ADJUSTABLE HIERARCHICAL SCORING METHOD AND SYSTEM

• US 20100151427A1
• Filed: 12/29/2008
• Published: 06/17/2010
• Est. Priority Date: 12/12/2008
• Status: Active Grant

• Current Assignee: Institute For Information Industry
• Original Assignee: Institute For Information Industry
• Inventors: Tien, Tzu-Chieh, Hung, Yu-Shiang, Jang, Jyh-Shing, Tsai, Te-Lu
• Granted Patent: US 8,157,566 B2
• Time in Patent Office: Days
• US Class Current: 434/169
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04

Abstract

An adjustable hierarchical scoring method is disclosed. A hierarchical scoring structure for speech-sound data is generated. Historical data of speech-sound scoring for the speech-sound data is retrieved from a speech-sound practice database while a professional scoring result for the hierarchical scoring structure of the speech-sound data is being collected. A weight-adjusting operation is performed according to the historical data of speech-sound scoring and the professional scoring result to calculate optimum adjusting weights for each layer of the hierarchical scoring structure. Retrieved speech-sound data of a student is scored using a speech-sound scoring system and a weighted average operation is performed to the score of the speech-sound data of the student according to a corresponding adjusting weight, thereby generating the final score of the speech-sound data of the student.

Claims

1. An adjustable hierarchical scoring method, comprising:

generating a hierarchical scoring structure for speech-sound data;

retrieving historical data of speech-sound scoring for the speech-sound data from a speech-sound practice database while a professional scoring result for the hierarchical scoring structure of the speech-sound data is being collected;

performing a weight-adjusting operation according to the historical data of speech-sound scoring and the professional scoring result to calculate optimum adjusting weights for each layer of the hierarchical scoring structure;

scoring retrieved speech-sound data of a student using a speech-sound scoring system; and

performing a weighted average operation to the score of the speech-sound data of the student according to a corresponding adjusted weight, thereby generating the adjusted score of the speech-sound data of the student.

2. The adjustable hierarchical scoring method as claimed in claim 1, wherein optimum adjusted weights for each layer of the hierarchical scoring structure is calculated using an iterative least-squares method.

3. The adjustable hierarchical scoring method as claimed in claim 1, wherein the speech-sound data comprises sentences, words, syllables, and phonemes.

4. An adjustable hierarchical scoring system, comprising:

a speech-sound scoring system, scoring retrieved speech-sound data of a student;

a speech-sound practice database, storing historical data for the speech-sound data scored by the speech-sound scoring system;

a weight database, storing calculated adjusted weights;

a score input interface, retrieving a professional scoring result for a hierarchical scoring structure of the speech-sound data;

a hierarchical weight-adjusting module, retrieving the historical data of speech-sound scoring for the speech-sound data from the speech-sound practice database and simultaneously collecting the professional scoring result for the hierarchical scoring structure of the speech-sound data, performing a weight-adjusting operation according to the historical data of speech-sound scoring and the professional scoring result to calculate optimum adjusting weights for each layer of the hierarchical scoring structure, and transmitting the calculated adjusted weights to the weight database; and

a hierarchical weighting and scoring module, when speech-sound data of a student is retrieved, scoring the retrieved speech-sound data of the student using the speech-sound scoring system, selecting an adjusted weight corresponding to the speech-sound data of the student from the weight database, and performing a weighted average operation to the score of the speech-sound data of the student according to the selected adjusted weight, thereby generating the adjusted score of the speech-sound data of the student.

5. The adjustable hierarchical scoring system as claimed in claim 4, wherein the hierarchical weight-adjusting module calculates optimum adjusting weights for each layer of the hierarchical scoring structure using an iterative least-squares method.

6. The adjustable hierarchical scoring system as claimed in claim 4, wherein the speech-sound data comprises sentences, words, syllables, and phonemes.

7. A computer-readable medium encoded with computer executable instructions for performing an adjustable hierarchical scoring method, wherein the computer executable instructions comprise:

generating a hierarchical scoring structure for speech-sound data;

retrieving historical data of speech-sound scoring for the speech-sound data from a speech-sound practice database while a professional scoring result for the hierarchical scoring structure of the speech-sound data is being collected;

performing a weight-adjusting operation according to the historical data of speech-sound scoring and the professional scoring result to calculate optimum adjusting weights for each layer of the hierarchical scoring structure;

scoring retrieved speech-sound data of a student using a speech-sound scoring system; and

performing a weighted average operation to the score of the speech-sound data of the student according to a corresponding adjusted weight, thereby generating the adjusted score of the speech-sound data of the student.