Information processing apparatus, information processing method, recording medium, and program

• US 6,996,530 B2
• Filed: 05/09/2002
• Issued: 02/07/2006
• Est. Priority Date: 05/10/2001
• Status: Expired due to Fees

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Kato, Yasuhiko, Fujimura, Satoshi, Shizuka, Utaha
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US10/142,560
• Publication Number:
  US 20020184004A1
• Time in Patent Office: 1,370 Days
• Field of Search: 704/255, 704/258, 704/260, 704/270, 379/88.01
• US Class Current: 704/260
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems

Abstract

Two types of voice can be set for reading text data of an electronic mail. A user selects a detailed setting button associated with one of the voice types to display a voice setting window, in which setting for the voice can be made individually. A drop-down list box include preset voice types such as woman, man, child, robot, and alien, and also names of voice types corresponding to phonemes created by the user, allowing selection thereof. In relation to a voice selected from the drop-down list box, reading speed, voice pitch, and strength of stress are set according to positions of setting levers.

Claims

1. An information processing apparatus comprising:

a text input mechanism configured to input text data;

a first display control configured to control display of a first display screen that aids a user to enter setting for speech synthesis;

a first setting input mechanism configured to control input of information representing the setting for speech synthesis, entered by the user with reference to the first display screen, display of which is controlled by said first display control;

a phoneme data holder configured to hold at least one kind of phoneme data used for speech synthesis;

a generator configured to divide the text data input via said text input means according to a predetermined rule to generate a plurality of text groups, the plurality of text groups including at least one phrase having more than one word; and

a speech synthesizer configured to execute speech synthesis using the phoneme data held in said phoneme data holder based on the setting for speech synthesis, input via said first setting input, to generate speech data corresponding to the text data;

wherein said first setting input means receives input of a plurality of settings for speech synthesis, and said speech synthesizer executes speech synthesis to generate speech data of different speech properties for adjacent ones of the plurality of text groups based on the plurality of settings for speech synthesis, input via said first setting input.

2. An information processing apparatus according to claim 1, further comprising a speech output mechanism configured to output the speech data generated by the speech synthesis by said speech synthesizer.

3. An information processing apparatus according to claim 2, further comprising a second display control configured to control display of text corresponding to the speech output by said speech output.

4. An information processing apparatus according to claim 1, further comprising an output mechanism configured to output the speech data generated by the speech synthesis by said speech synthesizer to an external recording apparatus or an external recording medium.

5. An information processing apparatus according to claim 4, further comprising a format converter configured to convert the speech data from a first format, in which the speech data is represented, into a second format, which allows recording on the external recording apparatus or the external recording medium, if the first format differs from the second format.

6. An information processing apparatus according to claim 1, wherein the information representing the setting for speech synthesis includes at least one of speed, voice pitch, and strength of stress for reading the phoneme data.

7. An information processing apparatus according to claim 1, wherein said text input mechanism receives input of text data corresponding to a body of an electronic mail, and said generator generates a plurality of text groups based on whether a predetermined symbol is present at the beginning of each line in the body of the electronic mail.

8. An information processing apparatus according to claim 1, wherein said text input mechanism receives input of text data corresponding to a body of an electronic mail, and said generator generates a plurality of text groups based on whether a predetermined symbol is present, and the number of occurrences of the symbol, at the beginning of each line in the body of the electronic mail.

9. An information processing apparatus according to claim 1, wherein said text input mechanism receives input of text data corresponding to a body of an electronic mail, and said generator generates a plurality of text groups based on whether each portion of the body of the electronic mail is a quotation or not.

10. An information processing apparatus according to claim 1, wherein said text input mechanism receives input of text data corresponding to a body of an electronic mail written in a markup language, and said generator generates a plurality of text groups based on tag information included in the electronic mail.

11. An information processing apparatus according to claim 1, further comprising:

a third display control configured to control display of a second display screen that aids the user to set details of the phoneme data;

a second setting input mechanism configured to receive input of information representing the details of the phoneme data, entered by the user with reference to the second display screen, display of which is controlled by said third display control; and

a registrator configured to register the information representing the details of the phoneme data, input via said second setting input mechanism, in said phoneme data holder.

12. An information processing method comprising:

receiving input of text data;

controlling display of a display screen that aids a user to enter setting for speech synthesis;

receiving input of information representing the setting for speech synthesis, entered by the user with reference to the display screen;

holding step of holding at least one kind of phoneme data used for speech synthesis;

dividing the received text data input according to a predetermined rule to generate a plurality of text groups, the plurality of text groups including at least one phrase having more than one word; and

executing speech synthesis using the held phoneme data based on the setting for speech synthesis, to generate speech data corresponding to the text data;

wherein input of a plurality of settings for speech synthesis is received in receiving input of information representing the setting for speech synthesis, and speech synthesis is executed to generate speech data of different speech properties for adjacent ones of the plurality of text groups based on the plurality of settings for speech synthesis.

13. A recording medium having recorded thereon a computer-readable program comprising instructions to:

receive input of text data;

control display of a display screen that aids a user to enter a setting for speech synthesis;

receive input of information representing the setting for speech synthesis, entered by the user with reference to the display screen;

hold at least one kind of phoneme data used for speech synthesis;

divide the text data input according to a predetermined rule to generate a plurality of text groups, the plurality of text groups including at least one phrase having more than one word; and

execute speech synthesis using the held phoneme data based on the setting for speech synthesis, to generate speech data corresponding to the text data;

wherein input of a plurality of settings for speech synthesis is received in receiving input of information representing the setting for speech synthesis and speech synthesis is executed to generate speech data of different speech properties for adjacent ones of the plurality of text groups based on the plurality of settings for speech synthesis, input in said setting input step.