Arabic poetry meter identification system and method

• US 8,219,386 B2
• Filed: 01/21/2009
• Issued: 07/10/2012
• Est. Priority Date: 01/21/2009
• Status: Expired due to Fees

• Current Assignee: King Fahd University of Petroleum & Minerals (Government of Saudi Arabia)
• Original Assignee: King Fahd University Of Petroleum And Minerals
• Inventors: Saleh, Al-Zahrani Abdul Kareem, Elshafei, Moustafa
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): Kovacek, David
• Application Number:
  US12/320,196
• Publication Number:
  US 20100185436A1
• Time in Patent Office: 1,266 Days
• Field of Search: 704 1- 10, 704231-257, 704/276, 704E15001-E1505, 704E11001-E11007, 434112-118, 434128-129, 434156-185, 434/245, 434308-321, 434/364, 434/433
• US Class Current: 704/9
• CPC Class Codes: G06F 40/237 Lexical tools

Abstract

The Arabic poetry meter identification system and method produces coded Al-Khalyli transcriptions of Arabic poetry. The meters (Wazn, Awzan being forms of the Arabic poems units Bayt, Abyate) are identified. A spoken or written poem is accepted as input. A coded transcription of the poetry pattern forms is produced from input processing. The system identifies and distinguishes between proper spoken poetic meter and improper poetic meter. Error in the poem meters (Bahr, Buhur) and the ending rhyme pattern, “Qafiya” are detected and verified. The system accepts user selection of a desired poem meter and then interactively aids the user in the composition of poetry in the selected meter, suggesting alternative words and word groups that follow the desired poem pattern and dactyl components. The system can be in a stand-alone device or integrated with other computing devices.

Claims

1. A poetry meter identification system, comprising:

a data input device for entering poetry, wherein said data input device comprises an audio input for inputting and receiving spoken audio voice input from a user;

a data output device for outputting a coded transcription of the at least one meter form of the poetry; and

a processor having software executable thereon, the software including;

means for recording the spoken audio voice input;

means for segmenting the spoken audio voice input into a sequence of basic sound signal classes;

means for automatically identifying at least one meter form of the poetry entry;

means for distinguishing between proper spoken poetic meter and improper spoken poetic meter of the poetry;

means for identifying poetry meter errors; and

means for identifying ending rhyme pattern errors.

2. The poetry meter identification system according to claim 1, wherein the software further comprises:

means for extracting feature vectors from the spoken poetry, the feature vectors representing frame sequences of speech;

means for accessing a list of models of syllabic and sub-syllabic patterns; and

means for identifying spoken language syllabic and sub-syllabic patterns from the list of models of syllabic and sub-syllabic patterns and selecting a best sequence of spoken language syllabic patterns matching the spoken poetry.

3. The poetry meter identification system according to claim 2, wherein the spoken language of the poetry is Arabic.

4. The poetry meter identification system according to claim 3, wherein the software further comprises means for parsing and coding the recognized sequence of Arabic syllabic patterns into Khalili transcription.

5. The poetry meter identification system according to claim 3, wherein the software further comprises means for computing feature vector sequences identifying syllabic and sub-syllabic patterns having unvoweled Arabic consonants, Arabic consonants followed by short vowels, Arabic consonants followed by long vowels, and consonant-short vowel-consonant clusters.

6. The poetry meter identification system according to claim 4, wherein the software further comprises:

means for parsing Arabic poem text into Arabic syllables;

means for identifying the Arabic syllables by common syllabic patterns; and

means for encoding the resulting Arabic syllabic pattern sequence into Khalili transcription.

7. The poetry meter identification system according to claim 6, wherein the stored list of models of syllabic and sub-syllabic patterns further comprises tables of Arabic word groups corresponding to standard Arabic poem dactyls.

8. The poetry meter identification system according to claim 6, wherein the software further comprises means for parsing the Khalili sequence into a sequence of dactyls from the list of dactyls, the list of dactyls containing the permissible dactyl patterns and a possible set of wrong dactyl patterns.

9. The poetry meter identification system according to claim 8, wherein the data output device comprises a display screen for indicating the coded transcription of the at least one meter form of the poetry.

