SYSTEM AND METHOD FOR VARIABLE TEXT-TO-SPEECH WITH MINIMIZED DISTRACTION TO OPERATOR OF AN AUTOMOTIVE VEHICLE

• US 20100057464A1
• Filed: 08/29/2008
• Published: 03/04/2010
• Est. Priority Date: 08/29/2008
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Huang, Ritchie Winson, KIRSCH, DAVID MICHAEL
• Granted Patent: US 8,165,881 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: B60R 16/0373 Voice control in general G10L
• CPC Class Codes: G01C 21/3629 Guidance using speech or audio output, e.g. text-to-speech text to speech systems per se G10L13/00
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser

Abstract

A text-to-speech (TTS) system implemented in an automotive vehicle is dynamically tuned to increase intelligibility over a wide variety of vehicle operating states and environmental conditions by tuning characteristics of the synthesized voice in response to measured operating states. To decrease distractions to an operator of the vehicle, an embodiment of the invention prevents updates to the synthesized voice character from taking effect while a message phrase is being played. Instead, voice characteristics are updated only during natural phrase breaks. In another embodiment of the invention, a damping filter is applied to calculated changes in voice characteristics to prevent excessively rapid changes from being applied, reducing the likelihood of distracting the vehicle operator. In another embodiment of the invention, both phrase-break detectors and damping filters are employed.

Claims

1. A text-to-speech (TTS) control system for use in an automotive vehicle comprising:

at least one vehicle sensor adapted for measuring at least one operating state of the automotive vehicle;

a TTS voice synthesizer for synthesizing a TTS voice;

a TTS phrase database operatively coupled to the TTS voice synthesizer for providing data to be synthesized, the data comprising at least a plurality of phrases; and

a TTS processing engine comprising;

a TTS parameter database operatively coupled to the TTS voice synthesizer and adapted for storing at least one TTS voice parameter for controlling a characteristic of the TTS voice;

a TTS parameter calculation module operatively coupled to the at least one vehicle sensor and adapted for calculating a value of the at least one TTS voice parameter based on the at least one operating state of the automotive vehicle; and

a phrase break detector operatively coupled to the TTS phrase database and adapted for detecting at least one break in the plurality of phrases and for controlling an update of the at least one TTS voice parameter stored in the TTS parameter database with the value of the at least one TTS voice parameter calculated by the TTS parameter calculation module.

2. The TTS control system of claim 1, wherein the phrase break detector is further adapted for preventing the update of the at least one TTS voice parameter stored in the TTS parameter database when at least one of the plurality of phrases is being synthesized by the TTS voice synthesizer and for allowing the update of the at least one TTS voice parameter when none of the plurality of phrases is being synthesized by the TTS voice synthesizer

3. The TTS control system of claim 1, wherein the data provided by the TTS phrase database includes at least one control character for identifying the at least one break.

4. The TTS control system of claim 3, wherein the phrase break detector is further adapted for decoding the at least one control character to identify the at least one break.

5. The TTS control system of claim 1, wherein the phrase break detector is further adapted to parse the data provided by the TTS phrase database to identify the at least one break.

6. A text-to-speech (TTS) control system for use in an automotive vehicle comprising:

at least one vehicle sensor adapted for measuring at least one operating state of the automotive vehicle;

a TTS voice synthesizer for synthesizing a TTS voice;

a TTS phrase database operatively coupled to the TTS voice synthesizer for providing data to be synthesized; and

a TTS processing engine comprising;

a TTS parameter database operatively coupled to the TTS voice synthesizer and adapted for storing at least one TTS voice parameter for controlling a characteristic of the TTS voice;

a TTS parameter calculation module operatively coupled to the at least one vehicle sensor and adapted for calculating a value of the at least one TTS voice parameter based on the at least one operating state of the automotive vehicle; and

a TTS parameter damping module adapted for filtering the value of the at least one TTS voice parameter calculated by the TTS parameter calculation module and for controlling an update of the at least one TTS voice parameter stored in the TTS parameter database.

7. The TTS parameter damping module of claim 6, further comprising a moving-average filter adapted for averaging the value of the at least one TTS voice parameter calculated by the TTS parameter calculation module with values of the at least one TTS voice parameter calculated by the TTS parameter calculation module at previous times.

8. The TTS parameter damping module of claim 6, further comprising a slew rate limiter adapted for limiting a rate at which the value of the at least one TTS voice parameter calculated by the TTS parameter calculation module may change.

9. The TTS parameter damping module of claim 6, further comprising an exponential-time-decay filter for limiting a rate at which the value of the at least one TTS voice parameter calculated by the TTS parameter calculation module may change by the application of a decaying exponential time constant.

