Accession Number:

ADA282979

Title:

Speech Recognition of Foreign Accent

Descriptive Note:

Master's thesis

Corporate Author:

NAVAL POSTGRADUATE SCHOOL MONTEREY CA

Personal Author(s):

• Dewey, John K.

Report Date:

1994-06-01

Pagination or Media Count:

82.0

Abstract:

This thesis investigates the application of AutoRegressive AR modeling techniques on single syllable words to detect foreign accents in spoken American English. The study involves thirty-one native American English speakers, and six native Brazilian speakers. Five different distance measures are used for classification. Results show that correct classification is obtained for 88 of the native English speakers and 80.5 of the non-native foreign English speakers. Speech processing, Foreign accent recognition, AutoRegressive AR modeling

Descriptors:

• *SPEECH RECOGNITION
• *ENGLISH LANGUAGE
• SIGNAL PROCESSING
• FREQUENCY
• FOREIGN
• SPEECH ANALYSIS
• SOUND PITCH
• SYLLABLES
• PHONETICS
• CROSS CORRELATION
• FAST FOURIER TRANSFORMS
• WHITE NOISE
• THESES
• CLASSIFICATION

Subject Categories:

• Linguistics
• Voice Communications

Distribution Statement:

APPROVED FOR PUBLIC RELEASE