{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T12:15:03Z","timestamp":1648556103600},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,12,1]],"date-time":"2013-12-01T00:00:00Z","timestamp":1385856000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1186\/1687-4722-2013-28","type":"journal-article","created":{"date-parts":[[2013,12,11]],"date-time":"2013-12-11T00:01:45Z","timestamp":1386720105000},"source":"Crossref","is-referenced-by-count":7,"title":["A novel voice conversion approach using admissible wavelet packet decomposition"],"prefix":"10.1186","volume":"2013","author":[{"given":"Jagannath H","family":"Nirmal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mukesh A","family":"Zaveri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suprava","family":"Patnaik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pramod H","family":"Kachare","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,12,10]]},"reference":[{"issue":"2","key":"92_CR1","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1109\/TASL.2006.876760","volume":"15","author":"K-S Lee","year":"2007","unstructured":"Lee K-S: Statistical approach for voice personality transformation. Audio, Speech, Lang. Process., IEEE Trans 2007, 15(2):641-651.","journal-title":"Audio, Speech, Lang. Process., IEEE Trans"},{"key":"92_CR2","first-page":"I-9","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201904), vol. 1,","author":"H Ye","year":"2004","unstructured":"Ye H, Young S: High quality voice morphing. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201904), vol. 1,. Montreal; 17\u201321 May 2004:I-9\u201312."},{"key":"92_CR3","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/S0167-6393(99)00015-1","volume":"28","author":"LM Arslan","year":"1999","unstructured":"Arslan LM: Speaker transformation algorithm using segmental code books (stasc). Speech Commun 1999, 28: 211-226. 10.1016\/S0167-6393(99)00015-1","journal-title":"Speech Commun"},{"key":"92_CR4","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/0167-6393(94)00053-D","volume":"16","author":"H Kuwabara","year":"1995","unstructured":"Kuwabara H, Sagisaka Y: Acoustics characteristics of speaker individuality: control and conversion. Speech Commun 1995, 16: 165-173. 10.1016\/0167-6393(94)00053-D","journal-title":"Speech Commun"},{"key":"92_CR5","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1109\/ICASSP.1988.196671","volume-title":"International Conference on Acoustics, Speech, and Signal Processing (ICASSP-88)","author":"M Abe","year":"1988","unstructured":"Abe M, Nakamura S, Shikano K, Kuwabara H: Voice conversion through vector quantization. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP-88). New York, NY; 11\u201314 April 1988:655-658."},{"key":"92_CR6","first-page":"813","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201901), vol. 2","author":"A Kain","year":"2001","unstructured":"Kain A, Macon MW: Design and evaluation of a voice conversion algorithm based on spectral envelope mapping and residual prediction. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201901), vol. 2. Salt Lake City, UT; 7\u201311 May 2001:813-816."},{"issue":"3","key":"92_CR7","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/j.csl.2009.03.003","volume":"24","author":"KS Rao","year":"2010","unstructured":"Rao KS: Voice conversion by mapping the speaker-specific features using pitch synchronous approach. Comput. Speech & Lang 2010, 24(3):474-494. 10.1016\/j.csl.2009.03.003","journal-title":"Comput. Speech & Lang"},{"issue":"4","key":"92_CR8","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/j.csl.2005.06.001","volume":"20","author":"O Turk","year":"2006","unstructured":"Turk O, Arslan LM: Robust processing techniques for voice conversion. Comput. Speech & Lang 2006, 20(4):441-467. 