Text-to-speech apparatus and method, browser, and user terminal
View Patent ↗A text-to-speech method includes outputting an instruction according to voice information entered by a user; obtaining text information according to the instruction; converting the text information to audio; and playing the audio. According to the embodiments of the present invention, news or other text content in a browser can be played by voice, which liberates hands and eyes of a user. The user can use the browser in some scenarios where the user cannot easily use the browser, such as driving a car, thereby improving user experience.
1. A text-to-speech method, implemented by a user terminal having a browser, wherein the text-to-speech method comprises:
receiving first voice information entered by a user, wherein the first voice information comprises a participle of a verb;
determining a function requested in the first voice information entered by the user by analyzing the participle of the verb;
obtaining a set of prestored instructions based on the function requested in the first voice information entered by the user;
obtaining a first prompt voice based on the set of prestored instructions;
feeding back the first prompt voice to prompt the user for second voice information comprising an adjective corresponding to the set of prestored instructions;
receiving the second voice information comprising the adjective that is entered by the user in response to the first prompt voice;
searching a memory of the user terminal for a prestored instruction from the set of prestored instructions which matches the second voice information comprising the adjective entered by the user;
outputting the prestored instruction according to the second voice information comprising the adjective entered by the user;
obtaining text information according to the prestored instruction, by:
determining whether the text information is prestored in the user terminal;
in response to determining that the text information is prestored in the user terminal, obtaining the text information from the user terminal according to the prestored instruction; and
in response to determining that the text information is not stored in the user terminal, obtaining the text information from a server according to the prestored instruction;
obtaining prestored audio information according to the text information; and
playing the prestored audio information.
2. The text-to-speech method according to claim 1 , wherein the text-to-speech method further comprises loading the text information to a web page of the browser.
3. The text-to-speech method according to claim 1 , wherein the prestored audio information was obtained by:
partitioning the text information into words or phrases;
searching an audio library for multiple audio segments corresponding to the words or the phrases;
synthesizing the multiple audio segments into audio information; and
storing the audio information.
4. The text-to-speech method according to claim 1 , wherein the text-to-speech method further comprises playing a second prompt voice after playing of the audio is completed.
5. The text-to-speech method of claim 1 , wherein the obtaining prestored audio information according to the text information comprises obtaining the prestored audio information without converting the text information to an audio.
6. The text-to-speech method of claim 1 , further comprising:
in response to determining that the prestored audio information is not available, converting the text information to an audio.
7. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor of a computer system, cause the computer system to perform a method comprising:
receiving first voice information entered by a user, wherein the first voice information comprises a participle of a verb;
determining a function requested in the first voice information entered by the user by analyzing the participle of the verb;
obtaining a set of prestored instructions based on the function requested in the first voice information entered by the user;
obtaining a first prompt voice based on the set of prestored instructions;
feeding back the first prompt voice to prompt the user for second voice information comprising an adjective corresponding to the set of prestored instructions;
receiving the second voice information comprising the adjective that is entered by the user in response to the first prompt voice;
searching a memory of the user terminal for a prestored instruction from the set of prestored instructions which matches the second voice information comprising the adjective entered by the user;
outputting the prestored instruction according to the second voice information comprising the adjective entered by the user;
obtaining text information according to the prestored instruction, by:
determining whether the text information is prestored in the user terminal;
in response to determining that the text information is prestored in the user terminal, obtaining the text information from the user terminal according to the prestored instruction; and
in response to determining that the text information is not stored in the user terminal, obtaining the text information from a server according to the prestored instruction;
obtaining prestored audio information according to the text information; and
playing the prestored audio information.
8. The non-transitory computer-readable storage medium according to claim 7 , wherein the method further comprises loading the text information to a web page of a browser.
9. The non-transitory computer-readable storage medium according to claim 7 , wherein the method further comprises:
obtaining the prestored audio information by:
partitioning the text information into words or phrases;
searching an audio library for multiple audio segments corresponding to the words or the phrases;
synthesizing the multiple audio segments into audio information; and
storing the audio information.
10. A user terminal, comprises:
a processor; and
a memory storing executable instructions that, when executed by the processor, cause the processor to:
receive first voice entered by a user, wherein the first voice information comprises a participle of a verb;
determining a function requested in the first voice information entered by the user by analyzing the participle of the verb;
obtain a set of prestored instructions based on the function requested in the first voice information entered by the user;
obtain a first prompt voice based on the set of prestored instructions;
provide the first prompt voice to prompt the user for second voice information comprising an adjective corresponding to the set of prestored instructions;
receive the second voice information comprising the adjective that is entered by the user in response to the first prompt voice;
search the memory of the user terminal for a prestored instruction from the set of prestored instructions which matches the second voice information comprising the adjective entered by the user;
obtain the prestored instruction according to the second voice information comprising the adjective entered by the user;
obtain text information according to the prestored instruction, by:
determining whether the text information is prestored in the user terminal;
in response to determining that the text information is prestored in the user terminal, obtaining the text information from the user terminal according to the prestored instruction; and
in response to determining that the text information is not stored in the user terminal, obtaining the text information from a server according to the prestored instruction;
obtain prestored audio information according to the text information; and
play the prestored audio information.
11. The user terminal according to claim 10 , wherein the memory further stores executable instructions that, when executed by the processor, cause the processor to: load the text information to a web page of a browser.
12. The user terminal according to claim 10 , wherein the memory further stores executable instructions that, when executed by the processor, cause the processor to:
obtain the prestored audio information by:
partitioning the text information into words or phrases;
searching an audio library for multiple audio segments corresponding to the words or the phrases; and
synthesizing the multiple audio segments into the audio.
13. The user terminal according to claim 10 , wherein the memory further stores executable instructions that, when executed by the processor, cause the processor to: play a second prompt voice after playing of the audio is completed.