{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T11:51:42Z","timestamp":1781956302924,"version":"3.54.5"},"reference-count":52,"publisher":"Elsevier BV","issue":"7","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T00:00:00Z","timestamp":1774396800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004070","name":"Khalifa University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004070","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.ipm.2026.104774","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T09:55:13Z","timestamp":1775210113000},"page":"104774","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Emotion and noise-robust speaker identification via filter-free self-supervised learning"],"prefix":"10.1016","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9422-7251","authenticated-orcid":false,"given":"Shibani","family":"Hamsa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0112-2600","authenticated-orcid":false,"given":"Youssef","family":"Iraqi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7856-9342","authenticated-orcid":false,"given":"Ismail","family":"Shahin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9557-6496","authenticated-orcid":false,"given":"Ernesto","family":"Damiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3878-2621","authenticated-orcid":false,"given":"Kinda","family":"Khalaf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1573-3659","authenticated-orcid":false,"given":"Herbert F.","family":"Jelinek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5542-448X","authenticated-orcid":false,"given":"Naoufel","family":"Werghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.ipm.2026.104774_bib0001","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1007\/s41870-022-01142-1","article-title":"Person identification based on voice biometric using deep neural network","volume":"15","author":"Al-Shakarchy","year":"2023","journal-title":"International Journal of Information Technology"},{"key":"10.1016\/j.ipm.2026.104774_bib0002","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2025.3529125","article-title":"Novel speech-based emotion climate recognition in peers\u2019 conversations incorporating affect dynamics and temporal convolutional neural networks","volume":"13","author":"Alhussein","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.ipm.2026.104774_bib0003","unstructured":"Bai, Y., Chen, J., Chen, J., Chen, Z., Ding, C. et al. (2024). Seed-ASR: Understanding diverse speech and contexts with LLM-based speech recognition. arXiv: 2407.04675."},{"key":"10.1016\/j.ipm.2026.104774_bib0004","article-title":"Advanced speech emotion recognition utilizing optimized equivariant quantum convolutional neural network for accurate emotional state classification","volume":"316","author":"Balachandran","year":"2025","journal-title":"Knowledge-based Systems"},{"key":"10.1016\/j.ipm.2026.104774_bib0005","series-title":"Proceedings of the 2021 29th European signal processing conference (EUSIPCO)","first-page":"446","article-title":"Word-level embeddings for cross-task transfer learning in speech processing","author":"Beckmann","year":"2021"},{"key":"10.1016\/j.ipm.2026.104774_bib0006","unstructured":"Beckmann, P., Kegler, M., Saltini, H., & Cernak, M. (2019). Speech-VGG: A deep feature extractor for speech processing. arXiv: 1910.09909."},{"key":"10.1016\/j.ipm.2026.104774_bib0007","series-title":"Proceedings of the international conference on speech and computer","first-page":"79","article-title":"Data augmentation and loss normalization for deep noise suppression","author":"Braun","year":"2020"},{"key":"10.1016\/j.ipm.2026.104774_bib0008","series-title":"Proceedings of interspeech","first-page":"3257","article-title":"Front-end feature compensation and denoising for noise robust speech emotion recognition","author":"Chakraborty","year":"2019"},{"key":"10.1016\/j.ipm.2026.104774_bib0009","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.neucom.2020.08.040","article-title":"SpeakerGAN: Speaker identification with conditional generative adversarial network","volume":"418","author":"Chen","year":"2020","journal-title":"Neurocomputing"},{"issue":"6","key":"10.1016\/j.ipm.2026.104774_bib0010","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"WavLM: Large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"10.1016\/j.ipm.2026.104774_bib0011","series-title":"Proceedings of interspeech","first-page":"581","article-title":"The effect of spectral profile on the intelligibility of emotional speech in noise","author":"Davis","year":"2017"},{"key":"10.1016\/j.ipm.2026.104774_bib0012","series-title":"2017\u202fIEEE International conference on acoustics, speech and signal processing (ICASSP)","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"Gemmeke","year":"2017"},{"key":"10.1016\/j.ipm.2026.104774_bib0013","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.-A., & Glass, J. (2021). AST: Audio spectrogram transformer. arXiv: 2104.01778.","DOI":"10.21437\/Interspeech.2021-698"},{"key":"10.1016\/j.ipm.2026.104774_bib0014","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"10699","article-title":"SSAST: Self-supervised audio spectrogram transformer","volume":"vol. 36","author":"Gong","year":"2022"},{"key":"10.1016\/j.ipm.2026.104774_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.119871","article-title":"Speaker identification from emotional and noisy speech using learned voice segregation and speech VGG","volume":"224","author":"Hamsa","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.ipm.2026.104774_bib0016","series-title":"Fifth european conference on speech communication and technology","article-title":"Getting started with SUSAS: A speech under simulated and actual stress database","author":"Hansen","year":"1997"},{"key":"10.1016\/j.ipm.2026.104774_bib0017","series-title":"Proceedings of ICASSP 2025 - IEEE international conference on acoustics, speech and signal processing","first-page":"1","article-title":"Emotion-preserving prosody anonymization network for voice privacy protection","author":"He","year":"2025"},{"key":"10.1016\/j.ipm.2026.104774_bib0018","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: Self-supervised speech representation learning by masked prediction of hidden units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.ipm.2026.104774_bib0019","unstructured":"Hu, Y., Chen, C.