Speech synthesis apparatus, speech synthesis method, speech synthesis program, portable information terminal, and speech synthesis system

• US 9,812,120 B2
• Filed: 03/25/2009
• Issued: 11/07/2017
• Est. Priority Date: 04/23/2008
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Mobile Communications Incorporated (Sony Group Corp.)
• Inventors: Takatsuka, Susumu
• Primary Examiner(s): Sharma, Neeraj
• Application Number:
  US12/411,031
• Publication Number:
  US 20090271202A1
• Time in Patent Office: 3,149 Days
• Field of Search: 704258, 704260, 704243, 704235, 704204, 704270, 709206, 379 8803, 379 8813, 455566, 4555501, 715744, 715236, 715205, 707102
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser

Abstract

A speech synthesis apparatus includes a content selection unit that selects a text content item to be converted into speech; a related information selection unit that selects related information which can be at least converted into text and which is related to the text content item selected by the content selection unit; a data addition unit that converts the related information selected by the related information selection unit into text and adds text data of the text to text data of the text content item selected by the content selection unit; a text-to-speech conversion unit that converts the text data supplied from the data addition unit into a speech signal; and a speech output unit that outputs the speech signal supplied from the text-to-speech conversion unit.

Claims

1. A speech synthesis apparatus comprising:

a receiver that receives an e-mail as a text content item;

a memory that stores the text content item to be converted into speech;

a content selection unit that selects the text content item to be converted into speech based on a vocal command from a user in which the user commands that the received e-mail be read aloud;

a related information selection unit that selects related information which can be at least converted into text and which is related to the text content item selected by the content selection unit, wherein the related information includes at least identification of a sender of the e-mail, and wherein when the name of the sender is locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the name of the sender is used as the identification of the sender, and when the name of the sender is not locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the e-mail address is used as the identification of the sender;

a data addition unit that converts the related information selected by the related information selection unit into text by inserting the related information into a predetermined type of phrase to form a text phrase, and adds text data of the text phrase to text data of the text content item selected by the content selection unit, wherein the predetermined type of phrase includes at least one predetermined location within the phrase at which the identification of the sender of the e-mail is inserted;

a text-to-speech conversion unit that converts the text data supplied from the data addition unit into a speech signal; and

a speech output unit that outputs the speech signal supplied from the text-to-speech conversion unit.

2. The speech synthesis apparatus according to claim 1,

wherein the related information selection unit selects music data related to the selected text content item, and

the speech output unit mixes the speech signal supplied from the text-to-speech conversion unit and a music signal of the music data and outputs a resulting signal.

3. The speech synthesis apparatus according to claim 1 or claim 2,

wherein the related information selection unit selects the related information which is related to the text content item selected by the content selection unit from among a plurality of pieces of related information which are related to a plurality of text content items capable of being selected by the content selection unit and which are recorded in advance.

4. The speech synthesis apparatus according to claim 1 or claim 2,

wherein the content selection unit selects a desired text content item from among a plurality of text content items on a network, and

the related information selection unit selects the related information which is related to the text content item selected by the content selection unit from among a plurality of pieces of related information which are related to a plurality of text content items capable of being selected by the content selection unit and which are stored on a network.

14. The speech synthesis apparatus according to claim 1, wherein the related information further includes at least one of a time relating to the text content item, a subject of the text content item, and a current time.

15. The speech synthesis apparatus according to claim 1, wherein the text phrase includes a salutation.

16. The speech synthesis apparatus according to claim 15, wherein the salutation is determined based on a current time.

5. A speech synthesis method comprising the steps of:

receiving an e-mail as a text content item;

selecting the text content item to be converted into speech, the text content item being selected by a content selection unit based on a vocal command from a user in which the user commands that the received e-mail be read aloud;

selecting related information which can be at least converted into text and which is related to the text content item selected by the content selection unit, the related information being selected by a related information selection unit, wherein the related information includes at least identification of a sender of the e-mail, and wherein when the name of the sender is locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the name of the sender is used as the identification of the sender, and when the name of the sender is not locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the e-mail address is used as the identification of the sender;

converting the related information selected by the related information selection unit into text by inserting the related information into a predetermined type of phrase to form a text phrase, and adding text data of the text phrase to text data of the text content item selected by the content selection unit, the conversion and addition being performed by a data addition unit, wherein the predetermined type of phrase includes at least one predetermined location within the phrase at which the identification of the sender of the e-mail is inserted;

converting text data supplied from the data addition unit into a speech signal, the conversion being performed by a text-to-speech conversion unit; and

outputting the speech signal supplied from the text-to-speech conversion unit, the speech signal being output by a speech output unit.

6. The speech synthesis method according to claim 5, further comprising the steps of:

selecting music data related to the selected text content item, the music data being selected by the related information selection unit; and

mixing the speech signal supplied from the text-to-speech conversion unit and a music signal of the music data and outputting a resulting signal, the mixing and outputting being performed by the speech output unit.

