{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:40:09Z","timestamp":1750196409686,"version":"3.41.0"},"reference-count":38,"publisher":"SAGE Publications","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2017,4,1]]},"DOI":"10.3233\/ida-170869","type":"journal-article","created":{"date-parts":[[2017,4,7]],"date-time":"2017-04-07T15:40:57Z","timestamp":1491579657000},"page":"S5-S19","source":"Crossref","is-referenced-by-count":0,"title":["Single channel source separation using graph sparse NMF and adaptive dictionary learning"],"prefix":"10.1177","volume":"21","author":[{"given":"Tuan","family":"Pham","sequence":"first","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"}]},{"given":"Yuan-Shan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"}]},{"given":"Yan-Bo","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"}]},{"given":"Yung-Hui","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"}]},{"given":"Tzu-Chiang","family":"Tai","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, Providence University, Taichung, Taiwan"}]},{"given":"Jia-Ching","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-170869_ref1","unstructured":"Lee D.D. and Seung H.S., Algorithms for non-negative matrix factorization, Advances in Neural Information Processing Systems (2001). Cambridge, MA, USA: MIT Press, 13."},{"issue":"3","key":"10.3233\/IDA-170869_ref2","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/LSP.2014.2346506","article-title":"Mixtures of local dictionaries for unsupervised speech enhancement","volume":"22","author":"Minje","year":"2015","journal-title":"IEEE Signal Processing Letters"},{"key":"10.3233\/IDA-170869_ref3","doi-asserted-by":"crossref","unstructured":"F\u00e9votte C. and Idier J., Algorithms for nonnegative matrix factorization with the beta-divergence, Neural Computation (2011).","DOI":"10.1162\/NECO_a_00168"},{"key":"10.3233\/IDA-170869_ref5","first-page":"1457","article-title":"Non-negative matrix factorization with sparseness Constraints","volume":"5","author":"Hoyer","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"10.3233\/IDA-170869_ref6","doi-asserted-by":"crossref","unstructured":"Lef\u00e8vre A., Bach F. and F\u00e9votte C., Itakura-Saito non-negative matrix factorization with group sparsity, in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Process (ICASSP) (2011).","DOI":"10.1109\/ICASSP.2011.5946318"},{"key":"10.3233\/IDA-170869_ref7","doi-asserted-by":"crossref","unstructured":"Virtanen T., Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Trans. Audio, Speech and Language Processing 15 (2007), 1066-1074. %Hurmalainen A., Saeidi R. and Virtanen T., %Similarity induced group %sparsity for non-negative matrix factorization, in Proc. IEEE Int. Conf. Acoustics, % Speech, and Signal Process (ICASSP) (2015).","DOI":"10.1109\/TASL.2006.885253"},{"volume-title":"ISM Research Memo","year":"2001","author":"Eguchi","key":"10.3233\/IDA-170869_ref8"},{"key":"10.3233\/IDA-170869_ref9","doi-asserted-by":"crossref","unstructured":"Eggert J. and K\u00f6rner E., Sparse coding and NMF, in Proc. IEEE International Joint Conference on Neural Networks 4, 2529-2533.","DOI":"10.1109\/IJCNN.2004.1381036"},{"key":"10.3233\/IDA-170869_ref10","doi-asserted-by":"crossref","unstructured":"Belkin M. and Niyogi P., Laplacian eigenmaps and spectral techniques for embedding and clustering, Advances in neural information processing systems (2001). Cambridge, MA: MIT Press.","DOI":"10.7551\/mitpress\/1120.003.0080"},{"key":"10.3233\/IDA-170869_ref11","first-page":"351","article-title":"Speech database development at MIT: Timit and beyond","author":"Seneff","year":"1990","journal-title":"Speech Communication"},{"key":"10.3233\/IDA-170869_ref12","doi-asserted-by":"crossref","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","article-title":"Performance measurement in blind audio source separation","volume":"14","author":"Vincent","year":"2006","journal-title":"IEEE Trans. Audio, Speech and Language Processing"},{"volume-title":"Elsevier","year":"2007","author":"Mikkel","key":"10.3233\/IDA-170869_ref13"},{"key":"10.3233\/IDA-170869_ref14","unstructured":"Reddy A.M. and Raj B., Soft mask estimation for single channel speaker separation, in Proc. ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing (October 2004)."},{"key":"10.3233\/IDA-170869_ref15","first-page":"1548","article-title":"Graph regularized nonnegative matrix factorization for data representation","author":"Cai","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"10.3233\/IDA-170869_ref16","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1162\/neco.2008.04-08-771","article-title":"Nonnegative matrix factorization with the Itakura-Saito divergence: With application to music","author":"Fevotte","year":"2009","journal-title":"Neural Comput"},{"key":"10.3233\/IDA-170869_ref17","doi-asserted-by":"crossref","unstructured":"Sun D.L. and Mysore G.J., Universal speech models for speaker independent single channel source separation, in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Process (2013), Vancouver.","DOI":"10.1109\/ICASSP.2013.6637625"},{"key":"10.3233\/IDA-170869_ref18","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.1109\/TASLP.2014.2320575","article-title":"Learning a discriminative dictionary for single-channel speech separation","author":"Bao","year":"2014","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.3233\/IDA-170869_ref19","doi-asserted-by":"crossref","first-page":"4298","DOI":"10.1109\/TSP.2014.2332434","article-title":"Kernel additive models for source separation","author":"Liutkus","year":"2014","journal-title":"Signal