-H. H., Yang, C.-H. H., Li, R., Zhang, C., Chen, P.-Y., & Chng, E. S. (2024). Large language models are efficient learners of noise-robust speech recognition. arXiv: 2401.10446."},{"key":"10.1016\/j.ipm.2026.104774_bib0020","series-title":"Proceedings of interspeech 2019","first-page":"1701","article-title":"Learning temporal clusters using capsule routing for speech emotion recognition","author":"Jalal","year":"2019"},{"issue":"6","key":"10.1016\/j.ipm.2026.104774_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2023.103501","article-title":"A deep interpretable representation learning method for speech emotion recognition","volume":"60","author":"Jing","year":"2023","journal-title":"Information Processing Management"},{"key":"10.1016\/j.ipm.2026.104774_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.dsp.2024.104811","article-title":"Comparative analysis of speaker identification performance using deep learning, machine learning, and novel subspace classifiers with multiple feature extraction techniques","volume":"156","author":"Keser","year":"2025","journal-title":"Digital Signal Processing"},{"issue":"7","key":"10.1016\/j.ipm.2026.104774_bib0023","first-page":"2067","article-title":"Robust speaker recognition in reverberant and noisy conditions","volume":"19","author":"Larcher","year":"2011","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.ipm.2026.104774_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.chb.2025.108598","article-title":"Avatar-mediated communication in collaborative virtual environments: A study on users\u2019 attention allocation and perception of social interactions","volume":"167","author":"Li","year":"2025","journal-title":"Computers in Human Behavior"},{"issue":"6","key":"10.1016\/j.ipm.2026.104774_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2021.102717","article-title":"Semi-supervised emotion recognition in textual conversation via a context-augmented auxiliary training task","volume":"58","author":"Kang","year":"2021","journal-title":"Information Processing Management"},{"key":"10.1016\/j.ipm.2026.104774_bib0026","series-title":"Proceedings of ICASSP 2023 - IEEE international conference on acoustics, speech and signal processing","first-page":"1","article-title":"AST-SED: An effective sound event detection method based on audio spectrogram transformer","author":"Li","year":"2023"},{"issue":"5","key":"10.1016\/j.ipm.2026.104774_bib0027","doi-asserted-by":"crossref","DOI":"10.1115\/1.4053521","article-title":"The effect of different occupational background noises on voice recognition accuracy","volume":"22","author":"Li","year":"2022","journal-title":"Journal of Computing and Information Science in Engineering"},{"key":"10.1016\/j.ipm.2026.104774_bib0028","doi-asserted-by":"crossref","first-page":"4026","DOI":"10.1109\/TASLP.2024.3453606","article-title":"U-Style: Cascading U-Nets with multi-level speaker and style modeling for zero-shot voice cloning","volume":"32","author":"Li","year":"2024","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"12","key":"10.1016\/j.ipm.2026.104774_bib0029","doi-asserted-by":"crossref","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","article-title":"A survey of convolutional neural networks: Analysis, applications, and prospects","volume":"33","author":"Li","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"10.1016\/j.ipm.2026.104774_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2006.05.011","article-title":"Multimodal emotion recognition in complex acoustic environments","volume":"61","author":"Liu","year":"2025","journal-title":"Information Processing Management"},{"issue":"5","key":"10.1016\/j.ipm.2026.104774_bib0031","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"},{"key":"10.1016\/j.ipm.2026.104774_bib0032","series-title":"Proc. interspeech","first-page":"4328","article-title":"AA-SLLM: An acoustically augmented speech large language model for speech emotion recognition","volume":"vol. 2025","author":"Mai","year":"2025"},{"key":"10.1016\/j.ipm.2026.104774_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2024.110435","article-title":"Stationary wavelet filtering cepstral coefficients (SWFCC) for robust speaker identification","volume":"231","author":"Missaoui","year":"2025","journal-title":"Applied Acoustics"},{"key":"10.1016\/j.ipm.2026.104774_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.116469","article-title":"Emotional speaker identification using a novel capsule nets model","volume":"193","author":"Nassif","year":"2022","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.ipm.2026.104774_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2021.107141","article-title":"Casa-based speaker identification using cascaded GMM-CNN classifier in noisy and emotional talking conditions","volume":"103","author":"Nassif","year":"2021","journal-title":"Applied Soft Computing"},{"issue":"2","key":"10.1016\/j.ipm.2026.104774_bib0036","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1109\/TSP.2018.2883021","article-title":"Learning