{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T19:23:12Z","timestamp":1770492192553,"version":"3.49.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1016\/j.asoc.2020.106775","type":"journal-article","created":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T01:04:37Z","timestamp":1602205477000},"page":"106775","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":13,"special_numbering":"PA","title":["Simplified inverse filter tracked affective acoustic signals classification incorporating deep convolutional neural networks"],"prefix":"10.1016","volume":"97","author":[{"given":"Yuxiang","family":"Kuang","sequence":"first","affiliation":[]},{"given":"Qun","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Nilanjan","family":"Dey","sequence":"additional","affiliation":[]},{"given":"Fuqian","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Rub\u00e9n Gonz\u00e1lez","family":"Crespo","sequence":"additional","affiliation":[]},{"given":"R. Simon","family":"Sherratt","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2020.106775_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2019.101646","article-title":"A machine learning model for affective recognition from physiological signals","volume":"55","author":"Dom\u00ednguez-Jim\u00e9nez","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.asoc.2020.106775_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2019.102423","article-title":"A survey of affective recognition methods with emphasis on E-learning environments","volume":"147","author":"Imani","year":"2019","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.asoc.2020.106775_b3","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1016\/j.neucom.2017.09.049","article-title":"Karpov efficient and effective strategies for cross-corpus acoustic emotion recognition","volume":"275","author":"Kaya","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2020.106775_b4","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1016\/j.neucom.2017.09.049","article-title":"Efficient and effective strategies for cross-corpus acoustic affective recognition","volume":"275","author":"Kaya","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2020.106775_b5","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1016\/j.procs.2015.09.177","article-title":"A wavelet packet and mel-frequency cepstral coefficients-based feature extraction method for speaker identification","volume":"61","author":"Turner","year":"2015","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.asoc.2020.106775_b6","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/j.neucom.2020.02.085","article-title":"Wavelet packet analysis for speaker-independent affective recognition","volume":"398","author":"Wang","year":"2020","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.asoc.2020.106775_b7","doi-asserted-by":"crossref","first-page":"98","DOI":"10.4018\/IJACI.2017010105","article-title":"Design and implementation of a robust acoustic recognition system for waterbird species using TMS320C6713 DSK","volume":"8","author":"Boulmaiz","year":"2017","journal-title":"Int. J. Ambient Comput. Intell."},{"issue":"2","key":"10.1016\/j.asoc.2020.106775_b8","doi-asserted-by":"crossref","first-page":"2157","DOI":"10.1016\/j.eswa.2011.07.065","article-title":"Classification of speech dysfluencies with MFCC and LPCC features","volume":"39","author":"Chia","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.asoc.2020.106775_b9","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.specom.2019.12.001","article-title":"Speech affective recognition: emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers","volume":"116","author":"Ak\u00e7ay","year":"2020","journal-title":"Speech Commun."},{"key":"10.1016\/j.asoc.2020.106775_b10","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.ins.2019.06.065","article-title":"DuG: Dual speaker-based acoustic gesture recognition for humanoid robot control","volume":"504","author":"Ai","year":"2019","journal-title":"Inform. Sci."},{"key":"10.1016\/j.asoc.2020.106775_b11","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.inffus.2020.01.011","article-title":"Affective recognition using multi-modal data and machine learning techniques: A tutorial and review","volume":"59","author":"Zhang","year":"2020","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.asoc.2020.106775_b12","article-title":"Affective recognition in speech signals using optimization based multi-SVNN classifier","author":"Mannepalli","year":"2018","journal-title":"J. King Saud Univ. - Comput. Inform. Sci."