10. The poetry meter identification system according to claim 9, wherein the software further comprises means for displaying:

a first display row showing a Khalili transcription of a corresponding line of the spoken poem;

a second display row showing a dactyl sequence of the Khalili transcription; and

a third display row showing a meter of the spoken poem.

11. The poetry meter identification system according to claim 10, wherein said means for displaying further comprises means for displaying a fourth display row showing the possible set of wrong dactyl patterns.

12. The poetry meter identification system according to claim 10, wherein the means for displaying further comprises means for displaying a line of text associated with a respective display row, the line of text describing the type of ending rhyme of the poem and whether the type of ending rhyme is consistent with the rhyme structure of the poem.

13. An electronic poetry meter identification method, comprising the steps of:

accepting entry of a poem into an electronic device, wherein said electronic device includes an audio input for inputting and receiving spoken audio voice input from a user;

recording the spoken audio voice input;

segmenting the spoken audio voice input into a sequence of basic sound signal classes;

electronically identifying at least one meter form of the poem entry automatically;

electronically providing a coded transcription of the at least one meter form of the poem;

electronically distinguishing between proper spoken poetic meter and improper poetic meter of the poem;

electronically identifying poem meter errors; and

electronically identifying ending rhyme pattern errors.

14. The electronic poetry meter identification method according to claim 13, further comprising the steps of electronically:

extracting feature vectors from the spoken poetry, the feature vectors representing frame sequences of speech;

using the feature vector sequences to identify spoken language syllabic and sub-syllabic patterns from a stored list of models of syllabic and sub-syllabic patterns; and

selecting a best sequence of spoken language syllabic patterns matching the spoken poetry.

15. The electronic poetry meter identification method according to claim 14, wherein the spoken language of the poetry is Arabic.

16. The electronic poetry meter identification method according to claim 15, further comprising the steps of parsing and coding recognized sequences of Arabic syllabic patterns into Khalili transcription.

17. The electronic poetry meter identification method according to claim 15, further comprising the step of providing feature vector sequences identifying syllabic and sub-syllabic patterns having unvoweled Arabic consonants, Arabic consonants followed by short vowels, Arabic consonants followed by long vowels, and consonant-short vowel-consonant clusters.

18. The electronic poetry meter identification method according to claim 16, further comprising the steps of

parsing Arabic poem text into Arabic syllables;

identifying the Arabic syllables by their common syllabic patterns; and

encoding the resulting Arabic syllabic pattern sequence into Khalili transcription.

19. The electronic poetry meter identification method according to claim 17, further comprising the steps of:

parsing the Khalili sequence into a sequence of dactyls from the list of dactyls, the list of dactyls containing the permissible dactyl patterns and a possible set of wrong dactyl patterns;

displaying in a first display row a Khalili transcription of a corresponding line of the spoken poem;

displaying in a second display row a dactyl sequence of the Khalili transcription;

displaying in a third display row the meter of the spoken poem; and

displaying in a fourth display row the possible set of wrong dactyl patterns.

20. A computer software product that includes a non-transitory computer storage medium readable by a processor, the non-transitory computer storage medium having stored thereon a set of instructions for performing poetry meter identification, the instructions comprising:

(a) a first set of instructions which, when loaded into main memory and executed by the processor, causes the processor to accept entry of a poem from a user in the form of spoken audio voice input;

(b) a second set of instructions which, when loaded into main memory and executed by the processor, causes the processor to record the spoken audio voice input;

(c) a third set of instructions which, when loaded into main memory and executed by the processor, causes the processor to segment the spoken audio voice input into a sequence of basic sound signal classes;

(d) a fourth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to automatically identify at least one meter form of the poem entry;

(e) a fifth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to provide the user a coded transcription of the at least one meter form of the poem;

(f) a sixth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to distinguish between proper spoken poetic meter and improper poetic meter of the poem;

(g) a seventh set of instructions which, when loaded into main memory and executed by the processor, causes the processor to notify the user of poem meter errors; and

(h) an eighth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to notify the user of ending rhyme pattern errors.