10.1016\/j.csl.2005.06.001","journal-title":"Comput. Speech & Lang"},{"issue":"5","key":"92_CR9","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1109\/TASL.2010.2047683","volume":"18","author":"S Desai","year":"2010","unstructured":"Desai S, Black AW, Yegnanarayana B, Prahallad K: Spectral mapping using artificial neural networks for voice conversion. Audio, Speech, and Lang. Process., IEEE Trans 2010, 18(5):954-964.","journal-title":"Audio, Speech, and Lang. Process., IEEE Trans"},{"issue":"5","key":"92_CR10","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1109\/TASL.2010.2041699","volume":"18","author":"E Helander","year":"2010","unstructured":"Helander E, Virtanen T, Nurminen J, Gabbouj M: Voice conversion using partial least squares regression. Audio, Speech, Lang. Process., IEEE Trans 2010, 18(5):912-921.","journal-title":"Audio, Speech, Lang. Process., IEEE Trans"},{"key":"92_CR11","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1109\/ASRU.2005.1566484","volume-title":"2005 IEEE Workshop on Automatic Speech Recognition and Understanding","author":"D Sundermann","year":"2005","unstructured":"Sundermann D, Hoge H, Bonafonte A, Ney H, Black AW: Residual prediction based on unit selection. In 2005 IEEE Workshop on Automatic Speech Recognition and Understanding. San Juan; 27 Nov 2005:369-374."},{"issue":"4","key":"92_CR12","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.specom.2007.10.005","volume":"50","author":"X Lu","year":"2008","unstructured":"Lu X, Dang J: An investigation of dependencies between frequency components and speaker characteristics for text-independent speaker identification. Speech Commun 2008, 50(4):312-322. 10.1016\/j.specom.2007.10.005","journal-title":"Speech Commun"},{"issue":"3","key":"92_CR13","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/S0167-6393(98)00085-5","volume":"27","author":"H Kawahara","year":"1999","unstructured":"Kawahara H, Masuda-Katsuse I, de Cheveign\u00e9 A: Restructuring speech representations using a pitch-adaptive time\u2013frequency smoothing and an instantaneous-frequency-based f0 extractionpossible role of a repetitive structure in sounds. Speech Commun 1999, 27(3):187-207.","journal-title":"Speech Commun"},{"key":"92_CR14","first-page":"I\/137","volume-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing, (ICASSP-94), vol.1","author":"S Hayakawa","year":"1994","unstructured":"Hayakawa S, Itakura F: Text-dependent speaker recognition using the information in the higher frequency band. In IEEE International Conference on Acoustics, Speech, and Signal Processing, (ICASSP-94), vol.1. Adelaide; 19\u201322 Apr 1994:I\/137-140."},{"key":"92_CR15","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1109\/ICASSP.1983.1172250","volume-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '83","author":"S Imai","year":"1983","unstructured":"Imai S: Cepstral analysis synthesis on the mel frequency scale. In IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '83. Boston, MA; 14\u201316 April 1983:93-96."},{"key":"92_CR16","first-page":"289","volume-title":"International Conference on Spoken Language Processing","author":"O Turk","year":"2002","unstructured":"Turk O, Arslan LM: Subband based voice conversion. In International Conference on Spoken Language Processing. Denver, CO; 16\u201320 Sept 2002:289-292."},{"key":"92_CR17","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/978-3-540-46551-5_5","volume-title":"Algorithms for Approximation","author":"C Orphanidou","year":"2007","unstructured":"Orphanidou C, Moroz IM, Roberts SJ: Multiscale voice morphing using radial basis function analysis. In Algorithms for Approximation. Berlin Heidelberg: Springer; 2007:61-69."},{"issue":"1","key":"92_CR18","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.neucom.2007.08.010","volume":"71","author":"RC Guido","year":"2007","unstructured":"Guido RC, Sasso Vieira L, Barbon J\u00fanior S, Sanchez FL, Dias Maciel C, Silva Fonseca E, Carlos Pereira J: A neural-wavelet architecture for voice conversion. Neurocomputing 2007, 71(1):174-180.","journal-title":"Neurocomputing"},{"issue":"2","key":"92_CR19","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/0167-6393(86)90007-5","volume":"5","author":"S Furui","year":"1986","unstructured":"Furui S: Research of individuality features in speech waves and automatic speaker recognition techniques. Speech Commun 1986, 5(2):183-197. 10.1016\/0167-6393(86)90007-5","journal-title":"Speech Commun"},{"issue":"11","key":"92_CR20","doi-asserted-by":"publisher","first-page":"3332","DOI":"10.1016\/j.asoc.2012.05.027","volume":"12","author":"R Laskar","year":"2012","unstructured":"Laskar R, Chakrabarty D, Talukdar F, Rao KS, Banerjee K: Comparing ann and gmm in a voice conversion framework. Appl. Soft Comput 2012, 12(11):3332-3342. 