What is claimed:
1. A method for modifying synthesized speech, the method including the steps of:
generating synthesized speech based on textual input and a plurality of run-time control parameter values;
generating real-time data based on an input signal, the input signal characterizing an intelligibility of the speech with regard to a listener; and
modifying one or more of the run-time control parameter values based on the real-time data such that the intelligibility of the speech increases.
2. The method of claim 1 further including the step of generating the real-time data based on background noise contained in an environment in which the speech is reproduced.
3. The method of claim 2 further including the steps of:
converting the background noise into an electrical signal;
retrieving one or more interference models from a model database; and
characterizing the background noise with the real-time data based on the electrical signal and the interference models.
4. The method of claim 3 further including the step of performing a time domain analysis on the electrical signal.
5. The method of claim 3 further including the step of performing a frequency domain analysis on the electrical signal.
6. The method of claim 3 wherein the characterizing step is selected from the group consisting essentially of the steps of:
identifying high level interference in the background noise;
identifying low level interference in the background noise;
identifying momentary interference in the background noise;
identifying continuous interference in the background noise;
identifying varying interference in the background noise;
identifying stationary interference in the background noise;
identifying spatial locations of sources of the background noise;
identifying potential sources of the background noise; and
identifying speech in the background noise.
7. The method of claim 1 further including the steps of:
receiving the real-time data;
identifying relevant characteristics of the speech based on the real-time data, the relevant characteristics having corresponding run-time control parameters; and
applying adjustment values to parameter values of the control parameters such that the relevant characteristics of the speech change in a desired fashion.
8. The method of claim 7 further including the step of changing relevant speaker characteristics of the speech.
9. The method of claim 8 further including the step of changing relevant voice characteristics of the speech.
10. The method of claim 9 further including the step of changing characteristics selected from the group consisting essentially of:
speech rate;
pitch;
volume;
parametric equalization;
formant frequencies and bandwidths;
glottal sources;
speech power spectrum tilt;
gender;
age; and
identity.
11. The method of claim 8 further including the step of changing relevant speaking style characteristics of the speech.
12. The method of claim 11 further including the step of changing characteristics selected from the group consisting essentially of:
dynamic prosody; and
articulation.
13. The method of claim 7 further including the step of changing relevant emotion characteristics of the speech.
14. The method of claim 13 further including the step of changing an urgency characteristic of the speech.
15. The method of claim 7 further including the step of changing relevant dialect characteristics of the speech.
16. The method of claim 15 further including the step of changing characteristics selected from the group consisting essentially of:
pronunciation; and
articulation.
17. The method of claim 7 further including the step of changing relevant content characteristics of the speech.
18. The method of claim 17 further including the step of changing characteristics selected from the group consisting essentially of:
repetition;
redundancy; and
vocabulary.
19. The method of claim 1 further including the step of using polyphonic audio processing to spatially reposition the speech based on the real-time data.
20. The method of claim 1 further including step of generating the real-time data based on listener input.
21. The method of claim 1 further including the step of using the synthesized speech in an automotive application.
22. A method for modifying one or more speech synthesizer run-time control parameters, the method comprising the steps of:
receiving real-time data;
identifying relevant characteristics of synthesized speech based on the real-time data, the relevant characteristics having corresponding run-time control parameters; and
applying adjustment values to parameter values of the control parameters such that the relevant characteristics of the speech change in a desired fashion.
23. The method of claim 22 further including the step of changing relevant speaker characteristics of the speech.
24. The method of claim 23 further including the step of changing relevant voice characteristics of the speech.
25. The method of claim 23 further including the step of changing relevant speaking style characteristics of the speech.
26. The method of claim 22 further including the step of changing relevant emotion characteristics of the speech.
27. The method of claim 22 further including the step of changing relevant dialect characteristics of the speech.
28. The method of claim 22 further including the step of changing relevant content characteristics of the speech.
29. A speech synthesizer adaptation system comprising:
a text-to-speech synthesizer for generating speech based on textual input and a plurality of run-time control parameter values;
an audio input system for generating real-time data based on background noise contained in an environment in which the speech is reproduced; and
an adaptation controller operatively coupled to the synthesizer and the audio input system, the adaptation controller modifying one or more of the run-time control parameter values based on the real-time data such that interference between the background noise and the speech is reduced.
30. The adaptation system of claim 29 wherein the audio input system includes an acoustic-to-electric signal converter.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. Architecture for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) comprising a communication interface and processing circuitry to in real-time:
receive a data stream of an intensity image via the communication interface;
provide labels for light image regions and dark image regions within the intensity image for a given intensity threshold t;
find extremal regions within the intensity image based upon the labels; and
determine MSER ellipses parameters based on the extremal regions and MSER criteria.
2. The architecture of claim 1 wherein the processing circuitry is configured to substantially simultaneously provide the labels for the light image regions and the dark image regions within the intensity image for the given intensity threshold t.
3. The architecture of claim 1 wherein the processing circuitry is configured to provide the labels for the light image regions and the dark image regions within the intensity image during a single processing pass for the given intensity threshold t.
4. The architecture of claim 1 wherein the MSER criteria include a nested MSER tolerance value.
5. The architecture of claim 4 wherein the MSER criteria further include a minimum MSER area, a maximum MSER area, and an acceptable growth rate value for MSER areas.
6. The architecture of claim 1 wherein the MSER ellipses parameters include a center of gravity, a major axis length, a minor axis length, and an angle of the major axis length with respect to a horizontal axis.
7. The architecture of claim 1 wherein the processing circuitry includes MSER moments calculator hardware configured to calculate MSER moments.
8. The architecture of claim 7 wherein the processing circuitry further includes elliptical fit approximator hardware configured to receive the MSER moments from the MSER moments calculator hardware and fit an MSER ellipse to an extremal region based upon the MSER moments.
