{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T07:43:23Z","timestamp":1782459803472,"version":"3.54.5"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T00:00:00Z","timestamp":1666310400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T00:00:00Z","timestamp":1666310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s11042-022-14051-z","type":"journal-article","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T03:29:41Z","timestamp":1666322981000},"page":"11443-11460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["A statistical feature extraction for deep speech emotion recognition in a bilingual scenario"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9413-3829","authenticated-orcid":false,"given":"Sara","family":"Sekkate","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Khalil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdellah","family":"Adib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,21]]},"reference":[{"key":"14051_CR1","doi-asserted-by":"crossref","unstructured":"Aggarwal CC (2018) Neural networks and deep learning. Springer, vol 10, pp 978\u2013983","DOI":"10.1007\/978-3-319-94463-0"},{"key":"14051_CR2","doi-asserted-by":"publisher","first-page":"108046","DOI":"10.1016\/j.apacoust.2021.108046","volume":"179","author":"J Ancilin","year":"2021","unstructured":"Ancilin J, Milton A (2021) Improved speech emotion recognition with mel frequency magnitude coefficient. Appl Acoustics 179:108046","journal-title":"Appl Acoustics"},{"key":"14051_CR3","doi-asserted-by":"crossref","unstructured":"Badshah AM, Ahmad J, Rahim N, Baik SW (2017) Speech emotion recognition from spectrograms with deep convolutional neural network. In: 2017 International conference on platform technology and service (PlatCon), pp 1\u20135","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"14051_CR4","doi-asserted-by":"crossref","unstructured":"Bensalah N, Ayad H, Adib A, Farouk AIE (2020) Lstm vs. gru for arabic machine translation. In: SoCPaR, pp 156\u2013165","DOI":"10.1007\/978-3-030-73689-7_16"},{"key":"14051_CR5","doi-asserted-by":"publisher","first-page":"104886","DOI":"10.1016\/j.knosys.2019.104886","volume":"184","author":"A Bhavan","year":"2019","unstructured":"Bhavan A, Chauhan P, Hitkul, Shah RR (2019) Bagged support vector machines for emotion recognition from speech. Knowl-Based Syst 184:104886","journal-title":"Knowl-Based Syst"},{"key":"14051_CR6","doi-asserted-by":"crossref","unstructured":"Bouny LE, Khalil M, Adib A (2020) ECG heartbeat classification based on multi-scale wavelet convolutional neural networks. In: 2020 IEEE international conference on acoustics, speech and signal processing, ICASSP. Barcelona, Spain, 4-8 May 2020. IEEE, pp 3212\u20133216","DOI":"10.1109\/ICASSP40776.2020.9054749"},{"key":"14051_CR7","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.neucom.2020.07.056","volume":"417","author":"LE Bouny","year":"2020","unstructured":"Bouny LE, Khalil M, Adib A (2020) An end-to-end multi-level wavelet convolutional neural networks for heart diseases diagnosis. Neurocomputing 417:187\u2013201","journal-title":"Neurocomputing"},{"key":"14051_CR8","doi-asserted-by":"crossref","unstructured":"Braga D, Madureira A, Coelho L, Ajith R (2019) Automatic detection of parkinson\u2019s disease based on acoustic analysis of speech. In: Engineering applications of artificial intelligence, vol 77, pp 148\u2013158","DOI":"10.1016\/j.engappai.2018.09.018"},{"key":"14051_CR9","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1109\/LSP.2018.2860246","volume":"25","author":"M Chen","year":"2018","unstructured":"Chen M, He X, Yang J, Zhang H (2018) 3-d Convolutional recurrent neural networks with attention model for speech emotion recognition. IEEE Signal Process Lett 25:1440\u20131444","journal-title":"IEEE Signal Process Lett"},{"key":"14051_CR10","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s10772-020-09713-y","volume":"23","author":"A Christy","year":"2020","unstructured":"Christy A, Vaithyasubramanian S, Jesudoss A et al (2020) Multimodal speech emotion recognition and classification using convolutional neural network techniques. Int J Speech Technol 23:381\u2013388","journal-title":"Int J Speech Technol"},{"key":"14051_CR11","unstructured":"Costantini G, Iaderola I, Paoloni A, Massimiliano T (2014) EMOVO Corpus: an