10.1016\/j.asoc.2012.05.027","journal-title":"Appl. Soft Comput"},{"key":"92_CR21","first-page":"225","volume-title":"International (TC-STAR) Workshop on Speech-to-Speech Translation, Audio and Visual Communications,Nokia Research Center","author":"J Nurminen","year":"2006","unstructured":"Nurminen J, Popa V, Tian J, Tang Y, Kiss I: A parametric approach for voice conversion. In International (TC-STAR) Workshop on Speech-to-Speech Translation, Audio and Visual Communications,Nokia Research Center. Barcelona, Spain; June 2006:225-229."},{"issue":"2","key":"92_CR22","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/0167-6393(94)00058-I","volume":"16","author":"M Narendranath","year":"1995","unstructured":"Narendranath M, Murthy HA, Rajendran S, Yegnanarayana B: Transformation of formants for voice conversion using artificial neural networks. Speech Commun 1995, 16(2):207-216. 10.1016\/0167-6393(94)00058-I","journal-title":"Speech Commun"},{"key":"92_CR23","first-page":"2581","volume-title":"Proceedings of the ICSLP 2002,INTERSPEECH","author":"E Ormanci","year":"2002","unstructured":"Ormanci E, Nikbay UH, Turk O, Arslan LM: Subjective assessment of frequency bands for perception of speaker identity. In Proceedings of the ICSLP 2002,INTERSPEECH. Denver, CO; 16\u201320 September 2002:2581-2584."},{"issue":"7","key":"92_CR24","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/97.928676","volume":"8","author":"O Farooq","year":"2001","unstructured":"Farooq O, Datta S: Mel filter-like admissible wavelet packet structure for speech recognition. Signal Processing Letters, IEEE 2001, 8(7):196-198.","journal-title":"Signal Processing Letters, IEEE"},{"issue":"8","key":"92_CR25","doi-asserted-by":"publisher","first-page":"1518","DOI":"10.1016\/j.patcog.2006.02.004","volume":"39","author":"S-Y Lung","year":"2006","unstructured":"Lung S-Y: Wavelet feature selection based neural networks with application to the text independent speaker identification. Pattern Recognit 2006, 39(8):1518-1521. 10.1016\/j.patcog.2006.02.004","journal-title":"Pattern Recognit"},{"issue":"3","key":"92_CR26","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1016\/j.dsp.2006.06.007","volume":"17","author":"LD Alsteris","year":"2007","unstructured":"Alsteris LD, Paliwal KK: Short-time phase spectrum in speech processing: a review and some experimental results. Digit. Signal Process 2007, 17(3):578-616. 10.1016\/j.dsp.2006.06.007","journal-title":"Digit. Signal Process"},{"key":"92_CR27","first-page":"16","volume-title":"Seventh International Conference on Spoken Language Processing, INTERSPEECH, ISCA(2002)","author":"T Watanabe","year":"2002","unstructured":"Watanabe T, Murakami T, Namba M, Hoya T, Ishida Y: Transformation of spectral envelope for voice conversion based on radial basis function networks. Seventh International Conference on Spoken Language Processing, INTERSPEECH, ISCA(2002), (Denver, CO, 16\u201320 September 2002)"},{"issue":"2","key":"92_CR28","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/0167-6393(94)00051-B","volume":"16","author":"N Iwahashi","year":"1995","unstructured":"Iwahashi N, Sagisaka Y: Speech spectrum conversion based on speaker interpolation and multi-functional representation with weighting by radial basis function networks. Speech Commun 1995, 16(2):139-151. 10.1016\/0167-6393(94)00051-B","journal-title":"Speech Commun"},{"key":"92_CR29","first-page":"223","volume-title":"SSW5-2004","author":"J Kominek","year":"2004","unstructured":"Kominek J, Black AW: The CMU ARCTIC Speech Databases. In SSW5-2004. Pittsburgh, PA; 14\u201316 June 2004:223-224."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2013-28\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-28.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-28.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T02:01:46Z","timestamp":1548122506000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2013-28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["92"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2013-28","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,12]]},"article-number":"28"}}