back icon
close icon

Capture phrases in quotes for more specific queries (e.g. "rocket ship" or "Fred Lynn")

Article  May 1, 2015

Classification of lexical stress using spectral and prosodic features for computer-assisted language learning systems

SRI Authors Harry Bratt, Colleen Richey, Horacio Franco, Victor Abrash, Kristin Precoda

Citation

COPY

Ferrer, L., Bratt, H., Richey, C., Franco, H., Abrash, V., & Precoda, K. (2015). Classification of lexical stress using spectral and prosodic features for computer-assisted language learning systems. Speech communication, 69(0), 31-45.

Abstract

We present a system for detection of lexical stress in English words spoken by English learners. This system was designed to be part of the EduSpeak® computer-assisted language learning (CALL) software. The system uses both prosodic and spectral features to detect the level of stress (unstressed, primary or secondary) for each syllable in a word. Features are computed on the vowels and include normalized energy, pitch, spectral tilt, and duration measurements, as well as log-posterior probabilities obtained from the frame-level mel-frequency cepstral coefficients (MFCCs). Gaussian mixture models (GMMs) are used to represent the distribution of these features for each stress class. The system is trained on utterances by L1-English children and tested on English speech from L1-English children and L1-Japanese children with variable levels of English proficiency. Since it is trained on data from L1-English speakers, the system can be used on English utterances spoken by speakers of any L1 without retraining. Furthermore, automatically determined stress patterns are used as the intended target; therefore, hand-labeling of training data is not required. This allows us to use a large amount of data for training the system. Our algorithm results in an error rate of approximately 11% on English utterances from L1-English speakers and 20% on English utterances from L1-Japanese speakers. We show that all features, both spectral and prosodic, are necessary for achievement of optimal performance on the data from L1-English speakers; MFCC log-posterior probability features are the single best set of features, followed by duration, energy, pitch and finally, spectral tilt features. For English utterances from L1-Japanese speakers, energy, MFCC log-posterior probabilities and duration are the most important features.

How can we help?

    Once you hit send…

    We’ll match your inquiry to the person who can best help you. Expect a response within 48 hours.

    Our Privacy Policy