HANDLING SPEECH SYNTHESIS OF CONTENT FOR MULTIPLE LANGUAGES

• US 20130238339A1
• Filed: 03/06/2012
• Published: 09/12/2013
• Est. Priority Date: 03/06/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Fleizach, Christopher Brian, Minifie, Darren C.
• Granted Patent: US 9,483,461 B2
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Techniques that enable a user to select, from among multiple languages, a language to be used for performing text-to-speech conversion. In some embodiments, upon determining that multiple languages may be used to perform text-to-speech conversion for a portion of text, the multiple languages may be displayed to the user. The user may then select a particular language to be used from the multiple languages. The portion of text may then be converted to speech in the user-selected language.

Claims

1. A method comprising:

determining, by a processing device, a set of languages for converting text to speech, the set of languages comprising a plurality of candidate languages for converting a portion of the text to speech;

causing, by the processing device, the plurality of candidate languages to be displayed;

receiving input indicative of selection of a first candidate language from the plurality of candidate languages; and

converting, by the processing device, the text to speech, the converting comprising converting the portion of the text to speech in the first candidate language.

2. The method of claim 1 wherein converting the portion of the text to speech in the first candidate language comprises using a language synthesizer corresponding to the first candidate language to generate speech for the portion of the text.

3. The method of claim 1 wherein the portion of the text is the entire text or a subset of the text.

4. The method of claim 1 wherein converting the text to speech comprises:

converting a first character in the text to speech using a first language synthesizer; and

converting a second character following the first character in the text to speech using a second language synthesizer different from the first language synthesizer.

5. The method of claim 1 wherein converting the second character to speech comprises:

reading a first character in the text;

determining a first language to be used for converting the first character to speech;

associating the first language with the first character;

reading a second character in the text following the first character;

determining a second language to be used for converting the second character to speech, wherein the second language is different from the first language; and

associating the second language with the second character.

6. The method of claim 1 wherein the determining comprises performing at least one of:

determining a language for converting the text to speech based upon one or more loaded keyboards;

determining a language for converting the text to speech based upon one or more tags associated with the text;

determining a language for converting the text to speech based upon one or more languages identified by a language analysis tool upon analysis of the text;

determining a language for converting the text to speech based upon data provided by an application associated with the text;

or determining a language for converting the text to speech based upon encoding information associated with one or more characters in the text.

7. The method of claim 1 wherein the determining comprises performing at least one of:

determining a language for converting the text to speech based upon one or more user preferences;

determining a language for converting the text to speech based upon a language selected for a prior text-to-speech conversion;

determining a language for converting the text to speech based upon a source of the text;

determining a language for converting the text to speech based country code top-level domain information associated with the text;

or

determining a language for converting the text to speech based upon global positioning system (GPS) information.

8. The method of claim 1 wherein determining the set of languages for converting the text to speech comprises:

determining a first list of languages for converting the text to speech; and

determining a second list of languages from the first list of languages by filtering out at least one language from the first list of languages.

9. A non-transitory computer-readable storage medium storing a plurality of instructions for controlling a processor, the plurality of instructions comprising:

instructions that cause the processor to determine a set of languages for converting text to speech, the set of languages comprising a plurality of candidate languages for converting a portion of the text to speech;

instructions that cause the processor to display the plurality of candidate languages; and

instructions that cause the processor to, in response to receiving input indicative of selection of a first candidate language from the plurality of candidate languages, convert the text to speech, the converting comprising converting the portion of the text to speech in the first candidate language.

10. The non-transitory computer-readable storage medium of claim 9 wherein instructions that cause the processor to convert the portion of the text to speech in the first candidate language comprise instructions that cause the processor to use a language synthesizer corresponding to the first candidate language to generate speech for the portion of text.

11. The non-transitory computer-readable storage medium of claim 9 wherein the portion of the text is the entire text or a subset of the text.