10. A text-to-speech (TTS) control system for use in an automotive vehicle comprising:

at least one vehicle sensor adapted for measuring at least one operating state of the automotive vehicle;

a TTS voice synthesizer for synthesizing a TTS voice;

a TTS phrase database operatively coupled to the TTS voice synthesizer for providing data to be synthesized, the data comprising at least a plurality of phrases; and

a TTS processing engine comprising;

a TTS parameter database operatively coupled to the TTS voice synthesizer and adapted for storing at least one TTS voice parameter for controlling a characteristic of the TTS voice;

a TTS parameter calculation module operatively coupled to the at least one vehicle sensor and adapted for calculating a value of the at least one TTS voice parameter based on the at least one operating state of the automotive vehicle;

a phrase break detector operatively coupled to the TTS phrase database and adapted for detecting at least one break in the plurality of phrases and for controlling an update of the at least one TTS voice parameter stored in the TTS parameter database; and

a TTS parameter damping module adapted for filtering the value of the at least one TTS voice parameter calculated by the TTS parameter calculation module and for further controlling the update of the at least one TTS voice parameter stored in the TTS parameter database.

11. The TTS control system of claim 10, wherein the phrase break detector is further adapted for preventing the update of the at least one TTS voice parameter stored in the TTS parameter database when at least one of the plurality of phrases is being synthesized by the TTS voice synthesizer and for allowing the update of the at least one TTS voice parameter when none of the plurality of phrases is being synthesized by the TTS voice synthesizer

12. The TTS control system of claim 10, wherein the data provided by the TTS phrase database includes at least one control character for identifying the at least one break.

13. The TTS control system of claim 12 wherein the phrase break detector is further adapted for decoding the at least one control characters to identify the at least one break.

14. The TTS control system of claim 10, wherein the phrase break detector is further adapted to parse the data provided by the TTS phrase database to identify the at least one break.

15. The TTS parameter damping module of claim 10, further comprising a moving-average filter adapted for averaging the value of the at least one TTS voice parameter calculated by the TTS parameter calculation module with values of the at least one TTS voice parameter calculated by the TTS parameter calculation module at previous times.

16. The TTS parameter damping module of claim 10, further comprising a slew rate limiter adapted for limiting a rate at which the value of the at least one TTS voice parameter calculated by the TTS parameter calculation module may change.

17. The TTS parameter damping module of claim 10, further comprising an exponential-time-decay filter for limiting a rate at which the value of the at least one TTS voice parameter calculated by the TTS parameter calculation module may change by the application of a decaying exponential time constant.

18. In an automotive vehicle equipped with a text-to-speech (TTS) control system adapted to adjust characteristics of a TTS voice in response to a measured state of the automotive vehicle, a method of adjusting at least one TTS voice characteristic while reducing distraction to an operator of the automotive vehicle includes the steps of:

measuring at least one operating state of the automotive vehicle;

calculating a value of at least one parameter characterizing the TTS voice to produce a calculated value based on the measured operating state of the automotive vehicle such that intelligibility of the TTS voice would be increased;

processing a message to be synthesized by the TTS voice synthesizer to detect at least one break within the message to be synthesized;

storing a processed value in a memory device wherein the processed value is equal to a previous value of the at least one parameter if the at least one break is not yet detected and is equal to the calculated value if the at least one break is detected; and

applying the processed value to a TTS voice synthesizer.

19. The method of claim 18, wherein the step of processing a message to be synthesized further comprises the step of identifying at least one control character within the message indicating the at least one break;

20. The method of claim 18, further comprising the steps of:

damping a change in the calculated value of the at least one parameter by applying a filtering operation to produce a damped value; and

setting the calculated value equal to the damped value;

21. The method of claim 20, wherein the step of damping a change in the calculated value further comprises the step of applying a moving-average filter to average the calculated value with at least one previous value of the at least one parameter to produce a damped value.

22. The method of claim 20, wherein the step of damping a change in the calculated value further comprises the step of applying a slew-rate-limiter to limit a maximum rate of change of calculated value with respect to previous values of the at least one parameter to produce a damped value.

23. The method of claim 20, wherein the step of damping a change in the calculated value further comprises the step of applying an exponential-time-decay filter to the calculated value to produce a damped value.

24. The method of claim 20 wherein the step of processing a message to be synthesized by the TTS voice synthesizer further comprises the step of identifying at least one control character within the message indicating the at least one break.

25. The method of claim 24, wherein the step of damping a change in the calculated value further comprises the step of applying a moving-average filter to average the calculated value with at least one previous value of the at least one parameter to produce a damped value.

26. The method of claim 24, wherein the step of damping a change in the calculated value further comprises the step of applying a slew-rate-limiter to limit a maximum rate of change of calculated value with respect to previous values of the at least one parameter to produce a damped value.

27. The method of claim 24, wherein the step of damping a change in the calculated value further comprises the step of applying an exponential-time-decay filter to the calculated value to produce a damped value.