Italian emotional speech database. In: Proceedings of the ninth international conference on language resources and evaluation (LREC\u201914), pp 3501\u20133504, Reykjavik, Iceland. European language resources association (ELRA)"},{"key":"14051_CR12","doi-asserted-by":"crossref","unstructured":"Davis S, Mermelstein P (1980) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. In: IEEE transactions on acoustics, speech, and signal processing, vol 28, pp 357\u2013366","DOI":"10.1109\/TASSP.1980.1163420"},{"issue":"3","key":"14051_CR13","first-page":"550","volume":"99","author":"P Ekman","year":"1992","unstructured":"Ekman P (1992) Are there basic emotions?. Am Psychol Assoc 99 (3):550","journal-title":"Am Psychol Assoc"},{"key":"14051_CR14","doi-asserted-by":"crossref","unstructured":"Elangovan P, Nath MK (2021) A novel shallow convnet-18 for malaria parasite detection in thin blood smear images. In: SN computer science, vol 2, pp 1\u201311","DOI":"10.1007\/s42979-021-00763-w"},{"key":"14051_CR15","doi-asserted-by":"crossref","unstructured":"Han K, Yu D, Tashev I (2014) Speech emotion recognition using deep neural network and extreme learning machine. In: Interspeech 2014","DOI":"10.21437\/Interspeech.2014-57"},{"key":"14051_CR16","doi-asserted-by":"crossref","unstructured":"Heracleous P, Yoneyama A (2019) A comprehensive study on bilingual and multilingual speech emotion recognition using a two-pass classification scheme. PLoS One, vol 8","DOI":"10.1371\/journal.pone.0220386"},{"key":"14051_CR17","doi-asserted-by":"crossref","unstructured":"Hifny Y, networks AA (2019) Efficient arabic emotion recognition using deep neural. In: IEEE international conference on acoustics speech and signal processing (ICASSP), pp 6710\u20136714","DOI":"10.1109\/ICASSP.2019.8683632"},{"key":"14051_CR18","doi-asserted-by":"crossref","unstructured":"Huang Z, Dong M, Mao Q, Zhan Y (2014) Speech emotion recognition using cnn. In: Proceedings of the 22nd ACM international conference on multimedia, MM \u201914. New York, NY USA, pp 801\u2013804. Association for computing machinery","DOI":"10.1145\/2647868.2654984"},{"key":"14051_CR19","doi-asserted-by":"crossref","unstructured":"Huang Y, Tian K, Wu A, Zhang G (2017) Feature fusion methods research based on deep belief networks for speech emotion recognition under noise condition. In: Journal of ambient intelligence and humanized computing","DOI":"10.1007\/s12652-017-0644-8"},{"key":"14051_CR20","doi-asserted-by":"publisher","first-page":"101894","DOI":"10.1016\/j.bspc.2020.101894","volume":"59","author":"D Issa","year":"2020","unstructured":"Issa D, Demirci MF, Yazici A (2020) Speech emotion recognition with deep convolutional neural networks. Biomed Signal Process Contr 59:101894","journal-title":"Biomed Signal Process Contr"},{"key":"14051_CR21","doi-asserted-by":"crossref","unstructured":"John Kim, Saurous RA (2018) Emotion recognition from human speech using temporal information and deep learning. In: Proceeding interspeech, vol 2018, pp 937\u2013940","DOI":"10.21437\/Interspeech.2018-1132"},{"key":"14051_CR22","doi-asserted-by":"crossref","unstructured":"Kar MK, Nath MK, Neog DR (2021) A review on progress in semantic image segmentation and its application to medical images. In: SN computer science, vol 2","DOI":"10.1007\/s42979-021-00784-5"},{"key":"14051_CR23","doi-asserted-by":"crossref","unstructured":"Kerkeni L, Serrestou Y, Raoof K, Mbarki M, Mahjoub MA, Cleder C (2019) Automatic speech emotion recognition using an optimal combination of features based on emd-tkeo. In: Speech communication","DOI":"10.5772\/intechopen.84856"},{"key":"14051_CR24","doi-asserted-by":"crossref","unstructured":"Khan S, Rahmani H, Ali Shah SA, Bennamoun M, Medioni G, Dickinson S (2018) A guide to convolutional neural networks for computer vision. Springer, ISBN: 9783031006937","DOI":"10.1007\/978-3-031-01821-3"},{"key":"14051_CR25","doi-asserted-by":"crossref","unstructured":"Kim J (2007) Bimodal emotion recognition using speech and physiological changes. In: Robust speech recognition and understanding. I-tech education and publishing vienna, vol 265, p 280","DOI":"10.5772\/4754"},{"key":"14051_CR26","doi-asserted-by":"crossref","unstructured":"Kim J, Andr\u00e9 E (2008) Emotion recognition based on physiological changes in music listening. In: IEEE transactions