Artificial bandwidth extension of spectral envelope along a Viterbi path. Yagli, C., Turan, M. A. T., & Erzin, E. SPEECH COMMUNICATION, 55(1):111-118, JAN, 2013. doi abstract bibtex In this paper, we propose a hidden Markov model (HMM)-based wideband spectral envelope estimation method for the artificial bandwidth extension problem. The proposed HMM-based estimator decodes an optimal Viterbi path based on the temporal contour of the narrowband spectral envelope and then performs the minimum mean square error (MMSE) estimation of the wideband spectral envelope on this path. Experimental evaluations are performed to compare the proposed estimator to the state-of-the-art HMM and Gaussian mixture model based estimators using both objective and subjective evaluations. Objective evaluations are performed with the log-spectral distortion (LSD) and the wideband perceptual evaluation of speech quality (PESQ) metrics. Subjective evaluations are performed with the A/B pair comparison listening test. Both objective and subjective evaluations yield that the proposed wideband spectral envelope estimator consistently improves performances over the state-of-the-art estimators. (C) 2012 Elsevier B.V. All rights reserved.
@article{ ISI:000312422900009,
Author = {Yagli, Can and Turan, M. A. Tugtekin and Erzin, Engin},
Title = {{Artificial bandwidth extension of spectral envelope along a Viterbi path}},
Journal = {{SPEECH COMMUNICATION}},
Year = {{2013}},
Volume = {{55}},
Number = {{1}},
Pages = {{111-118}},
Month = {{JAN}},
Abstract = {{In this paper, we propose a hidden Markov model (HMM)-based wideband
spectral envelope estimation method for the artificial bandwidth
extension problem. The proposed HMM-based estimator decodes an optimal
Viterbi path based on the temporal contour of the narrowband spectral
envelope and then performs the minimum mean square error (MMSE)
estimation of the wideband spectral envelope on this path. Experimental
evaluations are performed to compare the proposed estimator to the
state-of-the-art HMM and Gaussian mixture model based estimators using
both objective and subjective evaluations. Objective evaluations are
performed with the log-spectral distortion (LSD) and the wideband
perceptual evaluation of speech quality (PESQ) metrics. Subjective
evaluations are performed with the A/B pair comparison listening test.
Both objective and subjective evaluations yield that the proposed
wideband spectral envelope estimator consistently improves performances
over the state-of-the-art estimators. (C) 2012 Elsevier B.V. All rights
reserved.}},
DOI = {{10.1016/j.specom.2012.07.003}},
ISSN = {{0167-6393}},
EISSN = {{1872-7182}},
Unique-ID = {{ISI:000312422900009}},
}
Downloads: 0
{"_id":"tpYXsnCfzCGyCNRRe","bibbaseid":"yagli-turan-erzin-artificialbandwidthextensionofspectralenvelopealongaviterbipath-2013","downloads":0,"creationDate":"2015-12-09T21:23:15.158Z","title":"Artificial bandwidth extension of spectral envelope along a Viterbi path","author_short":["Yagli, C.","Turan, M. A. T.","Erzin, E."],"year":2013,"bibtype":"article","biburl":"https://bibbase.org/network/files/CiHbjYG79MLcGLJka","bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Yagli"],"firstnames":["Can"],"suffixes":[]},{"propositions":[],"lastnames":["Turan"],"firstnames":["M.","A.","Tugtekin"],"suffixes":[]},{"propositions":[],"lastnames":["Erzin"],"firstnames":["Engin"],"suffixes":[]}],"title":"Artificial bandwidth extension of spectral envelope along a Viterbi path","journal":"SPEECH COMMUNICATION","year":"2013","volume":"55","number":"1","pages":"111-118","month":"JAN","abstract":"In this paper, we propose a hidden Markov model (HMM)-based wideband spectral envelope estimation method for the artificial bandwidth extension problem. The proposed HMM-based estimator decodes an optimal Viterbi path based on the temporal contour of the narrowband spectral envelope and then performs the minimum mean square error (MMSE) estimation of the wideband spectral envelope on this path. Experimental evaluations are performed to compare the proposed estimator to the state-of-the-art HMM and Gaussian mixture model based estimators using both objective and subjective evaluations. Objective evaluations are performed with the log-spectral distortion (LSD) and the wideband perceptual evaluation of speech quality (PESQ) metrics. Subjective evaluations are performed with the A/B pair comparison listening test. Both objective and subjective evaluations yield that the proposed wideband spectral envelope estimator consistently improves performances over the state-of-the-art estimators. (C) 2012 Elsevier B.V. All rights reserved.","doi":"10.1016/j.specom.2012.07.003","issn":"0167-6393","eissn":"1872-7182","unique-id":"ISI:000312422900009","bibtex":"@article{ ISI:000312422900009,\nAuthor = {Yagli, Can and Turan, M. A. Tugtekin and Erzin, Engin},\nTitle = {{Artificial bandwidth extension of spectral envelope along a Viterbi path}},\nJournal = {{SPEECH COMMUNICATION}},\nYear = {{2013}},\nVolume = {{55}},\nNumber = {{1}},\nPages = {{111-118}},\nMonth = {{JAN}},\nAbstract = {{In this paper, we propose a hidden Markov model (HMM)-based wideband\n spectral envelope estimation method for the artificial bandwidth\n extension problem. The proposed HMM-based estimator decodes an optimal\n Viterbi path based on the temporal contour of the narrowband spectral\n envelope and then performs the minimum mean square error (MMSE)\n estimation of the wideband spectral envelope on this path. Experimental\n evaluations are performed to compare the proposed estimator to the\n state-of-the-art HMM and Gaussian mixture model based estimators using\n both objective and subjective evaluations. Objective evaluations are\n performed with the log-spectral distortion (LSD) and the wideband\n perceptual evaluation of speech quality (PESQ) metrics. Subjective\n evaluations are performed with the A/B pair comparison listening test.\n Both objective and subjective evaluations yield that the proposed\n wideband spectral envelope estimator consistently improves performances\n over the state-of-the-art estimators. (C) 2012 Elsevier B.V. All rights\n reserved.}},\nDOI = {{10.1016/j.specom.2012.07.003}},\nISSN = {{0167-6393}},\nEISSN = {{1872-7182}},\nUnique-ID = {{ISI:000312422900009}},\n}\n\n","author_short":["Yagli, C.","Turan, M. A. T.","Erzin, E."],"key":"ISI:000312422900009","id":"ISI:000312422900009","bibbaseid":"yagli-turan-erzin-artificialbandwidthextensionofspectralenvelopealongaviterbipath-2013","role":"author","urls":{},"metadata":{"authorlinks":{"erzin, e":"http://home.ku.edu.tr/~eerzin/pubs/index6.html"}},"downloads":0},"search_terms":["artificial","bandwidth","extension","spectral","envelope","along","viterbi","path","yagli","turan","erzin"],"keywords":[],"authorIDs":["56689bc2b3110c264a000354","566927fe71adeb5a05000063","s4rze5RZET4EY5wXY"],"dataSources":["P7SB4qiBxZPhjXYRW","eoMYcQtZLjtLCGT3K","YTpRk266Eztyjz8mi"]}