dc.creator | Ferrer, Luciana | |
dc.creator | Bratt, Harry | |
dc.creator | Richey, Colleen | |
dc.creator | Franco, Horacio | |
dc.creator | Abrash, Victor | |
dc.creator | Precoda, Kristin | |
dc.date.accessioned | 2018-03-06T21:32:52Z | |
dc.date.accessioned | 2018-11-06T12:05:30Z | |
dc.date.available | 2018-03-06T21:32:52Z | |
dc.date.available | 2018-11-06T12:05:30Z | |
dc.date.created | 2018-03-06T21:32:52Z | |
dc.date.issued | 2015-02 | |
dc.identifier | Ferrer, Luciana; Bratt, Harry; Richey, Colleen; Franco, Horacio; Abrash, Victor; et al.; Classification of lexical stress using spectral and prosodic features for computer-assisted language learning systems; Elsevier Science; Speech Communication; 69; 2-2015; 31-45 | |
dc.identifier | 0167-6393 | |
dc.identifier | http://hdl.handle.net/11336/38100 | |
dc.identifier | CONICET Digital | |
dc.identifier | CONICET | |
dc.identifier.uri | http://repositorioslatinoamericanos.uchile.cl/handle/2250/1862979 | |
dc.description.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. | |
dc.language | eng | |
dc.publisher | Elsevier Science | |
dc.relation | info:eu-repo/semantics/altIdentifier/url/http://www.sciencedirect.com/science/article/pii/S0167639315000151 | |
dc.relation | info:eu-repo/semantics/altIdentifier/doi/http://dx.doi.org/10.1016/j.specom.2015.02.002 | |
dc.rights | https://creativecommons.org/licenses/by-nc-nd/2.5/ar/ | |
dc.rights | info:eu-repo/semantics/restrictedAccess | |
dc.subject | COMPUTER-ASSISTED LANGUAGE LEARNING | |
dc.subject | GAUSSIAN MIXTURE MODELS | |
dc.subject | LEXICAL STRESS DETECTION | |
dc.subject | MEL FREQUENCY CEPSTRAL COEFFICIENTS | |
dc.subject | PROSODIC FEATURES | |
dc.title | Classification of lexical stress using spectral and prosodic features for computer-assisted language learning systems | |
dc.type | Artículos de revistas | |
dc.type | Artículos de revistas | |
dc.type | Artículos de revistas | |