on pattern analysis and machine intelligence. IEEE, vol 30, pp 2067\u20132083","DOI":"10.1109\/TPAMI.2008.26"},{"key":"14051_CR27","doi-asserted-by":"crossref","unstructured":"Kim Y, Yun TS (2021) How to classify sand types: a deep learning approach. In: Engineering geology, vol 288, p 106142","DOI":"10.1016\/j.enggeo.2021.106142"},{"key":"14051_CR28","doi-asserted-by":"crossref","unstructured":"Kinnunen T, Li H (2010) An overview of text-independent speaker recognition: from features to supervectors. In: Speech communication. Elsevier, vol 52, pp 12\u201340","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"14051_CR29","doi-asserted-by":"crossref","unstructured":"Lakomkin E, Zamani MA, Weber C, Magg S, Wermter S (2018) On the robustness of speech emotion recognition for human-robot interaction with deep neural networks. In: 2018 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp 854\u2013860","DOI":"10.1109\/IROS.2018.8593571"},{"key":"14051_CR30","doi-asserted-by":"publisher","first-page":"107519","DOI":"10.1016\/j.apacoust.2020.107519","volume":"170","author":"S Lalitha","year":"2020","unstructured":"Lalitha S, Gupta D, Zakariah M, Alotaibi YA (2020) Investigation of multilingual and mixed-lingual emotion recognition using enhanced cues with data augmentation. Appl Acoustics 170:107519","journal-title":"Appl Acoustics"},{"key":"14051_CR31","doi-asserted-by":"crossref","unstructured":"Lang PJ (1995) The emotion probe: studies of motivation and attention. In: American psychologist, vol 50, p 372. American psychological association","DOI":"10.1037\/0003-066X.50.5.372"},{"key":"14051_CR32","doi-asserted-by":"crossref","unstructured":"Lella KK, Alphonse PJA (2021) Automatic covid-19 disease diagnosis using 1d convolutional neural network and augmentation with human respiratory sound based on parameters: cough, breath, and voice. In: AIMS public health, vol 8","DOI":"10.3934\/publichealth.2021019"},{"key":"14051_CR33","doi-asserted-by":"crossref","unstructured":"Livingstone SR, Russo FA (2018) The ryerson audio-visual database of emotionalspeech and song (ravdess): a dynamic, multimodal set of facial and vocal expressions in north american english. Plos One, vol 13","DOI":"10.1371\/journal.pone.0196391"},{"key":"14051_CR34","doi-asserted-by":"crossref","unstructured":"Lopez-Moreno I, Gonzalez-Dominguez J, Plchot O, Martinez D, Gonzalez-Rodriguez J, Moreno P (2014) Automatic language identification using deep neural networks. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 5337\u20135341","DOI":"10.1109\/ICASSP.2014.6854622"},{"key":"14051_CR35","doi-asserted-by":"crossref","unstructured":"Mansouri-Benssassi E, Ye J (2019) Speech emotion recognition with early visual cross-modal enhancement using spiking neural networks. In: 2019 International joint conference on neural networks (IJCNN), pp 1\u20138","DOI":"10.1109\/IJCNN.2019.8852473"},{"key":"14051_CR36","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"16","author":"Q Mao","year":"2014","unstructured":"Mao Q, Dong M, Huang Z, Zhan Y (2014) Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Trans Multimed 16:2203\u20132213","journal-title":"IEEE Trans Multimed"},{"key":"14051_CR37","doi-asserted-by":"crossref","unstructured":"McFee B, Raffel C, Liang D, Ellis DPW, McVicar M, Battenberg E, Nieto O (2015) Librosa: audio and music signal analysis in python. In: Proceedings of the 14th python in science conference, pp. 18\u201325.","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"14051_CR38","unstructured":"Meftah A, Alotaibi YA, Selouani S-A (2014) Designing, building, and analyzing an arabic speech emotional corpus. In: Phase 2. in 5th international conference on arabic language processing, pp 181\u2013184"},{"key":"14051_CR39","doi-asserted-by":"crossref","unstructured":"Mustaqeem, Kwon S (2020) A cnn-assisted enhanced audio signal processing for speech emotion recognition. In: Sensors, vol 20","DOI":"10.3390\/s20010183"},{"key":"14051_CR40","doi-asserted-by":"publisher","first-page":"102763","DOI":"10.1016\/j.dsp.2020.102763","volume":"104","author":"S Nagarajan","year":"2020","unstructured":"Nagarajan S, Srinivas Nettimi SS, Kumar LS, Nath MK, Kanhe A (2020) Speech emotion recognition using cepstral features extracted with novel triangular filter banks based on bark and erb frequency scales. Digital Signal Process 104:102763","journal-title":"Digital Signal Process"},{"key":"14051_CR41","doi-asserted-by":"crossref","unstructured":"Neumann M, Thang Vu NG (2018) Cross-lingual and multilingual speech emotion recognition on english and french. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 5769\u20135773","DOI":"10.1109\/ICASSP.2018.8462162"},{"key":"14051_CR42","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1037\/0033-295X.97.3.315","volume":"97","author":"A Ortony","year":"1990","unstructured":"Ortony A, Turner TJ (1990) What\u2019s basic about basic emotions? Psychological Rev 97:315\u2013331","journal-title":"Psychological Rev"},{"key":"14051_CR43","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.apacoust.2018.11.028","volume":"146","author":"T \u00d6zseven","year":"2019","unstructured":"\u00d6zseven T (2019) A novel feature selection method for speech emotion recognition. Appl Acoustics 146:320\u2013326","journal-title":"Appl Acoustics"},{"key":"14051_CR44","doi-asserted-by":"crossref","unstructured":"Palo HK, Mohanty MN (2018) Wavelet based feature combination for recognition of emotions. In: Ain shams engineering journal, vol 9, pp 1799\u20131806","DOI":"10.1016\/j.asej.2016.11.001"},{"key":"14051_CR45","doi-asserted-by":"crossref","unstructured":"Pandey SK, Shekhawat HS, Prasanna SRM (2019) Emotion recognition from raw speech using wavenet. In: TENCON 2019 - 2019 IEEE region 10 conference (TENCON), pp 1292\u20131297","DOI":"10.1109\/TENCON.2019.8929257"},{"key":"14051_CR46","doi-asserted-by":"crossref","unstructured":"Picone JW (1993) Signal modeling techniques in speech recognition. In: Proceedings of the IEEE, vol 81, pp 1215\u20131247","DOI":"10.1109\/5.237532"},{"key":"14051_CR47","doi-asserted-by":"crossref","unstructured":"Polzehl T, Schmitt A, Metze F (2010) Approaching multi-lingual emotion recognition from speech-on language dependency of acoustic prosodic features for anger detection. In: Proceedings of speech prosody","DOI":"10.21437\/SpeechProsody.2010-123"},{"key":"14051_CR48","doi-asserted-by":"crossref","unstructured":"Popova AS, Rassadin AG, Ponomarenko AA (2018) Emotion recognition in sound. In: Kryzhanovsky B, Dunin-Barkowski W, Redko V (eds) Advances in neural computation, machine learning, and cognitive research, pp 117\u2013124, Cham. Springer international publishing","DOI":"10.1007\/978-3-319-66604-4_18"},{"key":"14051_CR49","doi-asserted-by":"crossref","unstructured":"Riyad M, Khalil M, Adib A (2020) Incep-eegnet: a convnet for motor imagery decoding. In: Moataz AE, Mammass D, Mansouri A, Nouboud F (eds) Image and signal processing - 9th international conference, ICISP 2020, Marrakesh, Morocco, 4-6 June 2020, proceedings, vol 12119 of lecture notes in computer science. Springer, pp 103\u2013111","DOI":"10.1007\/978-3-030-51935-3_11"},{"key":"14051_CR50","doi-asserted-by":"crossref","unstructured":"Russell J (1980) A circumplex model of affect. In: Journal of personality and social psychology, vol 39, pp 1161\u20131178, 12","DOI":"10.1037\/h0077714"},{"key":"14051_CR51","doi-asserted-by":"crossref","unstructured":"Schuller B, Arsic D, Wallhoff F, Rigoll G (2006) Emotion recognition in the noise applying large acoustic feature sets. In: Speech Prosody","DOI":"10.21437\/SpeechProsody.2006-150"},{"key":"14051_CR52","unstructured":"Schuller B, Zhangm Z, Weninger F, Rigoll G (2011) Selecting training data for cross-corpus speech emotion recognition: prototypicality vs. generalization"},{"key":"14051_CR53","doi-asserted-by":"crossref","unstructured":"Sefara TJ (2019) The effects of normalisation methods on speech emotion recognition. In: 2019 International multidisciplinary information technology and engineering conference (IMITEC), pp 1\u20138","DOI":"10.1109\/IMITEC45504.2019.9015895"},{"key":"14051_CR54","doi-asserted-by":"crossref","unstructured":"Sekkate S, Khalil M, Adib A (2019) Speaker identification for ofdm-based aeronautical communication system. In: Circuits, systems, and signal processing. Springer US, vol 38, pp 3743\u20133761","DOI":"10.1007\/s00034-019-01026-z"},{"key":"14051_CR55","doi-asserted-by":"crossref","unstructured":"Sekkate S, Khalil M, Adib (2020) A statistical based modeling approach for deep learning based speech emotion recognition. In: International conference on intelligent systems design and