Method for displaying words and processing device and computer program product thereof

1. A method for displaying words, comprising:

receiving a speech signal;

extracting a pitch contour of the speech signal;

extracting an energy contour of the speech signal;

performing speech recognition on the speech signal to recognize a plurality of words corresponding to the speech signal and determine time alignment information of each of the plurality of words;

determining at least one display parameter of each of the plurality of words according to the pitch contour, the energy contour and the time alignment information of each of the plurality of words;

integrating the plurality of words into a sentence according to the at least one display parameter of each of the plurality of words; and

outputting the sentence to be displayed on at least one display device.

2. The method as claimed in claim 1 , wherein the at least one display parameter comprises a position parameter, a size parameter and a distance parameter.

3. The method as claimed in claim 2 , further comprising:

capturing a facial image via a video camera;

determining facial expression intensity according to the facial image; and

determining whether to insert at least one first emoticon into the sentence according to the facial expression intensity.

4. The method as claimed in claim 3 , further comprising:

calculating a plurality of Mel-scale frequency cepstral coefficients of the speech signal;

calculating energy of the speech signal according to the plurality of Mel-scale frequency cepstral coefficients to obtain the energy contour; and

performing the speech recognition on the speech signal according to the plurality of Mel-scale frequency cepstral coefficients to recognize the plurality of words and determine the time alignment information of each of the plurality of words.

5. The method as claimed in claim 4 , wherein the time alignment information of each of the plurality of words comprises a starting time and an ending time in the speech signal of each of the plurality of words.

6. The method as claimed in claim 5 , further comprising:

determining the distance parameter of each of the plurality of words according to a time difference between the starting time and the ending time of each of the plurality of words.

7. The method as claimed in claim 6 , further comprising:

calculating an average energy of each of the plurality of words according to the energy contour between the starting time and the ending time of each of the plurality of words; and

determining the size parameter of each of the plurality of words according to the average energy of each of the plurality of words.

8. The method as claimed in claim 7 , further comprising:

calculating a regression line of each of the plurality of words according to the pitch contour between the starting time and the ending time of each of the plurality of words; and

determining the position parameter of each of the plurality of words according to a slope of the regression line of each of the plurality of words.

9. The method as claimed in claim 8 , further comprising:

determining whether to insert at least one second emoticon into a position in the sentence near at least one word the plurality of words according to the average energy of the at least one word and the slope of the regression line of the at least one word; and

if so, determining the at least one second emoticon according to the average energy of the at least one word and the slope of the regression line of the at least one word.

10. A processing device, comprising:

a speech input unit, receiving a speech signal;

a processor, comprising:

a pitch extracting module, extracting a pitch contour of the speech signal;

an energy calculating module, extracting an energy contour of the speech signal;

a speech recognition engine, performing speech recognition on the speech signal to recognize a plurality of words corresponding to the speech signal and determine time alignment information of each of the plurality of words; and

a text processing module, determining at least one display parameter of each of the plurality of words according to the pitch contour, the energy contour and the time alignment information of each of the plurality of words and integrating the plurality of words into a sentence according to the at least one display parameter of each of the plurality of words; and

a text output unit, outputting the sentence to be displayed on at least one display device.

11. The processing device as claimed in claim 10 , wherein the at least one display parameter comprises a position parameter, a size parameter and a distance parameter.

12. The processing device as claimed in claim 11 further comprising:

an image input unit, capturing an image,

wherein the processor further comprises:

a face recognition module, performing face recognition on the image to retrieve a facial image;

a facial feature extracting module, extracting a facial feature of the facial image; and

an expression parameter module, determining facial expression intensity according to the facial feature, and

wherein the text processing module further determines whether to insert at least one first emoticon into the sentence according to the facial expression intensity.

13. The processing device as claimed in claim 12 , wherein the processor further comprises:

a Mel-scale frequency cepstral coefficient (MFCC) module, calculating a plurality of Mel-scale frequency cepstral coefficients of the speech signal,

wherein the energy calculating module calculates energy of the speech signal according to the plurality of Mel-scale frequency cepstral coefficients to obtain the energy contour, and

wherein the speech recognition engine recognizes the plurality of words and determines the time alignment information of each of the plurality of words according to the plurality of Mel-scale frequency cepstral coefficients.

14. The processing device as claimed in claim 13 , wherein the time alignment information of each of the plurality of words comprises a starting time and an ending time in the speech signal of each of the plurality of words.

15. The processing device as claimed in claim 14 , wherein the text processing module determines the distance parameter of each of the plurality of words according to a time difference between the starting time and the ending time of each of the plurality of words.

16. The processing device as claimed in claim 15 , wherein the text processing module calculates an average energy of each of the plurality of words according to the energy contour between the starting time and the ending time of each of the plurality of words and determines the size parameter of each of the plurality of words according to the average energy of each of the plurality of words.

17. The processing device as claimed in claim 16 , wherein the text processing module calculates a regression line of each of the plurality of words according to the pitch contour between the starting time and the ending time of each of the plurality of words and determines the position parameter of each of the plurality of words according to a slope of the regression line of each of the plurality of words.

18. The processing device as claimed in claim 17 , wherein the text processing module determines whether to insert at least one second emoticon into a position in the sentence near at least one word of the plurality of words according to the average energy of the at least one word and the slope of the regression line of the at least one word, and if so, the text processing module determines the at least one second emoticon according to the average energy of the at least one word and the slope of the regression line of the at least one word.

19. A computer program product embodied in a non-transitory computer-readable storage medium, wherein the computer program product is loaded into and executed by an electronic device for performing a method for displaying words, the computer program product comprising:

a first code for receiving a speech signal;

a second code for extracting a pitch contour of the speech signal;

a third code for extracting an energy contour of the speech signal;

a fourth code for performing speech recognition on the speech signal to recognize a plurality of words corresponding to the speech signal and determine time alignment information of each of the plurality of words;

a fifth code for determining at least one display parameter of each of the plurality of words according to the pitch contour, the energy contour and the time alignment information of each of the plurality of words; and

a sixth code for integrating the plurality of words into a sentence according to the at least one display parameter of each of the plurality of words and outputting the sentence to be displayed on at least one display device.

20. The computer program product as claimed in claim 19 , further comprising:

a seventh code for capturing a facial image via a video camera;

an eighth code for determining facial expression intensity according to the facial image; and

a ninth code for determining whether to insert at least one first emoticon into the sentence according to the facial expression intensity.