{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:30:34Z","timestamp":1784212234868,"version":"3.55.0"},"reference-count":77,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T00:00:00Z","timestamp":1679961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Sci."],"abstract":"<jats:p>Automatic emotion recognition (AER) systems are burgeoning and systems based on either audio, video, text, or physiological signals have emerged. Multimodal systems, in turn, have shown to improve overall AER accuracy and to also provide some robustness against artifacts and missing data. Collecting multiple signal modalities, however, can be very intrusive, time consuming, and expensive. Recent advances in deep learning based speech-to-text and natural language processing systems, however, have enabled the development of reliable multimodal systems based on speech <jats:italic>and<\/jats:italic> text while only requiring the collection of audio data. Audio data, however, is extremely sensitive to environmental disturbances, such as additive noise, thus faces some challenges when deployed \u201cin the wild.\u201d To overcome this issue, speech enhancement algorithms have been deployed <jats:italic>at the input signal level<\/jats:italic> to improve testing accuracy in noisy conditions. Speech enhancement algorithms can come in different flavors and can be optimized for different tasks (e.g., for human perception vs. machine performance). Data augmentation, in turn, has also been deployed <jats:italic>at the model level<\/jats:italic> during training time to improve accuracy in noisy testing conditions. In this paper, we explore the combination of task-specific speech enhancement and data augmentation as a strategy to improve overall multimodal emotion recognition in noisy conditions. We show that AER accuracy under noisy conditions can be improved to levels close to those seen in clean conditions. When compared against a system without speech enhancement or data augmentation, an increase in AER accuracy of 40% was seen in a cross-corpus test, thus showing promising results for \u201cin the wild\u201d AER.<\/jats:p>","DOI":"10.3389\/fcomp.2023.1039261","type":"journal-article","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:24:35Z","timestamp":1679981075000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Task-specific speech enhancement and data augmentation for improved multimodal emotion recognition under noisy conditions"],"prefix":"10.3389","volume":"5","author":[{"given":"Shruti","family":"Kshirsagar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anurag","family":"Pendyala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiago H.","family":"Falk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,3,28]]},"reference":[{"key":"B1","first-page":"458","article-title":"Philosophy of Language","volume":"2","author":"Alston","year":"1964","journal-title":"J. Philos. Logic"},{"key":"B2","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1109\/TAFFC.2018.2858255","article-title":"Feature pooling of modulation spectrum features for improved speech emotion recognition in the wild","volume":"12","author":"Avila","year":"2021","journal-title":"IEEE Trans. Affect. Comput"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.11477","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"arXiv preprint"},{"key":"B4","doi-asserted-by":"crossref","first-page":"5609","DOI":"10.1109\/ICASSP.2018.8462622","article-title":"\u201cSpectral feature mapping with mimic loss for robust speech recognition,\u201d","volume-title":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Bagchi","year":"2018"},{"key":"B5","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1037\/0022-3514.70.3.614","article-title":"Acoustic profiles in vocal emotion expression","volume":"70","author":"Banse","year":"1996","journal-title":"J. Pers. Soc. Psychol"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IWAENC.2016.7602930","article-title":"\u201cLate reverberation psd estimation for single-channel dereverberation using relative convolutive transfer functions,\u201d","volume-title":"2016 IEEE International Workshop on Acoustic Signal Enhancement (IWAENC)","author":"Braun","year":"2016"},{"key":"B7","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1186\/s13634-015-0242-x","article-title":"Combination of mvdr beamforming and single-channel spectral processing for enhancing noisy and reverberant speech","volume":"2015","author":"Cauchi","year":"2015","journal-title":"EURASIP J. Adv. Signal Process"},{"key":"B8","doi-asserted-by":"publisher","first-page":"7530","DOI":"10.3390\/s21227530","article-title":"The impact of attention mechanisms on speech emotion recognition","volume":"21","author":"Chen","year":"2021","journal-title":"Sensors"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.08379","article-title":"Emotionlines: an emotion corpus of multi-party conversations","author":"Chen","year":"2018","journal-title":"arXiv preprint"},{"key":"B10","unstructured":"\u201cMulti-modal emotion recognition from speech and text,\u201d4562\n            ChuangZ.-J.\n            WuC.-H.