{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T13:54:22Z","timestamp":1762005262545,"version":"3.37.3"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T00:00:00Z","timestamp":1599436800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T00:00:00Z","timestamp":1599436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61862041","61363078"],"award-info":[{"award-number":["61862041","61363078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11042-020-09748-y","type":"journal-article","created":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T17:02:55Z","timestamp":1599498175000},"page":"1201-1221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["A retrieval algorithm for encrypted speech based on convolutional neural network and deep hashing"],"prefix":"10.1007","volume":"80","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1488-388X","authenticated-orcid":false,"given":"Qiu-yu","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Yu-zhou","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ying-jie","family":"Hu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,7]]},"reference":[{"key":"9748_CR1","doi-asserted-by":"crossref","unstructured":"Alamodi AOA, Sun K, Ai W, Chen C, Peng D (2019) Design new chaotic maps based on dimension expansion. Chinese physics B 28(2): 020503. CNKI:SUN:ZGWL.0.2019-02-016","DOI":"10.1088\/1674-1056\/28\/2\/020503"},{"key":"9748_CR2","doi-asserted-by":"publisher","unstructured":"Cummins N, Amiriparian S, Hagerer G, Batliner A, Steidl S, Schuller BW (2017) An image-based deep spectrum feature representation for the recognition of emotional speech. In International Conference on Multimedia, 25th ACM international conference on. ACM, 2017: 478\u2013484. https:\/\/doi.org\/10.1145\/3123266.3123371","DOI":"10.1145\/3123266.3123371"},{"issue":"3","key":"9748_CR3","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1109\/TLA.2018.8358674","volume":"16","author":"LMQ De Santana","year":"2018","unstructured":"De Santana LMQ, Santos RM, Matos LN, Macedo HT (2018) Deep neural networks for acoustic modeling in the presence of noise. IEEE Lat Am Trans 16(3):918\u2013925. https:\/\/doi.org\/10.1109\/TLA.2018.8358674","journal-title":"IEEE Lat Am Trans"},{"key":"9748_CR4","doi-asserted-by":"publisher","unstructured":"Dhiraj BR, Ghattamaraju N (2018) An effective analysis of deep learning based approaches for audio based feature extraction and its visualization. Multimedia Tools and Applications 1\u201324. https:\/\/doi.org\/10.1007\/s11042-018-6706-x","DOI":"10.1007\/s11042-018-6706-x"},{"key":"9748_CR5","doi-asserted-by":"publisher","unstructured":"Elizalde B, Zarar S, Raj B (2019) Cross modal audio search and retrieval with joint embeddings based on text and audio. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019-2019 IEEE International Conference on. IEEE 4095\u20134099. https:\/\/doi.org\/10.1109\/ICASSP.2019.8682632","DOI":"10.1109\/ICASSP.2019.8682632"},{"issue":"7","key":"9748_CR6","doi-asserted-by":"publisher","first-page":"9203","DOI":"10.1007\/s11042-017-5301-x","volume":"77","author":"BB Gupta","year":"2018","unstructured":"Gupta BB, Yamaguchi S, Agrawal DP (2018) Advances in security and privacy of multimedia big data in mobile and cloud computing. Multimed Tools Appl 77(7):9203\u20139208. https:\/\/doi.org\/10.1007\/s11042-017-5301-x","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"9748_CR7","doi-asserted-by":"publisher","first-page":"703","DOI":"10.2298\/CSIS170112024H","volume":"14","author":"SF He","year":"2017","unstructured":"He SF, Zhao H (2017) A retrieval algorithm of encrypted speech based on syllable-level perceptual hashing. Comput Sci Inf Syst 14(3):703\u2013718. https:\/\/doi.org\/10.2298\/CSIS170112024H","journal-title":"Comput Sci Inf Syst"},{"key":"9748_CR8","doi-asserted-by":"publisher","unstructured":"Hertel L, Barth E, K\u00e4ster T, Martinetz T (2015) Deep convolutional neural networks as generic feature extractors. In International Joint Conference on Neural Networks (IJCNN), 2015 International Joint Conference on. IEEE 1\u20134. https:\/\/doi.org\/10.1109\/IJCNN.2015.7280683","DOI":"10.1109\/IJCNN.2015.7280683"},{"key":"9748_CR9","doi-asserted-by":"publisher","unstructured":"Hertel L, Phan H, Mertins A (2016) Comparing time and frequency domain for audio event recognition using deep learning. In International Joint Conference on Neural Networks (IJCNN), 2016 International Joint Conference on. IEEE 3407\u20133411. https:\/\/doi.org\/10.1109\/IJCNN.2016.7727635","DOI":"10.1109\/IJCNN.2016.7727635"},{"key":"9748_CR10","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning, the 32nd International Conference on International Conference on Machine Learning. 