{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T10:40:09Z","timestamp":1751798409921,"version":"3.41.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030004330"},{"type":"electronic","value":"9783030004347"}],"license":[{"start":{"date-parts":[[2018,8,15]],"date-time":"2018-08-15T00:00:00Z","timestamp":1534291200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-319-98678-4_13","type":"book-chapter","created":{"date-parts":[[2018,8,14]],"date-time":"2018-08-14T13:25:31Z","timestamp":1534253131000},"page":"109-119","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Audio\/Speech Coding Based on the Perceptual Sparse Representation of the Signal with DAE Neural Network Quantizer and Near-End Listening Enhancement"],"prefix":"10.1007","author":[{"given":"Vadzim","family":"Herasimovich","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Petrovsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladislav","family":"Avramov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Petrovsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,15]]},"reference":[{"issue":"12","key":"13_CR1","doi-asserted-by":"publisher","first-page":"3397","DOI":"10.1109\/78.258082","volume":"41","author":"S Mallat","year":"1993","unstructured":"Mallat, S., Zhang, Z.: Matching pursuits with time-frequency dictionaries. IEEE Trans. Sig. Process. 41(12), 3397\u20133415 (1993)","journal-title":"IEEE Trans. Sig. Process."},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Chardon, G., Necciari, T., Balazs, P.: Perceptually matching pursuit with Gabor dictionaries and time-frequency masking. In: ICASSP 2014, Florence, Italy, pp. 3126\u20133130 (2014)","DOI":"10.1109\/ICASSP.2014.6854171"},{"key":"13_CR3","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.1109\/TASL.2008.2004290","volume":"16","author":"E Ravelli","year":"2008","unstructured":"Ravelli, E., Richard, G., Daudet, L.: Union of MDCT bases for audio coding. IEEE Trans. Audio Speech Lang. Process. 16, 1361\u20131372 (2008)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"3","key":"13_CR4","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1109\/TASL.2009.2037396","volume":"18","author":"N Ruiz Reyes","year":"2010","unstructured":"Ruiz Reyes, N., Vera Candeas, P.: Adaptive signal modelling based on sparse approximations for scalable parametric audio coding. IEEE Trans. Audio Speech Lang. Process. 18(3), 447\u2013460 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"13_CR5","unstructured":"Petrovsky, Al., Azarov, E., Petrovsky, A.: Hybrid signal decomposition based on instantaneous harmonic parameters and perceptually motivated wavelet packet for scalable audio coding. Sig. Process. 91, 1489\u20131504 (2011)"},{"key":"13_CR6","unstructured":"Valin, J.-M., Maxwell, G., Terriberry, T., Vos, K.: High-quality, low-delay music coding in the Opus codec. In: AES 135th Convention, paper 8942, New York, USA (2013)"},{"key":"13_CR7","unstructured":"Vos, K., S\u00f8rensen, K. V., Jensen, S. S., Valin, J.-M.: Voice coding with Opus. In: AES 135th Convention, paper 8941, New York, USA (2013)"},{"key":"13_CR8","unstructured":"Sercov, V., Petrovsky, A.: Neural network quantizer of the parameters of the low bitrate vocoder with \u201cspeech\u2009+\u2009noise\u201d speech formation model. In: Proceedings of the 4th International Conference \u201cDigital signal processing and its applications\u201d DSPA-2002, pp. 426\u2013428 (2002). (in Russian)"},{"key":"13_CR9","doi-asserted-by":"publisher","DOI":"10.1002\/0471668850","volume-title":"Speech Coding Algorithms: Foundation and Evolution of Standardized Coders","author":"WC Chu","year":"2003","unstructured":"Chu, W.C.: Speech Coding Algorithms: Foundation and Evolution of Standardized Coders. Wiley, Hoboken (2003)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Sauert, B., Vary, P.: Near end listening enhancement: speech intelligibility improvement in noisy environments. In: ICASSP 2006, Toulouse, France, pp. 493\u2013496 (2006)","DOI":"10.1109\/ICASSP.2006.1660065"},{"key":"13_CR11","unstructured":"Petrovsky, A., Krahe, D., Petrovsky, A.A.: Real-time wavelet packet-based low bit rate audio coding on a dynamic reconfiguration system. In: AES 114th Convention, paper 5778, Amsterdam, The Netherlands (2003)"},{"key":"13_CR12","unstructured":"Petrovsky, Al., Herasimovich, V., Petrovsky, A.: Scalable parametric audio coder using sparse approximation with frame-to-frame perceptually optimized wavelet packet based dictionary. In: AES 138th Convention, paper 9264, Warsaw, Poland (2015)"},{"key":"13_CR13","unstructured":"Mallat, S.A.: Wavelet Tour of Signal Processing. The Sparse Way, 3rd ed. Academic Press, Burlington (2008)"},{"key":"13_CR14","unstructured":"Mumey, B., Gedeon, T.: Optimal mutual information quantization is NP-complete. In: Neural Information Coding Workshop, Snowbird, Utah, USA (2003)"},{"issue":"2","key":"13_CR15","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157\u2013166 (1994)","journal-title":"IEEE Trans. Neural Netw."},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Proceedings of the 19th International Conference on Neural Information Processing Systems (NIPS), pp. 153\u2013160 (2006)","DOI":"10.7551\/mitpress\/7503.003.0024"},{"issue":"5232","key":"13_CR17","doi-asserted-by":"publisher","first-page":"1860","DOI":"10.1126\/science.269.5232.1860","volume":"269","author":"R Hecht-Nielsen","year":"1995","unstructured":"Hecht-Nielsen, R.: Replicator neural networks for universal optimal source coding. Science 269(5232), 1860\u20131863 (1995)","journal-title":"Science"},{"key":"13_CR18","unstructured":"Bengio, Y., Leonard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. In: arXiv preprint arXiv:1308.3432 (2013)"},{"key":"13_CR19","unstructured":"Azarov, E., Vashkevich, M., Herasimovich, V., Petrovsky, A.: General-purpose listening enhancement based on subband non-linear amplification with psychoacoustic criterion. In: AES 138th Convention, paper 9265, Warsaw, Poland (2015)"}],"container-title":["Lecture Notes in Computer Science","Cryptology and Network Security"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-98678-4_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T10:09:09Z","timestamp":1751796549000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-98678-4_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,15]]},"ISBN":["9783030004330","9783030004347"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-98678-4_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018,8,15]]}}}