METHOD AND APPARATUS FOR PHONETICALLY ANNOTATING TEXT

• US 20160306783A1
• Filed: 06/23/2016
• Published: 10/20/2016
• Est. Priority Date: 05/07/2014
• Status: Active Grant

• Current Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Original Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Inventors: DAI, Qiang, WU, Xiaoping
• Granted Patent: US 10,114,809 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/129 Handling non-Latin characters, e.g. kana-to-kanji conversion
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• 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

Abstract

Method and apparatus for phonetically annotating text are disclosed. The method includes: at a device having one or more processors and memory: identifying a first polyphonic word segment in a text input, the first polyphonic word segment having at least a first pronunciation and a second pronunciation; determining at least a first probability for the first pronunciation and a second probability for the second pronunciation; comparing a difference between the first probability and the second probability with a predetermined threshold difference; and selecting the first probability as a current pronunciation for the first polyphonic word segment in accordance with a determination that the difference between the first probability and the second probability exceeds the predetermined threshold difference.

Claims

1. A method for phonetically annotating text, comprising:

at a device having one or more processors and memory;

identifying a first polyphonic word segment in a text input, the first polyphonic word segment having at least a first pronunciation and a second pronunciation;

determining at least a first probability for the first pronunciation and a second probability for the second pronunciation;

comparing a difference between the first probability and the second probability with a predetermined threshold difference; and

selecting the first probability as a current pronunciation for the first polyphonic word segment in accordance with a determination that the difference between the first probability and the second probability exceeds the predetermined threshold difference.

2. The method of claim 1, further comprising:

obtaining the text input for phonetic annotation;

determining whether the text input contains at least one polyphonic character; and

in accordance with a determination that the text input includes at least one polyphonic character, segmenting the text input into a plurality of word segments including the first polyphonic word segment.

3. The method of claim 2, further comprising:

determining whether the plurality of word segments contain at least one polyphonic word segment, wherein the identification of the first polyphonic word segment in the text input is performed in accordance with a determination that the plurality of word segments contains at least one polyphonic word segment.

4. The method of claim 1, further comprising:

selecting a current value for the predetermined threshold difference based on the first probability and the second probability.

5. The method of claim 4, wherein selecting the current value for the predetermined threshold difference based on the first probability and the second probability further comprises:

selecting a first difference value for the predetermined threshold difference when both the first and the second probabilities are above a predetermined threshold probability value; and

selecting a second difference value for the predetermined threshold difference when the first probability is above the predetermined threshold probability value and the second probability is below the predetermined threshold probability value.

6. The method of claim 5, wherein the first difference value is smaller than the second difference value.

7. The method of claim 6, wherein the first pronunciation and the second pronunciation have the two largest probabilities among all pronunciations of the first polyphonic word segment.

8. A non-transitory computer-readable medium having instructions stored thereon, the instructions, when executed by one or more processors cause the processors to perform operations for phonetically annotating text, and the operations comprising:

identifying a first polyphonic word segment in a text input, the first polyphonic word segment having at least a first pronunciation and a second pronunciation;

determining at least a first probability for the first pronunciation and a second probability for the second pronunciation;

comparing a difference between the first probability and the second probability with a predetermined threshold difference; and

selecting the first probability as a current pronunciation for the first polyphonic word segment in accordance with a determination that the difference between the first probability and the second probability exceeds the predetermined threshold difference.

9. The computer-readable medium of claim 8, wherein the operations further comprise:

obtaining the text input for phonetic annotation;

determining whether the text input contains at least one polyphonic character; and

in accordance with a determination that the text input includes at least one polyphonic character, segmenting the text input into a plurality of word segments including the first polyphonic word segment.

10. The computer-readable medium of claim 9, wherein the operations further comprise:

determining whether the plurality of word segments contain at least one polyphonic word segment, wherein the identification of the first polyphonic word segment in the text input is performed in accordance with a determination that the plurality of word segments contains at least one polyphonic word segment.

11. The computer-readable medium of claim 8, wherein the operations further comprise:

selecting a current value for the predetermined threshold difference based on the first probability and the second probability.

12. The computer-readable medium of claim 11, wherein selecting the current value for the predetermined threshold difference based on the first probability and the second probability further comprises:

selecting a first difference value for the predetermined threshold difference when both the first and the second probabilities are above a predetermined threshold probability value; and

selecting a second difference value for the predetermined threshold difference when the first probability is above the predetermined threshold probability value and the second probability is below the predetermined threshold probability value.

13. The computer-readable medium of claim 12, wherein the first difference value is smaller than the second difference value.

14. The computer-readable medium of claim 13, wherein the first pronunciation and the second pronunciation have the two largest probabilities among all pronunciations of the first polyphonic word segment.

15. A system for phonetically annotating text, comprising:

one or more processors; and

memory having instructions stored thereon, the instructions, when executed by the one or more processors, cause the processors to perform operations comprising;

identifying a first polyphonic word segment in a text input, the first polyphonic word segment having at least a first pronunciation and a second pronunciation;

determining at least a first probability for the first pronunciation and a second probability for the second pronunciation;

comparing a difference between the first probability and the second probability with a predetermined threshold difference; and

selecting the first probability as a current pronunciation for the first polyphonic word segment in accordance with a determination that the difference between the first probability and the second probability exceeds the predetermined threshold difference.

16. The system of claim 15, wherein the operations further comprise:

obtaining the text input for phonetic annotation;

determining whether the text input contains at least one polyphonic character; and

in accordance with a determination that the text input includes at least one polyphonic character, segmenting the text input into a plurality of word segments including the first polyphonic word segment.

17. The system of claim 16, wherein the operations further comprise:

determining whether the plurality of word segments contain at least one polyphonic word segment, wherein the identification of the first polyphonic word segment in the text input is performed in accordance with a determination that the plurality of word segments contains at least one polyphonic word segment.

18. The system of claim 15, wherein the operations further comprise:

selecting a current value for the predetermined threshold difference based on the first probability and the second probability.

19. The system of claim 18, wherein selecting the current value for the predetermined threshold difference based on the first probability and the second probability further comprises:

selecting a first difference value for the predetermined threshold difference when both the first and the second probabilities are above a predetermined threshold probability value; and

selecting a second difference value for the predetermined threshold difference when the first probability is above the predetermined threshold probability value and the second probability is below the predetermined threshold probability value.

20. The system of claim 19, wherein the first difference value is smaller than the second difference value.