{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:16Z","timestamp":1740122776107,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,6,6]],"date-time":"2018-06-06T00:00:00Z","timestamp":1528243200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100006187","name":"Ecole Nationale d\u2019Ing\u00e9nieurs de Tunis","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006187","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s10772-018-9522-9","type":"journal-article","created":{"date-parts":[[2018,6,6]],"date-time":"2018-06-06T14:56:34Z","timestamp":1528296994000},"page":"619-632","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Determining the optimal conditions for signal reconstruction based on STFT magnitude"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1154-4893","authenticated-orcid":false,"given":"Raja","family":"Abdelmalek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zied","family":"Mnasri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faouzi","family":"Benzarti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,6]]},"reference":[{"unstructured":"Adler, A., et al. (2016). A deep learning approach to block-based compressed sensing of images. arXiv preprint arXiv: 1606.01519.","key":"9522_CR1"},{"doi-asserted-by":"crossref","unstructured":"Alsteris, L. D., & Paliwal, K. K. (2004). Importance of window shape for phase-only reconstruction of speech. In Proceedings of IEEE international conference on acoustics, speech, and signal processing, 2004 (ICASSP\u201904), Vol.\u00a01, Montreal, QC, Canada.","key":"9522_CR2","DOI":"10.1109\/ICASSP.2004.1326050"},{"issue":"S1","key":"9522_CR3","doi-asserted-by":"publisher","first-page":"S140","DOI":"10.1121\/1.2003853","volume":"64","author":"III Barnwell","year":"1978","unstructured":"Barnwell, I. I. I., Thomas, P., & Voiers, W. D. (1978). Objective measures for speech quality testing. The Journal of the Acoustical Society of America, 64(S1), S140.","journal-title":"The Journal of the Acoustical Society of America"},{"doi-asserted-by":"crossref","unstructured":"Beauregard, G. T., Harish, M., & Wyse, L. (2015). Single pass spectrogram inversion. In IEEE international conference on digital signal processing (DSP), Imperial College, London.","key":"9522_CR4","DOI":"10.1109\/ICDSP.2015.7251907"},{"unstructured":"Beauregard, G. T., Zhu, X. & Wyse, L. (2005). An efficient algorithm for real-time spectrogram inversion. In Proceedings of the 8th international conference on digital audio effects, Madrid, Spain.","key":"9522_CR5"},{"issue":"5","key":"9522_CR6","first-page":"870","volume":"86","author":"M Boudraa","year":"2000","unstructured":"Boudraa, M., Boudraa, B., & Guerin, B. (2000). Twenty lists of ten Arabic sentences for assessment. Acta Acustica United with Acustica, 86(5), 870\u2013882.","journal-title":"Acta Acustica United with Acustica"},{"issue":"2","key":"9522_CR7","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1137\/151005099","volume":"57","author":"EJ Candes","year":"2015","unstructured":"Candes, E. J., et al. (2015). Phase retrieval via matrix completion. SIAM Review, 57(2), 225\u2013251.","journal-title":"SIAM Review"},{"issue":"6","key":"9522_CR8","doi-asserted-by":"publisher","first-page":"483","DOI":"10.18178\/ijsps.4.6.483-486","volume":"4","author":"UV Dias","year":"2016","unstructured":"Dias, U. V., Mascarenhas, J. E., & Dias, L. J. (2016). Compressive sensed speech recognition. International Journal of Signal Processing Systems, 4(6), 483\u2013486.","journal-title":"International Journal of Signal Processing Systems"},{"issue":"5","key":"9522_CR9","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1109\/89.466653","volume":"3","author":"S Dimolitsas","year":"1995","unstructured":"Dimolitsas, S., Corcoran, F. L., & Ravishankar, C. (1995). Dependence of opinion scores on listening sets used in degradation category rating assessments. IEEE Transactions on Speech and Audio Processing, 3(5), 421\u2013424.