Processing IEEE Transactions on"},{"key":"10.3233\/IDA-170869_ref20","first-page":"229","article-title":"NMF-based target source separation using deep neural network","author":"Gyoon","year":"2015","journal-title":"IEEE Signals Processing Letters"},{"key":"10.3233\/IDA-170869_ref21","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.1121\/1.2229005","article-title":"An audio-visual corpus for speech perception and automatic speech recognition","author":"Cooke","year":"2006","journal-title":"J. of the Acoustical Society of America"},{"key":"10.3233\/IDA-170869_ref22","first-page":"2614","article-title":"Single-channel speech separation using sparse non-negative matrix factorization","author":"Schmidt","year":"2006","journal-title":"Proc. Interspeech"},{"key":"10.3233\/IDA-170869_ref23","doi-asserted-by":"crossref","first-page":"2299","DOI":"10.1109\/TASL.2007.904233","article-title":"Single-channel speech separation using soft mask filtering","author":"Radfar","year":"2007","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"10.3233\/IDA-170869_ref24","doi-asserted-by":"crossref","first-page":"2586","DOI":"10.1109\/TASL.2012.2208627","article-title":"A joint approach for single-channel speaker identification and speech separation","author":"Mowlaee","year":"2012","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"10.3233\/IDA-170869_ref25","doi-asserted-by":"crossref","unstructured":"Xu W., Xin L. and Yihong G., Document clustering based on non-negative matrix factorization, in Proc. of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval (2003).","DOI":"10.1145\/860484.860485"},{"volume-title":"Society for Industrial and Applied Mathematics","year":"2004","author":"Pauca","key":"10.3233\/IDA-170869_ref26"},{"key":"10.3233\/IDA-170869_ref27","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1109\/TIP.2010.2090535","article-title":"Graph regularized sparse coding for image representation","author":"Zheng","year":"2011","journal-title":"IEEE Trans. Image Process"},{"key":"10.3233\/IDA-170869_ref28","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1109\/LSP.2012.2229976","article-title":"Improving dictionary learning: Multiple dictionary updates and coefficient reuse","volume":"20","author":"Smith","year":"2013","journal-title":"Signal Processing Letters, IEEE"},{"key":"10.3233\/IDA-170869_ref29","first-page":"87","article-title":"An overview of bilevel optimization","author":"Colson","year":"2005","journal-title":"Annals of Operations Research"},{"key":"10.3233\/IDA-170869_ref30","doi-asserted-by":"crossref","unstructured":"Sprechmann P., Bronstein A. and Sapiro G., Supervised non-euclidean sparse NMF via bilevel optimization with applications to speech enhancement, in: Hands-free Speech Communication and Microphone Arrays (HSCMA), 4th Joint Workshop on (2014), pp. 11-15. IEEE.","DOI":"10.1109\/HSCMA.2014.6843241"},{"key":"10.3233\/IDA-170869_ref31","unstructured":"Yakar T.B., Sprechmann P., Litman R., Bronstein A.M. and Sapiro G., Bilevel Sparse Models for Polyphonic Music Transcription, In ISMIR (2013), pp. 65-70."},{"key":"10.3233\/IDA-170869_ref32","doi-asserted-by":"crossref","unstructured":"Tropp J., Needell D. and Vershynin R., Iterative signal recovery from incomplete and inaccurate measurements, Information Theory and Applications (2008).","DOI":"10.1109\/ACSSC.2008.5074572"},{"key":"10.3233\/IDA-170869_ref33","doi-asserted-by":"crossref","first-page":"2230","DOI":"10.1109\/TIT.2009.2016006","article-title":"Subspace pursuit for compressive sensing signal reconstruction","author":"Dai","year":"2009","journal-title":"Information Theory, IEEE Transactions on"},{"key":"10.3233\/IDA-170869_ref34","unstructured":"Logan B., Mel frequency cepstral coefficients for music modeling, ISMIR (2000)."},{"issue":"16","key":"10.3233\/IDA-170869_ref35","doi-asserted-by":"crossref","first-page":"4114","DOI":"10.1109\/TSP.2014.2326991","article-title":"Deep scattering spectrum","volume":"62","author":"And\u00e9n","year":"2014","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.3233\/IDA-170869_ref36","doi-asserted-by":"crossref","unstructured":"Bruna J., Sprechmann P. and Lecun Y., Source separation with scattering non-negative matrix factorization, Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Process (April 2015).","DOI":"10.1109\/ICASSP.2015.7178296"},{"key":"10.3233\/IDA-170869_ref37","first-page":"55","article-title":"Single Channel Source Separation Using Sparse NMF and Graph Regularization","author":"Pham","year":"2015","journal-title":"Proceedings of the ASE BigData & SocialInformatics"},{"key":"10.3233\/IDA-170869_ref39","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1109\/MSP.2013.2297715","article-title":"Static and dynamic source separation using nonnegative factorizations: A unified view","author":"Smaragdis","year":"2014","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.3233\/IDA-170869_ref40","unstructured":"Huang P.S., Kim M., Hasegawa-Johnson M. and Smaragdis P., Deep learning for monaural speech separation, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014). pp. 1562-1566. IEEE."}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-170869","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:24:52Z","timestamp":1750195492000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-170869"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,1]]},"references-count":38,"URL":"https:\/\/doi.org\/10.3233\/ida-170869","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"type":"print","value":"1088-467X"},{"type":"electronic","value":"1571-4128"}],"subject":[],"published":{"date-parts":[[2017,4,1]]}}}