37(448-456)"},{"key":"9748_CR11","doi-asserted-by":"publisher","unstructured":"Juvela L, Bollepalli B, Wang X, Kameoka H, Airaksinen M, Yamagishi J, Alku P (2018) Speech waveform synthesis from MFCC sequences with generative adversarial networks. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018 IEEE International Conference on. IEEE 5679-5683. https:\/\/doi.org\/10.1109\/ICASSP.2018.8461852","DOI":"10.1109\/ICASSP.2018.8461852"},{"key":"9748_CR12","unstructured":"Keras: The Python Deep Learning library. https:\/\/github.com\/keras-team\/keras\/tree\/master\/docs. Accessed 14 Oct 2019"},{"key":"9748_CR13","doi-asserted-by":"publisher","unstructured":"Li Y, Xu Y, Miao Z, Li H, Wang J, Zhang Y (2016) Deep feature hash codes framework for content-based image retrieval. In 2016 8th international conference on Wireless Communications & Signal Processing (WCSP). IEEE 1\u20136. https:\/\/doi.org\/10.1109\/WCSP.2016.7752525","DOI":"10.1109\/WCSP.2016.7752525"},{"key":"9748_CR14","doi-asserted-by":"publisher","unstructured":"Lin K, Yang HF, Hsiao JH, Chen CH (2015) Deep learning of binary hash codes for fast image retrieval. In Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), the IEEE Conference on. IEEE 27\u201335. https:\/\/doi.org\/10.1109\/CVPRW.2015.7301269","DOI":"10.1109\/CVPRW.2015.7301269"},{"key":"9748_CR15","doi-asserted-by":"publisher","unstructured":"Liu H, Wang R, Shan S, Chen X (2016) Deep supervised hashing for fast image retrieval. In conference on computer vision and pattern recognition, the IEEE conference on. IEEE 2064\u20132072. https:\/\/doi.org\/10.1109\/CVPR.2016.227","DOI":"10.1109\/CVPR.2016.227"},{"key":"9748_CR16","doi-asserted-by":"publisher","unstructured":"McFee B, Raffel C, Liang D, Ellis DP, McVicar M, Battenberg E, Nieto O (2015) Librosa: audio and music signal analysis in python. In Proceedings of the 14th python in science conference (SCIPY 2015). 8: 18-24. https:\/\/doi.org\/10.25080\/Majora-7b98e3ed-003","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"9748_CR17","doi-asserted-by":"publisher","unstructured":"Nayyar RK, Nair S, Patil O, Pawar R, Lolage A (2017) Content-based auto-tagging of audios using deep learning. In International Conference on Big Data, IoT and Data Science, 2017 International Conference on. IEEE 30\u201336. https:\/\/doi.org\/10.1109\/BID.2017.8336569","DOI":"10.1109\/BID.2017.8336569"},{"key":"9748_CR18","doi-asserted-by":"publisher","unstructured":"Pons J, Serra X (2019) Randomly weighted CNNs for (music) audio classification. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019-2019 IEEE International Conference on. IEEE 336\u2013340. https:\/\/doi.org\/10.1109\/ICASSP.2019.8682912","DOI":"10.1109\/ICASSP.2019.8682912"},{"issue":"3","key":"9748_CR19","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"Salamon J, Bello JP (2017) Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process Lett 24(3):279\u2013283. https:\/\/doi.org\/10.1109\/LSP.2017.2657381","journal-title":"IEEE Signal Process Lett"},{"key":"9748_CR20","doi-asserted-by":"publisher","unstructured":"Shen F, Shen C, Liu W, Tao SH (2015) Supervised discrete hashing. In proceedings of the IEEE conference on computer vision and pattern recognition. IEEE 37\u201345. https:\/\/doi.org\/10.1109\/CVPR.2015.7298598","DOI":"10.1109\/CVPR.2015.7298598"},{"key":"9748_CR21","doi-asserted-by":"publisher","unstructured":"Spring R, Shrivastava A (2017) Scalable and sustainable deep learning via randomized hashing. In International Conference on Knowledge Discovery and Data Mining, 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM 445\u2013454. https:\/\/doi.org\/10.1145\/3097983.3098035","DOI":"10.1145\/3097983.3098035"},{"issue":"7","key":"9748_CR22","doi-asserted-by":"publisher","first-page":"2399","DOI":"10.3390\/s18072399","volume":"18","author":"C Sun","year":"2018","unstructured":"Sun C, Yang Y, Wen C, Xie K, Wen F (2018) Voiceprint identification for limited dataset using the deep migration hybrid model based on transfer learning. Sensors 18(7):2399. https:\/\/doi.org\/10.3390\/s18072399","journal-title":"Sensors"},{"key":"9748_CR23","doi-asserted-by":"publisher","unstructured":"Thangavel M, Varalakshmi P, Renganayaki S, Subhapriya GR, Preethi T, Banu AZ (2016) SMCSRC\u2014secure multimedia content storage and retrieval in cloud. In 2016 international conference on recent trends in information technology (ICRTIT). IEEE 1\u20136. https:\/\/doi.org\/10.1109\/ICRTIT.2016.7569581","DOI":"10.1109\/ICRTIT.2016.7569581"},{"key":"9748_CR24","doi-asserted-by":"publisher","unstructured":"Valenti M, Squartini S, Diment A, Parascandolo G, Virtanen T (2017) A convolutional neural network approach for acoustic scene classification. In International Joint Conference on Neural Networks (IJCNN), 2017 International Joint Conference on. IEEE 1547\u20131554. https:\/\/doi.org\/10.1109\/IJCNN.2017.7966035","DOI":"10.1109\/IJCNN.2017.7966035"},{"key":"9748_CR25","unstructured":"Wang HX, Hao GY (2015) Encryption speech perceptual hashing algorithm and retrieval scheme based on time and frequency domain change characteristics. China patent, CN104835499A, 2015-08-12"},{"key":"9748_CR26","unstructured":"Wang D, Zhang XW (2015) Thchs-30: a free Chinese speech corpus. arXiv preprint arXiv:1512.01882"},{"key":"9748_CR27","doi-asserted-by":"publisher","unstructured":"Wang H, Zhou L, Zhang W, Liu S (2013) Watermarking-based perceptual hashing search over encrypted speech. In International Workshop on Digital Watermarking. Springer Berlin Heidelberg 423\u2013434. https:\/\/doi.org\/10.1007\/978-3-662-43886-2_3","DOI":"10.1007\/978-3-662-43886-2_3"},{"key":"9748_CR28","doi-asserted-by":"publisher","unstructured":"Wu Y, Lee T (2018) Reducing model complexity for DNN based large-scale audio classification. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018 IEEE International Conference on. IEEE 331\u2013335. https:\/\/doi.org\/10.1109\/ICASSP.2018.8462168","DOI":"10.1109\/ICASSP.2018.8462168"},{"issue":"2","key":"9748_CR29","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1587\/transinf.2017EDL8162","volume":"101","author":"JF Wu","year":"2018","unstructured":"Wu JF, Qin HB, Hua YZ, Fan LY (2018) Pitch estimation and voicing classification using reconstructed spectrum from MFCC. IEICE Trans Inf Syst 101(2):556\u2013559. https:\/\/doi.org\/10.1587\/transinf.2017EDL8162","journal-title":"IEICE Trans Inf Syst"},{"key":"9748_CR30","doi-asserted-by":"publisher","unstructured":"Xu Y, Kong Q, Wang W, Plumbley MD (2018) Large-scale weakly supervised audio classification using gated convolutional neural network. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018 IEEE International Conference on. IEEE, 121\u2013125. https:\/\/doi.org\/10.1109\/ICASSP.2018.8461975","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"9748_CR31","doi-asserted-by":"publisher","unstructured":"Zhang Q, Zhou L, Zhang T, Zhang D (2019) A retrieval algorithm of encrypted speech based on short-term cross-correlation and perceptual hashing, Multimedia Tools and Applications 1\u201322. https:\/\/doi.org\/10.1007\/s11042-019-7180-9","DOI":"10.1007\/s11042-019-7180-9"},{"key":"9748_CR32","doi-asserted-by":"publisher","unstructured":"Zhao H, He SF (2016) A retrieval algorithm for encrypted speech based on perceptual hashing. In 2016 12th international conference on natural computation, fuzzy systems and knowledge discovery (ICNC-FSKD). IEEE 1840\u20131845. https:\/\/doi.org\/10.1109\/FSKD.2016.7603458","DOI":"10.1109\/FSKD.2016.7603458"},{"key":"9748_CR33","doi-asserted-by":"publisher","unstructured":"Zhao S, Zhang Y, Xu H, Han T (2019) Ensemble classification based on feature selection for environmental sound recognition. Mathematical Problems in Engineering 1\u20137. https:\/\/doi.org\/10.1155\/2019\/4318463","DOI":"10.1155\/2019\/4318463"},{"key":"9748_CR34","unstructured":"Zheng W, Mo Z, Xing X, Zhao G (2018) CNNs-based acoustic scene classification using multi-spectrogram fusion and label expansions. arXiv preprint arXiv:1809.01543 1-7."},{"key":"9748_CR35","doi-asserted-by":"crossref","unstructured":"Zhu H, Long M, Wang J, Cao Y (2016) Deep hashing network for efficient similarity retrieval. In proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16). AAAI 2415-2421.","DOI":"10.1609\/aaai.v30i1.10235"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09748-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-09748-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09748-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T03:49:10Z","timestamp":1668656950000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-09748-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,7]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["9748"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09748-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2020,9,7]]},"assertion":[{"value":"8 July 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}