},{"key":"10.1016\/j.asoc.2020.106775_b13","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1016\/j.apacoust.2018.11.028","article-title":"A novel feature selection method for speech affective recognition","volume":"146","author":"\u00d6zseven","year":"2019","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.asoc.2020.106775_b14","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.asoc.2017.03.013","article-title":"Hybrid BBO_PSO and higher order spectral features for affective and stress recognition from natural speech","volume":"56","author":"C.K","year":"2017","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2020.106775_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2020.107360","article-title":"Speech affective recognition using hybrid spectral-prosodic features of speech signal\/glottal waveform, metaheuristic-based dimensionality reduction, and Gaussian elliptical basis function network classifier","volume":"166","author":"Daneshfar","year":"2020","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.asoc.2020.106775_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.image.2020.115831","article-title":"Human emotion recognition by optimally fusing facial expression and speech feature","volume":"84","author":"Wang","year":"2020","journal-title":"Signal Process., Image Commun."},{"key":"10.1016\/j.asoc.2020.106775_b17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2019.04.004","article-title":"Improving multilingual speech affective recognition by combining acoustic features in a three-layer model","volume":"110","author":"Li","year":"2019","journal-title":"Speech Commun."},{"key":"10.1016\/j.asoc.2020.106775_b18","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.apacoust.2018.12.006","article-title":"Acoustic event recognition using cochleagram image and convolutional neural networks","volume":"148","author":"Sharan","year":"2019","journal-title":"Appl. Acoust."},{"issue":"3","key":"10.1016\/j.asoc.2020.106775_b19","doi-asserted-by":"crossref","first-page":"92","DOI":"10.4018\/IJACI.2019070106","article-title":"Adam deep learning with SOM for human sentiment classification","volume":"10","author":"Ali","year":"2019","journal-title":"Int. J. Ambient Comput. Intell."},{"key":"10.1016\/j.asoc.2020.106775_b20","article-title":"Automated Parkinson\u2019s disease recognition based on statistical pooling method using acoustic features","volume":"135","author":"Orhan","year":"2020","journal-title":"Med. Hypotheses"},{"key":"10.1016\/j.asoc.2020.106775_b21","article-title":"Integrated optimization of underwater acoustic ship-radiated noise recognition based on two-dimensional feature fusion","volume":"159","author":"Ke","year":"2019","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.asoc.2020.106775_b22","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","article-title":"Speech affective recognition using deep 1D & 2D CNN LSTM networks","volume":"47","author":"Zhao","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"10.1016\/j.asoc.2020.106775_b23","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.specom.2020.03.005","article-title":"Speech affective recognition using fusion of three multi-task learning-based classifiers: HSF-DNN, MS-CNN and LLD-RNN","volume":"120","author":"Yao","year":"2020","journal-title":"Speech Commun."},{"key":"10.1016\/j.asoc.2020.106775_b24","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.specom.2019.03.006","article-title":"Training of reduced-rank linear transformations for multi-layer polynomial acoustic features for speech recognition","volume":"110","author":"Tahir","year":"2019","journal-title":"Speech Commun."},{"issue":"1","key":"10.1016\/j.asoc.2020.106775_b25","first-page":"107","article-title":"Comparative study on ant colony optimization (ACO) and k-means clustering approaches for jobs scheduling and energy optimization model in internet of things (IoT)","volume":"6","author":"Kumar","year":"2020","journal-title":"Int. J. Interact. Multimed. Artif. Intell."},{"issue":"3","key":"10.1016\/j.asoc.2020.106775_b26","first-page":"1175","article-title":"Fast single image haze removal method for inhomogeneous environment using variable scattering coefficient","volume":"123","author":"Gupta","year":"2020","journal-title":"CMES Comput. Model. Eng. Sci."},{"issue":"7","key":"10.1016\/j.asoc.2020.106775_b27","first-page":"22","article-title":"Gesture recognition of RGB and RGB-D static images using convolutional neural networks","volume":"5","author":"Khari","year":"2019","journal-title":"Int. J. Interact. Multimed. Artif. Intell."},{"issue":"1","key":"10.1016\/j.asoc.2020.106775_b28","first-page":"68","article-title":"Classification-based deep neural network architecture for collaborative filtering recommender systems","volume":"6","author":"Bobadilla","year":"2020","journal-title":"Int. J. Interact. Multimed. Artif. Intell."},{"key":"10.1016\/j.asoc.2020.106775_b29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.dsp.2018.11.005","article-title":"Ensemble of jointly trained deep neural network-based acoustic models for reverberant speech recognition","volume":"85","author":"Lee","year":"2019","journal-title":"Digit. Signal Process."