12. The non-transitory computer-readable storage medium of claim 9 wherein the instructions that cause the processor to convert the text to speech comprise:

instructions that cause the processor to read a first character in the text;

instructions that cause the processor to determine a first language to be used for converting the first character to speech;

instructions that cause the processor to associate the first language with the first character;

instructions that cause the processor to read a second character in the text following the first character;

instructions that cause the processor to determine a second language to be used for converting the second character to speech, wherein the second language is different from the first language;

instructions that cause the processor to associate the second language with the second character;

instructions that cause the processor to convert the first character to speech using a language synthesizer corresponding to the first language associated with the first character; and

instructions that cause the processor to convert the second character to speech using a language synthesizer corresponding to the second language synthesizer associated with the second character.

13. The non-transitory computer-readable storage medium of claim 9 wherein the instructions that cause the processor to determine the set of languages comprise instructions that cause the processor to perform at least one of:

determine a language for converting the text to speech based upon one or more loaded keyboards;

determine a language for converting the text to speech based upon one or more tags associated with the text;

determine a language for converting the text to speech based upon one or more languages identified by a language analysis tool upon analysis of the text;

determine a language for converting the text to speech based upon character encoding information associated with one or more characters in the text;

determine a language for converting the text to speech based upon one or more user preferences;

determine a language for converting the text to speech based upon a language selected for a prior text-to-speech conversion;

determine a language for converting the text to speech based upon a source of the text;

determine a language for converting the text to speech based country code top-level domain information associated with the text;

or

determine a language for converting the text to speech based upon global positioning system (GPS) information.

14. The non-transitory computer-readable storage medium of claim 9 wherein instructions that cause the processor to determine the set of languages for converting the text to speech comprise:

instructions that cause the processor to determine a first list of languages for converting the text to speech; and

instructions that cause the processor to determine a second list of languages from the first list of languages by filtering out at least one language from the first list of languages.

15. A system comprising:

a memory configured to store text; and

one or more processors coupled to the memory, the one or more processors configured to;

determine a set of languages for converting the text to speech, the set of languages comprising a plurality of candidate languages for converting a portion of the text to speech;

cause the plurality of candidate languages to be displayed; and

in response to receiving input indicative of selection of a first candidate language from the plurality of candidate languages, convert the text to speech, the converting comprising converting the portion of the text to speech in the first candidate language.

16. The system of claim 15 the one or more processors are configured to use a language synthesizer corresponding to the first candidate language to generate speech for the portion of text.

17. The system of claim 15 wherein the portion of the text is the entire text or a subset of the text.

18. The system of claim 15 wherein the one or more processors are configured to:

read a first character in the text;

determine a first language to be used for converting the first character to speech;

associate the first language with the first character;

read a second character in the text following the first character;

determine a second language to be used for converting the second character to speech, wherein the second language is different from the first language;

associate the second language with the second character;

convert the first character to speech using a language synthesizer corresponding to the first language associated with the first character; and

convert the second character to speech using a language synthesizer corresponding to the second language synthesizer associated with the second character.

19. The system of claim 15 wherein the one or more processors are configured to determine the set of languages by performing at least one of:

determine a language for converting the text to speech based upon one or more loaded keyboards;

determine a language for converting the text to speech based upon one or more tags associated with the text;

determine a language for converting the text to speech based upon one or more languages identified by a language analysis tool upon analysis of the text;

determine a language for converting the text to speech based upon character encoding information associated with one or more characters in the text;

determine a language for converting the text to speech based upon one or more user preferences;

determine a language for converting the text to speech based upon a language selected for a prior text-to-speech conversion;

determine a language for converting the text to speech based upon a source of the text;

determine a language for converting the text to speech based country code top-level domain information associated with the text;

or

determine a language for converting the text to speech based upon global positioning system (GPS) information.

20. The system of claim 15 wherein:

the text is selected from a webpage; and

the one or more processors are configured to determine the set of languages based upon a domain associated with a website hosting the webpage.