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"doi-asserted-by":"crossref","unstructured":"Govind, D., & Prasanna, S. R. M. (2012). Epoch extraction from emotional speech. In International conference on signal processing and communications (SPCOM), Indian Institute of Science, Bangalore.","key":"9522_CR10","DOI":"10.1109\/SPCOM.2012.6289995"},{"doi-asserted-by":"crossref","unstructured":"Govind, D., Prasanna, S. R. M., & Pati, D. (2011a). Epoch extraction in high pass filtered speech using hilbert envelope. In Twelfth annual conference of the international speech communication association, Florence, Italy.","key":"9522_CR11","DOI":"10.21437\/Interspeech.2011-520"},{"doi-asserted-by":"crossref","unstructured":"Govind, D., Prasanna, S. R. M. & Yegnanarayana, B. (2011b). Neutral to target emotion conversion using source and suprasegmental information. In Twelfth annual conference of the international speech communication association.","key":"9522_CR12","DOI":"10.21437\/Interspeech.2011-743"},{"doi-asserted-by":"crossref","unstructured":"Govind, D., Vishnu, R., & Pravena, D. (2015). Improved method for epoch estimation in telephonic speech signals using zero frequency filtering. In IEEE international conference on signal and image processing applications (ICSIPA), Kuala Lumpur, Malaysia.","key":"9522_CR13","DOI":"10.1109\/ICSIPA.2015.7412155"},{"issue":"2","key":"9522_CR14","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1109\/TASSP.1984.1164317","volume":"32","author":"D Griffin","year":"1984","unstructured":"Griffin, D., & Lim, J. (1984). Signal estimation from modified short-time Fourier transform. IEEE Transactions on Acoustics, Speech, and Signal Processing, 32(2), 236\u2013243.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"5","key":"9522_CR15","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1109\/LSP.2010.2042530","volume":"17","author":"D Gunawan","year":"2010","unstructured":"Gunawan, D., & Sen, D. (2010). Iterative phase estimation for the synthesis of separated sources from single-channel mixtures. IEEE Transactions on Signal Processing Letters, 17(5), 421\u2013424.","journal-title":"IEEE Transactions on Signal Processing Letters"},{"unstructured":"Halabi, N. & Wald, M. (2016). Phonetic inventory for an Arabic speech corpus, pp.\u00a0734\u2013738.","key":"9522_CR16"},{"issue":"6","key":"9522_CR18","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1109\/TASSP.1980.1163463","volume":"28","author":"M Hayes","year":"1980","unstructured":"Hayes, M., Lim, J., & Oppenheim, A. (1980). Signal reconstruction from phase or magnitude. IEEE Transactions on Acoustics, Speech, and Signal Processing, 28(6), 672\u2013680.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9522_CR19","volume-title":"Objective quality measurement of telephone-band (300\u20133400 Hz) speech codecs","author":"ITU-T Recommendation P.861","year":"1996","unstructured":"ITU-T Recommendation P.861. (1996). Objective quality measurement of telephone-band (300\u20133400 Hz) speech codecs. Geneva: ITU-T Recommendation P.861."},{"unstructured":"Le Roux, J., Ono, N. & Sagayama, S. (2008). Explicit consistency constraints for STFT spectrograms and their application to phase reconstruction. In Proceedings of SAPA@ INTERSPEECH, pp.\u00a023\u201328.","key":"9522_CR20"},{"issue":"3","key":"9522_CR21","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1109\/LSP.2012.2225617","volume":"20","author":"J Roux Le","year":"2013","unstructured":"Le Roux, J., & Vincent, E. (2013). Consistent Wiener filtering for audio source separation. IEEE Transactions on Signal Processing Letters, 20(3), 217\u2013220.","journal-title":"IEEE Transactions on Signal Processing Letters"},{"doi-asserted-by":"crossref","unstructured":"Loveimi, E., Ahadi, S. M. (2010). Objective evaluation of magnitude and phase only spectrum-based reconstruction of the speech signal. In 4th international symposium on communications, control and signal processing (ISCCSP), Limassol, Cyprus.","key":"9522_CR22","DOI":"10.1109\/ISCCSP.2010.5463311"},{"doi-asserted-by":"crossref","unstructured":"Maia, R., Akamine, M., & Gales, M. J. (2012). Complex cepstrum as phase information in statistical parametric speech synthesis. In IEEE international conference on acoustics, speech and signal processing (ICASSP), Kyoto, Japan.","key":"9522_CR23","DOI":"10.1109\/ICASSP.2012.6288938"},{"issue":"8","key":"9522_CR24","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1109\/TASLP.2015.2430820","volume":"23","author":"P Mowlaee","year":"2015","unstructured":"Mowlaee, P., & Kulmer, J. (2015). Phase estimation in single-channel speech enhancement: Limits-potential. IEEE Transactions on Audio, Speech, and Language Processing, 23(8), 1283\u20131294.