\n          International Journal of Computational Linguistics &Chinese Language Processing, Volume 9, Number 2, August 2004: Special Issue on New Trends of Speech and Language Processing2004"},{"key":"B11","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"B12","doi-asserted-by":"crossref","DOI":"10.1145\/3136755.3143004","article-title":"\u201cFrom individual to group-level emotion recognition: emotiw 5.0,\u201d","volume-title":"Proceedings of the 19th ACM International Conference on Multimodal Interaction","author":"Dhall","year":"2017"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.21437\/SMM.2018-5","article-title":"Cnn+ lstm architecture for speech emotion recognition with data augmentation","author":"Etienne","year":"2018","journal-title":"arXiv preprint"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.1145\/2502081.2502224","article-title":"\u201cRecent developments in openSMILE, the Munich open-source multimedia feature extractor,\u201d","volume-title":"Proceedings of the 21st ACM international conference on Multimedia","author":"Eyben","year":"2013"},{"key":"B15","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1109\/TAFFC.2015.2457417","article-title":"The geneva minimalistic acoustic parameter set GeMAPS for voice research and affective computing","volume":"7","author":"Eyben","year":"2016","journal-title":"IEEE Trans. Affect. Comput"},{"key":"B16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2013-484","article-title":"\u201cAffect recognition in real-life acoustic conditions-a new perspective on feature selection,\u201d","volume-title":"Proceedings 14th INTERSPEECH","author":"Eyben","year":"2013"},{"key":"B17","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/TASL.2009.2023679","article-title":"Modulation spectral features for robust far-field speaker identification","volume":"18","author":"Falk","year":"","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"B18","doi-asserted-by":"publisher","first-page":"24697","DOI":"10.1109\/TIM.2009.2024697","article-title":"Temporal dynamics for blind measurement of room acoustical parameters","volume":"59","author":"Falk","year":"","journal-title":"IEEE Trans. Instrum Meas"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1766","DOI":"10.1109\/TASL.2010.2052247","article-title":"A non-intrusive quality and intelligibility measure of reverberant and dereverberated speech","volume":"18","author":"Falk","year":"2010","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"B20","first-page":"2031","article-title":"\u201cMetricgan: generative adversarial networks based black-box metric scores optimization for speech enhancement,\u201d","volume-title":"International Conference on Machine Learning (PMLR)","author":"Fu","year":"2019"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599","article-title":"Metricgan+: an improved version of metricgan for speech enhancement","author":"Fu","year":"2021","journal-title":"arXiv preprint"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.5567","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv:1412.5567"},{"key":"B23","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neunet.2017.02.013","article-title":"Evaluating deep learning architectures for speech emotion recognition","volume":"92","author":"Haytham","year":"2017","journal-title":"Neural Netw"},{"key":"B24","article-title":"\u201cThe aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions,\u201d","volume-title":"Automatic Speech Recognition: Challenges for the new Millenium ISCA Tutorial and Research Workshop (ITRW)","author":"Hirsch","year":"2000"},{"key":"B25","doi-asserted-by":"publisher","first-page":"61672","DOI":"10.1109\/ACCESS.2020.2984368","article-title":"Multimodal approach of speech emotion recognition using multi-level multi-head fusion attention-based recurrent neural network","volume":"8","author":"Ho","year":"2020","journal-title":"IEEE Access"},{"key":"B26","doi-asserted-by":"crossref","first-page":"5044","DOI":"10.1109\/ICASSP.2018.8462624","article-title":"\u201cGenerative adversarial networks based data augmentation for noise robust speech recognition,\u201d","volume-title":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Hu","year":"2018"},{"key":"B27","doi-asserted-by":"crossref","first-page":"4749","DOI":"10.1109\/ICASSP.2015.7178872","article-title":"\u201cSpeech emotion recognition with acoustic and lexical features,\u201d","volume-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Jin","year":"2015"},{"key":"B28","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s12193-009-0025-5","article-title":"Multimodal emotion recognition in speech-based interaction using facial expression, body gesture and acoustic analysis","volume":"3","author":"Kessous","year":"2010","journal-title":"J. Multimodal User Interfaces"},{"key":"B29","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.dss.2018.09.002","article-title":"Deep learning for affective computing: text-based emotion recognition in decision support","volume":"115","author":"Kratzwald","year":"2018","journal-title":"Decis. Support. Syst"},{"key":"B30","doi-asserted-by":"publisher","first-page":"6445","DOI":"10.3390\/s22176445","article-title":"Cross-language