7. A non-transitory computer readable storage medium that stores a speech synthesis program, which when executed by a computer, causes the computer to function as:

a receiver that receives an e-mail as a text content item;

a content selection unit that selects the text content item to be converted into speech based on a vocal command from a user in which the user commands that the received e-mail be read aloud;

a related information selection unit that selects related information which can be at least converted into text and which is related to the text content item selected by the content selection unit, wherein the related information includes at least identification of a sender of the e-mail, and wherein when the name of the sender is locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the name of the sender is used as the identification of the sender, and when the name of the sender is not locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the e-mail address is used as the identification of the sender;

a data addition unit that converts the related information selected by the related information selection unit into text by inserting the related information into a predetermined type of phrase to form a text phrase, and adds text data of the text phrase to text data of the text content item selected by the content selection unit, wherein the predetermined type of phrase includes at least one predetermined location within the phrase at which the identification of the sender of the e-mail is inserted;

a text-to-speech conversion unit that converts text data supplied from the data addition unit into a speech signal; and

a speech output unit that outputs the speech signal supplied from the text-to-speech conversion unit.

8. The non-transitory computer readable storage medium according to claim 7,

wherein the related information selection unit selects music data related to the selected text content item, and

the speech output unit mixes the speech signal supplied from the text-to-speech conversion unit and a music signal of the music data and outputs a resulting signal.

9. A portable information terminal comprising:

a receiver that receives an e-mail as a text content item;

a command input unit that obtains a vocal command input by a user;

a content selection unit that selects the text content item to be converted into speech in accordance with the command input by the user in which the user commands that the received e-mail be read aloud;

a related information selection unit that selects related information which can be at least converted into text and which is related to the text content item selected by the content selection unit, wherein the related information includes at least identification of a sender of the e-mail, and wherein when the name of the sender is locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the name of the sender is used as the identification of the sender, and when the name of the sender is not locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the e-mail address is used as the identification of the sender;

a data addition unit that converts the related information selected by the related information selection unit into text by inserting the related information into a predetermined type of phrase to form a text phrase, and adds text data of the text phrase to text data of the text content item selected by the content selection unit, wherein the predetermined type of phrase includes at least one predetermined location within the phrase at which the identification of the sender of the e-mail is inserted;

a text-to-speech conversion unit that converts text data supplied from the data addition unit into a speech signal; and

a speech output unit that outputs the speech signal supplied from the text-to-speech conversion unit.

10. The portable information terminal according to claim 9,

wherein the related information selection unit selects music data related to the selected text content item, and

the speech output unit mixes the speech signal supplied from the text-to-speech conversion unit and a music signal of the music data and outputs a resulting signal.

11. A speech synthesis system comprising:

a receiver that receives an e-mail as a text content item;

a selection and addition apparatus that selects the text content item to be converted into speech in accordance with a vocal command input by a user, selects related information which can be at least converted into text and which is related to the selected text content item, converts the selected related information into text by inserting the related information into a predetermined type of phrase to form a text phrase, and adds text data of the text phrase to text data of the selected text content item in accordance with the command input by the user in which the user commands that the received e-mail be read aloud;

a text-to-speech conversion apparatus that converts the text data supplied from the selection and addition apparatus into a speech signal; and

a speech output apparatus that outputs, into the air, speech corresponding to the speech signal supplied from the text-to-speech conversion apparatus,

wherein the related information includes at least identification of a sender of the e-mail,

wherein when the name of the sender is locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the name of the sender is used as the identification of the sender, and when the name of the sender is not locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the e-mail address is used as the identification of the sender, and

wherein the predetermined type of phrase includes at least one predetermined location within the phrase at which the identification of the sender of the e-mail is inserted.

12. The speech synthesis system according to claim 11,

wherein the selection and addition apparatus selects music data related to the selected text content item, and

the speech output apparatus mixes the speech signal supplied from the text-to-speech conversion apparatus and a music signal of the music data and outputs speech according to a mixed speech signal.

13. The speech synthesis system according to claim 11,

wherein the selection and addition apparatus selects a music signal related to the selected text content item, and

the speech output apparatus includes a device that outputs, into the air, speech according to the speech signal supplied from the text-to-speech conversion apparatus and a device that outputs, into the air, music according to the music signal supplied from the selection and addition apparatus.

17. A speech synthesis apparatus comprising:

a processor;

a network interface unit that receives an e-mail as a text content item to be converted into speech from an external device;

a command input unit that obtains a vocal command input by a user;

a content selection unit that selects the text content item to be converted into speech in accordance with the command input by the user in which the user commands that the received e-mail be read aloud;

a related information selection unit, implemented by the processor, that selects related information which can be at least converted into text and which is related to the text content item received by the network interface unit, wherein the related information includes at least identification of a sender of the e-mail, and wherein when the name of the sender is locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the name of the sender is used as the identification of the sender, and when the name of the sender is not locally stored in association with an e-mail address of the sender prior to receipt of the e-mail, the e-mail address is used as the identification of the sender;

a data addition unit that converts the related information selected by the related information selection unit into text by inserting the related information into a predetermined type of phrase to form a text phrase, and adds text data of the text phrase to text data of the received text content item, wherein the predetermined type of phrase includes at least one predetermined location within the phrase at which the identification of the sender of the e-mail is inserted;

a text-to-speech conversion unit that converts the text data supplied from the data addition unit into a speech signal; and

a speech output unit that audibly outputs the speech signal supplied from the text-to-speech conversion unit.