Chinese prosodic words forming method and apparatus

• US 8,392,191 B2
• Filed: 12/10/2007
• Issued: 03/05/2013
• Est. Priority Date: 12/13/2006
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Qing, Guo, Katae, Nobuyuki
• Primary Examiner(s): Neway, Samuel G
• Application Number:
  US12/000,178
• Publication Number:
  US 20080147405A1
• Time in Patent Office: 1,912 Days
• Field of Search: None
• US Class Current: 704/258
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

The present invention provides a method and apparatus of forming Chinese prosodic words, which method comprises the steps of inputting Chinese text; performing process of word segmentation and part of speech annotation for the input Chinese text to generate an initial prosodic word sequence; inserting grids representing prosodic word boundaries for all the words in the initial prosodic word sequence to generate a grid prosodic word sequence; annotating the grids ready to be deleted in the grid prosodic word sequence based on the prosodic word forming means; judging the grids which actually need to be deleted in the grids ready to be deleted based on the prosodic word forming means; deleting the grids which actually need to be deleted in the grid prosodic word sequence, and word forming the words between every two grids in the remaining grids to generate prosodic words. The present invention avoids the defect whereby the type of insertion error of the prosodic word would render the pronunciation hard to understand or unnatural as far as possible, and reduces the number of the type of insertion error of prosodic word boundaries.

Claims

1. A method of forming Chinese prosodic words, implemented using a computer, said method comprising:

inputting Chinese text;

performing, via a computer, a process of word segmentation and part of speech annotation for the input Chinese text submitted to the computer to generate an initial prosodic word sequence;

inserting grids representing prosodic word boundaries for all the words in the initial prosodic word sequence to generate a grid prosodic word sequence including inserting at least one eliminable indicator in the grid prosodic word sequence;

annotating grids ready to be deleted in the grid prosodic word sequence based on a prosodic word forming means;

comprehensively judging grids which actually need to be deleted in the grids ready to be deleted based on a plurality of prosodic word forming means, the plurality of prosodic word forming means including a prosodic word forming based on a binary prosodic tree, a prosodic word forming based on statistical probability, and a prosodic word forming based on rules, and

wherein said comprehensively judging includes providing a trust degree for the grids ready to be deleted and judging whether the grids ready to be deleted actually need to be deleted based on said trust degree by checking whether a current grid has been marked with the at least one eliminable indicator; and

the grids which actually need to be deleted in the grid prosodic word sequence are deleted when said comprehensively judging indicates deletion, and forming the words between every two grids in the remaining grids to generate prosodic words.

2. The method according to claim 1, characterized in word dividing and part of speech annotating the input Chinese text to generate word segmentation result, and generating an initial prosodic word sequence based on said word segmentation result.

3. The method according to claim 1, characterized in that annotating said grids ready to be deleted defines annotating the grids ready to be deleted in the same grid prosodic word sequence forming of a plurality of prosodic words.

4. An apparatus to form Chinese prosodic words, comprising:

an input part to input Chinese text;

a word segmentation and part of speech annotating part to perform a process of word segmentation and part of speech annotation for the input Chinese text to generate an initial prosodic word sequence;

a prosodic word grid insert part to insert grids representing prosodic word boundaries for all the words in the initial prosodic word sequence to generate a grid prosodic word sequence including inserting at least one eliminable indicator in the grid prosodic word sequence;

a prosodic word grid delete part to annotate grids ready to be deleted in the grid prosodic word sequence based on a prosodic word forming means, the plurality of prosodic word forming means including a prosodic word forming based on a binary prosodic tree, a prosodic word forming based on statistical probability, and a prosodic word forming based on rules;

a grid deletion trust degree evaluation part to comprehensively to judge grids which actually need to be deleted in the grids ready to be deleted based on a plurality of prosodic word forming means and to provide a trust degree for the grids ready to be deleted;

a grid deletion part to judge whether the grids ready to be deleted actually need to be deleted based on said trust degree and to delete the grids which actually need to be deleted in the grid prosodic word sequence in accordance with a result from the grid deletion part by checking whether a current grid has been marked with the at least one eliminable indicator; and

a prosodic word generating part to form the words between every two grids in the remaining grids to generate prosodic words.

5. The apparatus according to claim 4, comprising:

a word dividing result storage part for storing the word dividing result after the process of word dividing and part of speech annotating the input Chinese text to generate an initial prosodic word sequence based on said word segmentation result.

6. The apparatus according to claim 4, characterized in that said prosodic word grid delete part comprises:

a plurality of prosodic word forming part to annotate said grids ready to be deleted and define annotating the grids ready to be deleted in the same grid prosodic word sequence based on the plurality of prosodic word forming means.

7. The apparatus according to claim 4, comprising:

a prosodic word forming result analysis part for analyzing and processing the prosodic words generated by the prosodic word generating part to generate prosodic word forming analysis result.

8. A program embedded in an apparatus and causing the apparatus to execute an operation including forming Chinese prosodic words, the operation comprising:

inputting Chinese text;

performing a process of word segmentation and part of speech annotation for the input Chinese text to generate an initial prosodic word sequence;

inserting grids representing prosodic word boundaries for all the words in the initial prosodic word sequence to generate a grid prosodic word sequence including inserting at least one eliminable indicator in the grid prosodic word sequence;

annotating grids ready to be deleted in the grid prosodic word sequence based on a prosodic word forming means;

comprehensively judging grids which actually need to be deleted in the grids ready to be deleted based on a plurality of prosodic word forming means, said comprehensively judging includes providing a trust degree for the grids ready to be deleted and judging whether the grids ready to be deleted actually need to be deleted based on said trust degree by checking whether a current grid has been marked with the at least one eliminable indicator; and

deleting the grids which actually need to be deleted in the grid prosodic word sequence when said comprehensively judging indicates deletion, and forming the words between every two grids in the remaining grids to generate prosodic words, and

wherein the plurality of prosodic word forming means includes a prosodic word forming based on a binary prosodic tree, a prosodic word forming based on statistical probability, and a prosodic word forming based on rules.

9. A non-transitory computer readable storage medium storing Chinese prosodic words forming program to cause a computer to execute an operation, comprising:

inputting Chinese text;

performing a process of word segmentation and part of speech annotation for the input Chinese text to generate an initial prosodic word sequence;

inserting grids representing prosodic word boundaries for all the words in the initial prosodic word sequence to generate a grid prosodic word sequence including inserting at least one eliminable indicator in the grid prosodic word sequence;

annotating grids ready to be deleted in the grid prosodic word sequence based on a prosodic word forming means;

comprehensively judging grids which actually need to be deleted in the grids ready to be deleted based on a plurality of prosodic word forming means, the plurality of prosodic word forming means including a prosodic word forming based on a binary prosodic tree, a prosodic word forming based on statistical probability, and a prosodic word forming based on rules, and

said comprehensively judging includes providing a trust degree the grids to be deleted;

judging whether the grids ready to be deleted actually need to be deleted based on said trust degree by checking whether a current grid has been marked with the at least one eliminable indicator;

deleting the grids which actually need to be deleted in the grid prosodic word sequence when said comprehensively judging indicates deletion, and forming the words between every two grids in the remaining grids to generate prosodic words.

10. The non-transitory computer readable storage medium according to claim 9, wherein a result of the word segmentation of the input Chinese text defines boundaries of the initial word sequence using which the grids representing the prosodic word boundaries are inserted into all the word boundaries.