includes comparing the data representing the parsed words with data representing emotive words.

19. An emotive text-to-speech system comprising:

means for receiving data representing a stream of text;

means for editing the data representing the stream of text with data representing emotional tags to form data representing a stream of emotively tagged text; and

means for outputting the data representing the stream of emotively tagged text for playback, the stream of emotively tagged text representing a spoken phrase having simulated emotional content.

20. The system of claim 19 further comprising means for playing the stream of emotively tagged text.