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
Autor principal: Ferrer, L.
Otros Autores: Bratt, H., Richey, C., Franco, H., Abrash, V., Precoda, K.
Formato: Acta de conferencia Capítulo de libro
Lenguaje:Inglés
Publicado: Institute of Electrical and Electronics Engineers Inc. 2014
Acceso en línea:Registro en Scopus
DOI
Handle
Registro en la Biblioteca Digital
Aporte de:Registro referencial: Solicitar el recurso aquí
LEADER 06022caa a22007097a 4500
001 PAPER-14438
003 AR-BaUEN
005 20230518204458.0
008 190411s2014 xx ||||fo|||| 10| 0 eng|d
024 7 |2 scopus  |a 2-s2.0-84905269582 
040 |a Scopus  |b spa  |c AR-BaUEN  |d AR-BaUEN 
030 |a IPROD 
100 1 |a Ferrer, L. 
245 1 0 |a Lexical stress classification for language learning using spectral and segmental features 
260 |b Institute of Electrical and Electronics Engineers Inc.  |c 2014 
506 |2 openaire  |e Política editorial 
504 |a Tepperman, J., Narayanan, S., Automatic syllable stress detection using prosodic features for pronunciation evaluation of language learners (2005) Proc. ICASSP, , Philadelphia, Mar 
504 |a Chen, J.Y., Wang, L., Automatic lexical stress detection for Chinese learners' of English (2010) Chinese Spoken Language Processing (ISCSLP), 2010 7th International Symposium on 
504 |a Deshmukh, O.D., Verma, A., Nucleus-level clustering for word-independent syllable stress classification (2009) Speech Communication, 51 (12) 
504 |a Chen, L.-Y., Jang, J.-S., Stress detection of English words for a CAPT system using word-length dependent GMM-based Bayesian classifiers (2012) Interdisciplinary Information Sciences, 18 (2), pp. 65-70 
504 |a Verma, A., Lal, K.L., Lo, Y.Y., Basak, J., Word independent model for syllable stress evaluation (2006) Proc. ICASSP, , Toulouse, May 
504 |a Li, C., Liu, J., Xia, S., English sentence stress detection system based on HMM framework (2007) Applied Mathematics and Computation, 185 (2) 
504 |a Lai, M., Chen, Y., Chu, M., Zhao, Y., Hu, F., A hierarchical approach to automatic stress detection in English sentences (2006) Proc. ICASSP, , Toulouse, May 
504 |a Ananthakrishnan, S., Narayanan, S., An automatic prosody recognizer using a coupled multi-stream acoustic model and a syntactic-prosodic language model (2005) Proc. ICASSP, , Philadelphia, Mar 
504 |a Franco, H., Abrash, V., Precoda, K., Bratt, H., Rao, R., Butzberger, J., Rossier, R., Cesari, F., The SRI EduSpeakTMsystem: Recognition and pronunciation scoring for language learning (2000) Proceedings of InSTILL 2000 
504 |a Franco, H., Bratt, H., Rossier, R., Gadde, V.R., Shriberg, E., Abrash, V., Precoda, K., EduSpeak: A speech recognition and pronunciation scoring toolkit for computeraided language learning applications (2010) Language Testing, 27 (3), pp. 401-418. , July 
504 |a Talkin, D., (1995) Robust Algorithm for Pitch Tracking, , Elsevier Science 
504 |a Lin, C.-Y., Wang, H.-C., Language identification using pitch contour information (2005) Proc. ICASSP, 1, pp. 601-604. , Philadelphia, Mar 
504 |a Reynolds, D.A., Quatieri, T.F., Dunn, R.B., Speaker verification using adapted Gaussian mixture models (2000) Digital Signal Processing, 10, pp. 19-41A4 - 
520 3 |a 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.  |l eng 
593 |a Speech Technology and Research Laboratory, SRI International, CA, United States 
593 |a CONICET, Argentina 
593 |a Departamento de Computación, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Argentina 
690 1 0 |a COMPUTER-AIDED LANGUAGE LEARNING 
690 1 0 |a GAUSSIAN MIXTURE MODELS 
690 1 0 |a STRESS CLASSIFICATION 
690 1 0 |a COMMUNICATION CHANNELS (INFORMATION THEORY) 
690 1 0 |a COMPUTER AIDED INSTRUCTION 
690 1 0 |a OBJECT RECOGNITION 
690 1 0 |a COMPUTER-AIDED LANGUAGE LEARNING 
690 1 0 |a ENGLISH WORD 
690 1 0 |a GAUSSIAN MIXTURE MODEL 
690 1 0 |a LANGUAGE LEARNING 
690 1 0 |a NON-NATIVE 
690 1 0 |a SPECTRAL FEATURE 
690 1 0 |a SPECTRAL TILT 
690 1 0 |a STRESS CLASSIFICATIONS 
690 1 0 |a SIGNAL PROCESSING 
700 1 |a Bratt, H. 
700 1 |a Richey, C. 
700 1 |a Franco, H. 
700 1 |a Abrash, V. 
700 1 |a Precoda, K. 
711 2 |c Florence  |d 4 May 2014 through 9 May 2014  |g Código de la conferencia: 106632 
773 0 |d Institute of Electrical and Electronics Engineers Inc., 2014  |h pp. 7704-7708  |p ICASSP IEEE Int Conf Acoust Speech Signal Process Proc  |n ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings  |x 15206149  |z 9781479928927  |t 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 
856 4 1 |u https://www.scopus.com/inward/record.uri?eid=2-s2.0-84905269582&doi=10.1109%2fICASSP.2014.6855099&partnerID=40&md5=25a0739879c37c54bfd880fcb114b228  |y Registro en Scopus 
856 4 0 |u https://doi.org/10.1109/ICASSP.2014.6855099  |y DOI 
856 4 0 |u https://hdl.handle.net/20.500.12110/paper_15206149_v_n_p7704_Ferrer  |y Handle 
856 4 0 |u https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_15206149_v_n_p7704_Ferrer  |y Registro en la Biblioteca Digital 
961 |a paper_15206149_v_n_p7704_Ferrer  |b paper  |c PE 
962 |a info:eu-repo/semantics/conferenceObject  |a info:ar-repo/semantics/documento de conferencia  |b info:eu-repo/semantics/publishedVersion 
999 |c 75391