filter bank sparsifying transforms","volume":"67","author":"Pfister","year":"2018","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.1016\/j.ipm.2026.104774_bib0037","series-title":"Proceedings of interspeech","first-page":"1612","article-title":"A discriminative model for speech recognition in adverse conditions","author":"Prabhavalkar","year":"2012"},{"issue":"1","key":"10.1016\/j.ipm.2026.104774_bib0038","article-title":"Multimodal disentanglement implicit distillation for speech emotion recognition","volume":"62","author":"Qi","year":"2025","journal-title":"Information Processing Management"},{"key":"10.1016\/j.ipm.2026.104774_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113452","article-title":"CTSE-NET: Resource-efficient convolutional and TF-transformer network for speech enhancement","volume":"317","author":"Saleem","year":"2025","journal-title":"Knowledge-based Systems"},{"key":"10.1016\/j.ipm.2026.104774_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113452","article-title":"CTSE-Net: Resource-efficient convolutional and TF-transformer network for speech enhancement","volume":"317","author":"Saleem","year":"2025","journal-title":"Knowledge-based Systems"},{"key":"10.1016\/j.ipm.2026.104774_bib0041","doi-asserted-by":"crossref","first-page":"26777","DOI":"10.1109\/ACCESS.2019.2901352","article-title":"Emotion recognition using hybrid Gaussian mixture model and deep neural network","volume":"7","author":"Shahin","year":"2019","journal-title":"IEEE Access"},{"issue":"7","key":"10.1016\/j.ipm.2026.104774_bib0042","doi-asserted-by":"crossref","first-page":"2575","DOI":"10.1007\/s00521-018-3760-2","article-title":"Novel cascaded Gaussian mixture model-deep neural network classifier for speaker identification in emotional talking environments","volume":"32","author":"Shahin","year":"2020","journal-title":"Neural Computing and Applications"},{"key":"10.1016\/j.ipm.2026.104774_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2024.109915","article-title":"Text-independent speaker identification using modified sincnet with robust features from suitable acoustic region and appropriate optimizer for raw audio analysis","volume":"121","author":"Shome","year":"2025","journal-title":"Computers and Electrical Engineering"},{"issue":"16","key":"10.1016\/j.ipm.2026.104774_bib0044","doi-asserted-by":"crossref","first-page":"48105","DOI":"10.1007\/s11042-023-17573-2","article-title":"A text independent speaker identification system using ANN, RNN, and CNN classification technique","volume":"83","author":"Singh","year":"2024","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.ipm.2026.104774_bib0045","series-title":"2011\u202fIEEE International conference on automatic face & gesture recognition (FG)","first-page":"803","article-title":"Continuous emotion detection in response to music videos","author":"Soleymani","year":"2011"},{"key":"10.1016\/j.ipm.2026.104774_bib0046","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2025.107811","article-title":"Multi-task coordinate attention gating network for speech emotion recognition under noisy circumstances","volume":"107","author":"Sun","year":"2025","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.1016\/j.ipm.2026.104774_bib0047","doi-asserted-by":"crossref","first-page":"14094","DOI":"10.1109\/ACCESS.2024.3356730","article-title":"Robust feature extraction using temporal context averaging for speaker identification in diverse acoustic environments","volume":"12","author":"Terraf","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.ipm.2026.104774_bib0048","unstructured":"Thimonier, H., Perzo, A., & Seguier, R. (2025). EmoSLLM: Parameter-efficient adaptation of LLMs for speech emotion recognition. arXiv: 2508.14130."},{"key":"10.1016\/j.ipm.2026.104774_bib0049","series-title":"Proceedings of the IEEE Southeastcon 2025","first-page":"333","article-title":"Comparing support vector machine and k nearest neighbor algorithms in classifying speech","author":"Thorpe","year":"2025"},{"key":"10.1016\/j.ipm.2026.104774_bib0050","doi-asserted-by":"crossref","first-page":"4971","DOI":"10.1109\/TASLP.2024.3492793","article-title":"Overview of speaker modeling and its applications: From the lens of deep speaker representation learning","volume":"32","author":"Wang","year":"2024","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"10.1016\/j.ipm.2026.104774_bib0051","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/j.aej.2025.03.071","article-title":"T_SRNET: A multimodal model based on convolutional neural network for emotional speech enhancement","volume":"124","author":"Wang","year":"2025","journal-title":"Alexandria Engineering Journal"},{"key":"10.1016\/j.ipm.2026.104774_bib0052","first-page":"1","article-title":"Using speech enhancement to improve speech emotion recognition in noisy environments","volume":"122","author":"Zhou","year":"2020","journal-title":"Speech Communication"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326001652?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326001652?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T11:29:47Z","timestamp":1781954987000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326001652"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":52,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["S0306457326001652"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104774","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Emotion and noise-robust speaker identification via filter-free self-supervised learning","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104774","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"104774"}}