applications (ISDA)","DOI":"10.1007\/978-3-030-71187-0_114"},{"key":"14051_CR56","doi-asserted-by":"crossref","unstructured":"Sekkate S, Khalil M, Adib A, Jebara SB (2019) A multiresolution-based fusion strategy for improving speech emotion recognition efficiency. In: Mobile, secure, and programmable networking, pp 96\u2013109, Cham. Springer international publishing","DOI":"10.1007\/978-3-030-22885-9_10"},{"key":"14051_CR57","doi-asserted-by":"crossref","unstructured":"Sekkate S, Khalil M, Adib A, Jebara SB (2019) An investigation of a feature-level fusion for noisy speech emotion recognition. In: Computers, vol 8","DOI":"10.3390\/computers8040091"},{"key":"14051_CR58","doi-asserted-by":"crossref","unstructured":"Settle S, Roux JL, Hori T, Watanabe S, Hershey JR (2018) End-to-end multi-speaker speech recognition. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 4819\u20134823","DOI":"10.1109\/ICASSP.2018.8461893"},{"key":"14051_CR59","doi-asserted-by":"publisher","first-page":"190784","DOI":"10.1109\/ACCESS.2020.3031763","volume":"8","author":"Y\u00dc S\u00f6nmez","year":"2020","unstructured":"S\u00f6nmez Y\u00dc, Varol A (2020) A speech emotion recognition model based on multi-level local binary and local ternary patterns. IEEE Access 8:190784\u2013190796","journal-title":"IEEE Access"},{"key":"14051_CR60","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Dropout RS (2014) A simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"14051_CR61","doi-asserted-by":"crossref","unstructured":"Sugan N, Srinivas NSS, Kar N, Kumar LS, Nath MK, Kanhe A (2018) Performance comparison of different cepstral features for speech emotion recognition. In: 2018 International CET conference on control, communication, and computing (IC4), pp 266\u2013271","DOI":"10.1109\/CETIC4.2018.8531065"},{"key":"14051_CR62","doi-asserted-by":"crossref","unstructured":"Sugan N, Srinivas NSS, Kar N, Kumar LS, Nath MK, Kanhe A (2019) Recognition of spoken languages from acoustic speech signals using fourier parameters. In: Circuits, systems, and signal processing, vol 38, pp 5018\u20135067","DOI":"10.1007\/s00034-019-01100-6"},{"key":"14051_CR63","doi-asserted-by":"crossref","unstructured":"Thoits PA (1989) The sociology of emotions. In: Annual review of sociology. Annual reviews 4139 el camino way, PO Box 10139, Palo Alto, CA 94303-0139, USA, vol 15, pp 317\u2013342","DOI":"10.1146\/annurev.so.15.080189.001533"},{"key":"14051_CR64","doi-asserted-by":"crossref","unstructured":"Trigeorgis G, Ringeval F, Brueckner R, Marchi E, Nicolaou MA, Schuller B, Zafeiriou S (2016) Adieu features? end-to-end speech emotion recognition using a deep convolutional recurrent network. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 5200\u20135204","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"14051_CR65","doi-asserted-by":"crossref","unstructured":"Yang B, Lugger M (2010) Emotion recognition from speech signals using new harmony features. In: Signal processing, vol 90, pp 1415\u20131423. Special Section on Statistical Signal & Array Processing","DOI":"10.1016\/j.sigpro.2009.09.009"},{"key":"14051_CR66","doi-asserted-by":"crossref","unstructured":"Yenigalla P, Kumar A, Tripathi S, Singh C, Kar S, Vepa J (2018) Speech emotion recognition using spectrogram & phoneme embedding. In: INTERSPEECH","DOI":"10.21437\/Interspeech.2018-1811"},{"key":"14051_CR67","doi-asserted-by":"crossref","unstructured":"Zeng Y, Mao H, Peng D, Yi Z (2019) Spectrogram based multi-task audio classification. In: Multimedia tools appl, vol 78, pp 3705\u20133722, USA. Kluwer academic publishers","DOI":"10.1007\/s11042-017-5539-3"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14051-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-14051-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14051-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T08:12:09Z","timestamp":1728202329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-14051-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,21]]},"references-count":67,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["14051"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-14051-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,21]]},"assertion":[{"value":"5 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest, or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}