Lexical stress classification for language learning using spectral and segmental features

We present a system for detecting lexical stress in English words spoken by English learners. The system uses both spectral and segmental features to detect three levels of stress for each syllable in a word. The segmental features are computed on the vowels and include normalized energy, pitch, spe...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ferrer, L., Bratt, H., Richey, C., Franco, H., Abrash, V., Precoda, K.
Formato:	CONF
Materias:	Computer-aided language learning Gaussian Mixture Models Stress classification Communication channels (information theory) Computer aided instruction Object recognition Computer-Aided Language Learning English word Gaussian Mixture Model Language learning Non-native Spectral feature Spectral tilt Stress classifications Signal processing
Acceso en línea:	http://hdl.handle.net/20.500.12110/paper_15206149_v_n_p7704_Ferrer
Aporte de:	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) de Universidad de Buenos Aires

id	todo:paper_15206149_v_n_p7704_Ferrer
record_format	dspace
spelling	todo:paper_15206149_v_n_p7704_Ferrer2023-10-03T16:20:34Z Lexical stress classification for language learning using spectral and segmental features Ferrer, L. Bratt, H. Richey, C. Franco, H. Abrash, V. Precoda, K. Computer-aided language learning Gaussian Mixture Models Stress classification Communication channels (information theory) Computer aided instruction Object recognition Computer-Aided Language Learning English word Gaussian Mixture Model Language learning Non-native Spectral feature Spectral tilt Stress classifications Signal processing We present a system for detecting lexical stress in English words spoken by English learners. The system uses both spectral and segmental features to detect three levels of stress for each syllable in a word. The segmental features are computed on the vowels and include normalized energy, pitch, spectral tilt and duration measurements. The spectral features are computed at the frame level and are modeled by one Gaussian Mixture Model (GMM) for each stress class. These GMMs are used to obtain segmental posteriors, which are then appended to the segmental features to obtain a final set of GMMs. The segmental GMMs are used to obtain posteriors for each stress class. The system was tested on English speech from native English-speaking children and from Japanese-speaking children with variable levels of English proficiency. Our algorithm results in an error rate of approximately 13% on native data and 20% on Japanese non-native data. © 2014 IEEE. CONF info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_15206149_v_n_p7704_Ferrer
institution	Universidad de Buenos Aires
institution_str	I-28
repository_str	R-134
collection	Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA)
topic	Computer-aided language learning Gaussian Mixture Models Stress classification Communication channels (information theory) Computer aided instruction Object recognition Computer-Aided Language Learning English word Gaussian Mixture Model Language learning Non-native Spectral feature Spectral tilt Stress classifications Signal processing
spellingShingle	Computer-aided language learning Gaussian Mixture Models Stress classification Communication channels (information theory) Computer aided instruction Object recognition Computer-Aided Language Learning English word Gaussian Mixture Model Language learning Non-native Spectral feature Spectral tilt Stress classifications Signal processing Ferrer, L. Bratt, H. Richey, C. Franco, H. Abrash, V. Precoda, K. Lexical stress classification for language learning using spectral and segmental features
topic_facet	Computer-aided language learning Gaussian Mixture Models Stress classification Communication channels (information theory) Computer aided instruction Object recognition Computer-Aided Language Learning English word Gaussian Mixture Model Language learning Non-native Spectral feature Spectral tilt Stress classifications Signal processing
description	We present a system for detecting lexical stress in English words spoken by English learners. The system uses both spectral and segmental features to detect three levels of stress for each syllable in a word. The segmental features are computed on the vowels and include normalized energy, pitch, spectral tilt and duration measurements. The spectral features are computed at the frame level and are modeled by one Gaussian Mixture Model (GMM) for each stress class. These GMMs are used to obtain segmental posteriors, which are then appended to the segmental features to obtain a final set of GMMs. The segmental GMMs are used to obtain posteriors for each stress class. The system was tested on English speech from native English-speaking children and from Japanese-speaking children with variable levels of English proficiency. Our algorithm results in an error rate of approximately 13% on native data and 20% on Japanese non-native data. © 2014 IEEE.
format	CONF
author	Ferrer, L. Bratt, H. Richey, C. Franco, H. Abrash, V. Precoda, K.
author_facet	Ferrer, L. Bratt, H. Richey, C. Franco, H. Abrash, V. Precoda, K.
author_sort	Ferrer, L.
title	Lexical stress classification for language learning using spectral and segmental features
title_short	Lexical stress classification for language learning using spectral and segmental features
title_full	Lexical stress classification for language learning using spectral and segmental features
title_fullStr	Lexical stress classification for language learning using spectral and segmental features
title_full_unstemmed	Lexical stress classification for language learning using spectral and segmental features
title_sort	lexical stress classification for language learning using spectral and segmental features
url	http://hdl.handle.net/20.500.12110/paper_15206149_v_n_p7704_Ferrer
work_keys_str_mv	AT ferrerl lexicalstressclassificationforlanguagelearningusingspectralandsegmentalfeatures AT bratth lexicalstressclassificationforlanguagelearningusingspectralandsegmentalfeatures AT richeyc lexicalstressclassificationforlanguagelearningusingspectralandsegmentalfeatures AT francoh lexicalstressclassificationforlanguagelearningusingspectralandsegmentalfeatures AT abrashv lexicalstressclassificationforlanguagelearningusingspectralandsegmentalfeatures AT precodak lexicalstressclassificationforlanguagelearningusingspectralandsegmentalfeatures
_version_	1807316732746924032

Lexical stress classification for language learning using spectral and segmental features

Ejemplares similares