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"unstructured":"Mowlaee, P., Saeidi, R. & Martin, R. (2012). Phase estimation in single-channel source separation. In Proceedings of the INTERSPEECH, Singapore, pp.\u00a01\u20134.","key":"9522_CR25"},{"unstructured":"Mowlaee, P., Saeidi, R., & Stylanou, Y. (2014). INTERSPEECH 2014 special session: Phase importance in speech processing applications. In Proceedings of the 15th international conference on spoken language processing, The Pennsylvania State University, Pennsylvania.","key":"9522_CR26"},{"unstructured":"Nakagawa, S., Asakawa, K., & Wang, L. (2007). Speaker recognition by combining MFCC and phase information spectrum 60.700 Hz. In Eighth annual conference of the international speech communication association, Francisco, CA, pp.\u00a076\u201374.","key":"9522_CR27"},{"issue":"1","key":"9522_CR28","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/TASL.2006.876878","volume":"15","author":"PA Naylor","year":"2007","unstructured":"Naylor, P. A., et al. (2007). Estimation of glottal closure instants in voiced speech using the DYPSA algorithm. IEEE Transactions on Audio, Speech, and Language Processing, 15(1), 34\u201343.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"doi-asserted-by":"crossref","unstructured":"Paliwal, K. K., & Alsteris, L. D. (2003). Usefulness of phase spectrum in human speech perception. In INTERSPEECH, Geneva, Switzerland.","key":"9522_CR29","DOI":"10.21437\/Eurospeech.2003-611"},{"issue":"2","key":"9522_CR30","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.specom.2004.08.001","volume":"45","author":"KK Paliwal","year":"2005","unstructured":"Paliwal, K. K., & Alsteris, L. D. (2005). On the usefulness of STFT phase spectrum in human listening tests. Speech Communication, 45(2), 153\u2013170.","journal-title":"Speech Communication"},{"unstructured":"Pru\u0161a, Z., & S\u00f8ndergaard, P. L. (2016). Real-time spectrogram inversion using phase gradient heap integration. In Proceedings of international conference on digital audio effects (DAFx-16), Edinburgh, Scotland.","key":"9522_CR31"},{"doi-asserted-by":"crossref","unstructured":"Ramdas, V., Mishra, D. & Gorthi, S. S. (2015). Speech coding and enhancement using quantized compressive sensing measurements. In IEEE international conference on Signal processing, informatics, communication and energy systems (SPICES), National Institute of Technology Calicut, Kerala, India.","key":"9522_CR32","DOI":"10.1109\/SPICES.2015.7091436"},{"issue":"4","key":"9522_CR33","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/s10772-017-9423-3","volume":"20","author":"H Shawky","year":"2017","unstructured":"Shawky, H., et al. (2017). Efficient compression and reconstruction of speech signals using compressed sensing. International Journal of Speech Technology, 20(4), 851\u2013857.","journal-title":"International Journal of Speech Technology"},{"issue":"5","key":"9522_CR34","doi-asserted-by":"publisher","first-page":"1867","DOI":"10.1109\/TSA.2005.858512","volume":"14","author":"G Shi","year":"2006","unstructured":"Shi, G., Shanechi, M. M., & Aarabi, P. (2006). On the importance of phase in human speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, 14(5), 1867\u20131874.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9522_CR35","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.sigpro.2014.03.049","volume":"104","author":"S Stankovi\u0107","year":"2014","unstructured":"Stankovi\u0107, S., Orovi\u0107, I. & Stankovi\u0107, L. (2014). An automated signal reconstruction method based on analysis of compressive sensed signals in noisy environment. Signal Processing, 104, 43\u201350.","journal-title":"Signal Processing"},{"unstructured":"Sturmel, N., & Daudet, L. (2011). Signal reconstruction from STFT magnitude: A state of the art. In International conference on digital audio effects (DAFx), Paris, France.","key":"9522_CR36"},{"unstructured":"Thorpe, L. A., & Shelton, B. (1993). Subjective test methodology: MOS vs. DMOS in evaluation of speech coding algorithms. In IEEE speech coding workshop, pp.