},{"key":"10.1016\/j.asoc.2020.106775_b30","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.eswa.2018.05.016","article-title":"Speech-music discrimination using deep visual feature extractors","volume":"114","author":"Papakostas","year":"2018","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"10.1016\/j.asoc.2020.106775_b31","doi-asserted-by":"crossref","first-page":"60","DOI":"10.4018\/IJACI.2019070104","article-title":"Convolutional neural network based American sign language static hand gesture recognition","volume":"10","author":"Ahuja","year":"2019","journal-title":"Int. J. Ambient Comput. Intell."},{"issue":"1","key":"10.1016\/j.asoc.2020.106775_b32","doi-asserted-by":"crossref","first-page":"34","DOI":"10.4018\/IJACI.2020010102","article-title":"A visual detection method for foreign objects in power lines based on mask R-CNN","volume":"11","author":"Chen","year":"2020","journal-title":"Int. J. Ambient Comput. Intell."},{"key":"10.1016\/j.asoc.2020.106775_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2019.107175","article-title":"Acoustic data augmentation for mandarin-english code-switching speech recognition","volume":"161","author":"Long","year":"2020","journal-title":"Appl. Acoust."},{"issue":"6","key":"10.1016\/j.asoc.2020.106775_b34","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"J. Commun. ACM"},{"key":"10.1016\/j.asoc.2020.106775_b35","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.compeleceng.2019.03.004","article-title":"Modified alexnet architecture for classification of diabetic retinopathy images","volume":"76","author":"Shanthi","year":"2019","journal-title":"Comput. Electr. Eng."},{"key":"10.1016\/j.asoc.2020.106775_b36","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1016\/j.procs.2018.10.342","article-title":"Deep AlexNet with reduced number of trainable parameters for satellite image classification","volume":"143","author":"Unnikrishnan","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.asoc.2020.106775_b37","doi-asserted-by":"crossref","first-page":"2048","DOI":"10.1016\/j.procs.2017.08.250","article-title":"Classifying environmental sounds using image recognition networks","volume":"112","author":"Boddapati","year":"2017","journal-title":"Procedia Comput. Sci."},{"key":"10.1016\/j.asoc.2020.106775_b38","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.neunet.2019.07.012","article-title":"Recognition of words from brain-generated signals of speech-impaired people: Application of autoencoders as a neural turing machine controller in deep neural networks","volume":"121","author":"Boloukian","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.asoc.2020.106775_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2019.105834","article-title":"Automatic determination of digital modulation types with different noises using Convolutional Neural Network based on time-frequency information","volume":"86","author":"Daldal","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2020.106775_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2020.106127","article-title":"Texture selection for automatic music genre classification","volume":"89","author":"Foleis","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2020.106775_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.jneumeth.2020.108599","article-title":"Odor-induced affective recognition based on average frequency band division of EEG signals","volume":"334","author":"Hou","year":"2020","journal-title":"J. Neurosci. Methods"},{"key":"10.1016\/j.asoc.2020.106775_b42","doi-asserted-by":"crossref","unstructured":"Cummins Nicholas, Amiriparian Shahin, Gerhard\u00a0Johann Hagerer, et al. An image-based deep spectrum feature representation for the recognition of affectiveal speech, in: MM\u201917: ACM Proceedings of the 25th ACM international conference on Multimedia, Mountain View, CA, USA, 2017, pp. 478-484.","DOI":"10.1145\/3123266.3123371"},{"issue":"4","key":"10.1016\/j.asoc.2020.106775_b43","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation applied to handwritten zip code recognition","volume":"1","author":"LeCun","year":"1989","journal-title":"Neural Comput."},{"key":"10.1016\/j.asoc.2020.106775_b44","unstructured":"Nair Vinod, Hinton Geoffrey, Rectified Linear Units Improve Restricted Boltzmann Machines, in: Proceedings of the 27th International Conference on Machine Learning, ICML 2010, Haifa, Israel, 2010."},{"issue":"5","key":"10.1016\/j.asoc.2020.106775_b45","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0196391","article-title":"The ryerson audio-visual database of emotional speech and song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American english","volume":"13","author":"Livingstone","year":"2018","journal-title":"PLoS ONE"},{"issue":"4","key":"10.1016\/j.asoc.2020.106775_b46","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1016\/j.dss.2008.12.001","article-title":"Introducing functional classification theory to land use planning by means of decision tables","volume":"46","author":"Witlox","year":"2019","journal-title":"Decis. Support Syst."