9. The architecture of claim 1 wherein the processing circuitry includes union-find hardware configured to provide the labels for light image regions and dark image regions within the intensity image for the given intensity threshold t.
10. The architecture of claim 9 wherein the processing circuitry includes extremal region find hardware that is configured to receive the labels for the image regions and find extremal regions based upon the labels for the light image regions and the dark image regions.
11. The architecture of claim 10 wherein the extremal region find hardware is configured to find extremal regions using a mathematical relationship q(t)=|(t+\u0394)\\(t\u2212\u0394)||(t)| where each extremal region’s cardinality, |(t)| is a function of the intensity threshold t and an intensity threshold increment \u0394.
12. The architecture of claim 1 wherein the processing circuitry includes MSER selector hardware configured to automatically select MSERs based upon the MSER criteria.
13. Architecture for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) comprising:
intensity image process hardware configured to receive a data stream of an intensity image and output labels for light image regions and dark image regions within the intensity image for a given intensity threshold t;
extremal regions find hardware configured to receive the labels for the intensity image and find extremal regions within the intensity image; and
MSER process hardware configured to receive MSER criteria and output MSER ellipses parameters based upon the extremal regions.
14. The architecture of claim 13 wherein the intensity image process hardware is configured to substantially simultaneously provide the labels for the light image regions and the dark image regions within the intensity image for the given intensity threshold t.
15. The architecture of claim 13 wherein the intensity image process hardware is configured to provide the labels for the light image regions and the dark image regions within the intensity image during a single processing pass for the given intensity threshold t.
16. The architecture of claim 13 wherein the MSER criteria include a nested MSER tolerance value.
17. The architecture of claim 16 wherein the MSER criteria further include a minimum MSER area value, a maximum MSER area value, and an acceptable growth rate value for MSER areas.
18. The architecture of claim 13 wherein the MSER ellipses parameters include a center of gravity, a major axis length, a minor axis length, and an angle of the major axis length with respect to a horizontal axis.
19. The architecture of claim 13 wherein the extremal regions find hardware is configured to find extremal regions using a mathematical relationship q(t)=|(t+\u0394)\\(t\u2212\u0394)||(t)|, where each extremal region’s cardinality, |(t)| is a function of the intensity threshold t and the intensity threshold increment \u0394.
20. The architecture of claim 13 wherein the intensity image process hardware includes union-find hardware configured to provide the labels for the light image regions and the dark image regions within the intensity image for a given intensity threshold t.
21. The architecture of claim 20 wherein the intensity image process hardware further includes labeled region seeds updaterunifier hardware configured to prevent a seed that is a first pixel location within the intensity image from being stored in a seed list if the seed is presently stored in the seed list.
22. The architecture of claim 21 further including region map updater hardware configured to store a value of (t+\u0394), (t), and (t\u2212\u0394) for each seed, where t is the intensity threshold and \u0394 is an increment of the intensity threshold t.
23. The architecture of claim 13 wherein the intensity image process hardware, the extremal regions find hardware, and the MSER process hardware are fabricated on a single application specific integrated circuit (ASIC).
24. The architecture of claim 13 wherein the intensity image process hardware, the extremal regions find hardware and the MSER process hardware are implemented on a single field programmable gate array (FPGA).
25. A method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via processing circuitry comprising:
receiving a data stream of an intensity image via a communication interface in communication with the processing circuitry;
generating labels for light image regions and dark image regions within the intensity image for a given intensity threshold t in real-time via the processing circuitry;
finding extremal regions within the intensity image based upon the labels in real-time via the processing circuitry; and
determining MSER ellipses parameters based on the extremal regions and MSER criteria in real-time via the processing circuitry.
26. The method of claim 25 wherein generating the labels for the light image regions and generating labels for the dark image regions occurs substantially simultaneously.
27. The method of claim 25 wherein generating the labels for the light image regions and generating labels for the dark image regions occurs during a single processing pass for the given intensity threshold t.
28. The method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via the processing circuitry of claim 25 wherein the MSER criteria include a nested MSER tolerance value.
29. The method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via the processing circuitry of claim 28 wherein the MSER criteria further include a minimum MSER area, a maximum MSER area, and an acceptable growth rate value for MSER areas.
30. The method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via the processing circuitry of claim 25 wherein the MSER ellipses parameters include a center of gravity, a major axis length, a minor axis length, and an angle of the major axis length with respect to a horizontal axis.
31. The method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via the processing circuitry of claim 25 wherein the processing circuitry includes MSER moments calculator hardware configured to calculate MSER moments.
32. The method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via the processing circuitry of claim 31 wherein the processing circuitry further includes elliptical fit approximator hardware configured to receive MSER moments from the MSER moments calculator hardware and fit an MSER ellipse to an extremal region based upon the MSER moments.
33. The method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via the processing circuitry of claim 25 wherein the processing circuitry includes union-find hardware configured to provide the labels for the light image regions and dark image regions within the intensity image that match a given intensity threshold t.
34. The method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via the processing circuitry of claim 31 wherein the processing circuitry includes extremal region find hardware that is configured to receive the labels for the light image regions and the dark image regions and find extremal regions based upon the labels for the light image regions and the dark image regions.
35. The method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via the processing circuitry of claim 34 wherein the extremal region find hardware is configured to find extremal regions using a mathematical relationship q(t)=|(t+\u0394)\\(t\u2212\u0394)||(t)| where each extremal region’s cardinality |(t)| is a function of the intensity threshold t and the intensity threshold increment \u0394.
36. The method for real-time parallel detection and extraction of maximally stable extremal regions (MSERs) via the processing circuitry of claim 25 wherein the processing circuitry includes MSER selector hardware configured to automatically select MSERs based upon the MSER criteria.