\u00a073\u201374, St. Adele, QC, Canada.","key":"9522_CR37"},{"issue":"5","key":"9522_CR38","doi-asserted-by":"publisher","first-page":"1286","DOI":"10.1109\/TASSP.1983.1164178","volume":"31","author":"P Hove Van","year":"1983","unstructured":"Van Hove, P., et al. (1983). Signal reconstruction from signed Fourier transform magnitude. IEEE Transactions on Acoustics, Speech, and Signal Processing, 31(5), 1286\u20131293.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9522_CR39","volume-title":"Methods of predicting user acceptance of voice communication systems. No. D-76-001-U","author":"WD Voiers","year":"1976","unstructured":"Voiers, W. D. (1976). Methods of predicting user acceptance of voice communication systems. No. D-76-001-U. Austin, TX: Dynastat Inc."},{"issue":"4","key":"9522_CR40","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TASSP.1982.1163920","volume":"30","author":"D Wang","year":"1982","unstructured":"Wang, D., & Lim, J. (1982). The unimportance of phase in speech enhancement. IEEE Transactions on Acoustics, Speech, and Signal Processing, 30(4), 679\u2013681.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"11","key":"9522_CR41","doi-asserted-by":"publisher","first-page":"2122","DOI":"10.1109\/TASLP.2016.2598306","volume":"24","author":"J-C Wang","year":"2016","unstructured":"Wang, J.-C., et al. (2016). Compressive sensing-based speech enhancement. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 24(11), 2122\u20132131.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"doi-asserted-by":"crossref","unstructured":"Watanabe, M. K., & Mowlaee, P. (2013). Iterative sinusoidal-based partial phase reconstruction in single-channel source separation. In INTERSPEECH, Portland, USA.","key":"9522_CR42","DOI":"10.21437\/Interspeech.2013-237"},{"unstructured":"Wonho, Y. (1999). Enhanced modified bark spectral distortion (EMBSD): An objective speech quality measure based on audible distortion and cognition model. Thesis (PhD), Temple University, Source DAI-B 60\/07, p.\u00a03479, January 2000, p.\u00a0163.","key":"9522_CR43"},{"issue":"11","key":"9522_CR44","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","volume":"51","author":"H Zen","year":"2009","unstructured":"Zen, H., Tokuda, K. & Black, A. W. (2009). Statistical parametric speech synthesis. Speech Communication, 51(11), 1039\u20131064.","journal-title":"Speech Communication"},{"doi-asserted-by":"crossref","unstructured":"Zhu, X., Gerald, T., Beauregard, & Wyse, L. L. (2006). Real-time iterative spectrum inversion with look-ahead. In IEEE international conference on multimedia and expo, Toronto, ON, Canada.","key":"9522_CR45","DOI":"10.1109\/ICME.2006.262424"},{"issue":"5","key":"9522_CR46","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1109\/TASL.2007.899236","volume":"15","author":"X Zhu","year":"2007","unstructured":"Zhu, X., Gerald, T., Beauregard, & Wyse, L. L. (2007). Real-time signal estimation from modified short-time Fourier transform magnitude spectra. IEEE Transactions on Audio, Speech, and Language Processing, 15(5), 1645\u20131653.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-9522-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9522-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9522-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T03:57:58Z","timestamp":1661399878000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-9522-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,6]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["9522"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-9522-9","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2018,6,6]]},"assertion":[{"value":"28 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}