},{"key":"10.1016\/j.asoc.2020.106775_b47","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.neucom.2016.08.147","article-title":"Brain voxel classification in magnetic resonance images using niche differential evolution-based Bayesian inference of variational mixture of Gaussians","volume":"269","author":"Li","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2020.106775_b48","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.specom.2020.04.005","article-title":"EgyptIan arabic speech emotion recognition using prosodic, spectral and wavelet features","volume":"122","author":"Abdel-Hamid","year":"2020","journal-title":"Speech Commun."},{"key":"10.1016\/j.asoc.2020.106775_b49","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1016\/j.proeng.2012.06.120","article-title":"Speech and non-speech identification and classification using KNN algorithm","volume":"38","author":"Priya","year":"2012","journal-title":"Procedia Eng."},{"key":"10.1016\/j.asoc.2020.106775_b50","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.knosys.2017.05.011","article-title":"SVM-Based multi-state-mapping approach for multi-class classification","volume":"129","author":"Liu","year":"2017","journal-title":"Knowl.-Based Syst."},{"issue":"3","key":"10.1016\/j.asoc.2020.106775_b51","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1016\/j.bbe.2020.05.003","article-title":"Deep back propagation\u2013long short-term memory network based upper-limb sEMG signal classification for automated rehabilitation","volume":"40","author":"Wang","year":"2020","journal-title":"Biocybern. Biomed. Eng."},{"key":"10.1016\/j.asoc.2020.106775_b52","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.asoc.2018.10.006","article-title":"Classification of mice hepatic granuloma microscopic images based on a deep convolutional neural network","volume":"74","author":"Wang","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2020.106775_b53","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ijleo.2018.10.155","article-title":"Optical pressure sensors based plantar image segmenting using an improved fully convolutional network","volume":"179","author":"Wang","year":"2019","journal-title":"Optik"},{"issue":"30","key":"10.1016\/j.asoc.2020.106775_b54","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.ifacol.2019.12.500","article-title":"Kiwifruit detection in field images using faster R-CNN with VGG16","volume":"52","author":"Song","year":"2019","journal-title":"IFAC-PapersOnLine"},{"key":"10.1016\/j.asoc.2020.106775_b55","doi-asserted-by":"crossref","unstructured":"F. Shi, et al. Texture features based microscopic image classification of liver cellular granuloma using artificial neural networks, in: 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), Chongqing, China, 2019, pp. 432-439.","DOI":"10.1109\/ITAIC.2019.8785563"},{"key":"10.1016\/j.asoc.2020.106775_b56","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.neucom.2016.11.023","article-title":"G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition","volume":"225","author":"Tang","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2020.106775_b57","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2019.105912","article-title":"Unsupervised feature learning for environmental sound classification using weighted cycle-consistent generative adversarial network","volume":"86","author":"Esmaeilpour","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2020.106775_b58","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijleo.2020.164237","article-title":"A CAD system for diagnosing alzheimer\u2019s disease using 2D slices and an improved AlexNet-SVM method","volume":"212","author":"Shakarami","year":"2020","journal-title":"Optik"},{"key":"10.1016\/j.asoc.2020.106775_b59","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.eswa.2018.05.016","article-title":"Speech-music discrimination using deep visual feature extractors","volume":"114","author":"Papakostas","year":"2018","journal-title":"Expert Syst. Appl."}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494620307134?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494620307134?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T19:42:54Z","timestamp":1761594174000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494620307134"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":59,"alternative-id":["S1568494620307134"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2020.106775","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2020,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Simplified inverse filter tracked affective acoustic signals classification incorporating deep convolutional neural networks","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2020.106775","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2020 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"106775"}}