speech emotion recognition using bag-of-word representations, domain adaptation, and data augmentation","volume":"22","author":"Kshirsagar","year":"","journal-title":"Sensors"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1892","DOI":"10.1109\/TAFFC.2022.3188223","article-title":"Quality-aware bag of modulation spectrum features for robust speech emotion recognition","volume":"13","author":"Kshirsagar","year":"","journal-title":"IEEE Tran. Affect. Comput"},{"key":"B32","doi-asserted-by":"publisher","first-page":"336","DOI":"10.21437\/Interspeech.2015-336","article-title":"High-level feature representation using recurrent neural network for speech emotion recognition","volume":"2015","author":"Lee","year":"2015","journal-title":"Interspeech"},{"key":"B33","doi-asserted-by":"publisher","first-page":"102185","DOI":"10.1016\/j.ipm.2019.102185","article-title":"Exploring temporal representations by leveraging attention-based bidirectional lstm-rnns for multi-modal emotion recognition","volume":"57","author":"Li","year":"2020","journal-title":"Inf. Process. Manag"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13673-019-0201-x","article-title":"Emotion classification based on brain wave: a survey","volume":"9","author":"Li","year":"2019","journal-title":"Hum. Centric Comput. Inf. Sci"},{"key":"B35","first-page":"436","article-title":"\u201cSpeech enhancement based on deep denoising autoencoder,\u201d","volume-title":"Interspeech","author":"Lu","year":"2013"},{"key":"B36","doi-asserted-by":"publisher","first-page":"106646","DOI":"10.1016\/j.cmpb.2022.106646","article-title":"Automated emotion recognition: current trends and future perspectives","volume":"2022","author":"Maithri","year":"2022","journal-title":"Comput. Methods Programs Biomed"},{"key":"B37","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1109\/TENCON.2019.8929493","article-title":"\u201cMultilingual cyber abuse detection using advanced transformer architecture,\u201d","volume-title":"TENCON 2019-2019 IEEE Region 10 Conference (TENCON)","author":"Malte","year":"2019"},{"key":"B38","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1109\/T-AFFC.2011.40","article-title":"Context-sensitive learning for enhanced audiovisual emotion classification","volume":"3","author":"Metallinou","year":"2012","journal-title":"IEEE Trans. Affect. Comput"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1109\/TASL.2010.2076804","article-title":"A framework for automatic human emotion classification using emotion profiles","volume":"19","author":"Mower","year":"2010","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"B40","first-page":"93","article-title":"\u201cMultimodal interaction: Intuitive, robust, and preferred?\u201d","volume-title":"IFIP Conference on Human-Computer Interaction","author":"Naumann","year":"2009"},{"key":"B41","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1109\/SLT48900.2021.9383588","article-title":"\u201cInvestigations on audiovisual emotion recognition in noisy conditions,\u201d","volume-title":"2021 IEEE Spoken Language Technology Workshop (SLT)","author":"Neumann","year":"2021"},{"key":"B42","doi-asserted-by":"crossref","first-page":"4131","DOI":"10.1109\/SMC.2019.8914254","article-title":"\u201cA multimodal approach to improve the robustness of physiological stress prediction during physical activity,\u201d","volume-title":"2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)","author":"Parent","year":"2019"},{"key":"B43","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/WCSE.2013.34","article-title":"\u201cIndividual emotion classification between happiness and sadness by analyzing photoplethysmography and skin temperature,\u201d","volume-title":"2013 Fourth World Congress on Software Engineering","author":"Park","year":"2013"},{"key":"B44","doi-asserted-by":"crossref","first-page":"I-733","DOI":"10.1109\/ICASSP.2004.1326090","article-title":"\u201cSpeech enhancement with missing data techniques using recurrent neural networks,\u201d","volume-title":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 1","author":"Parveen","year":"2004"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"Pascual","year":"2017","journal-title":"arXiv:1703.09452"},{"key":"B46","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1109\/PRML52754.2021.9520692","article-title":"\u201cTransformer based multimodal speech emotion recognition with improved neural networks,\u201d","volume-title":"2021 IEEE 2nd International Conference on Pattern Recognition and Machine Learning (PRML)","author":"Patamia","year":"2021"},{"key":"B47","first-page":"43","article-title":"Burnout in nursing","volume":"24","author":"Patrick","year":"2007","journal-title":"Aust. J. Adv. Nurs"},{"key":"B48","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"\u201cGlove: global vectors for word representation,\u201d","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Pennington","year":"2014"},{"key":"B49","doi-asserted-by":"crossref","first-page":"873","DOI":"10.18653\/v1\/P17-1081","article-title":"\u201cContext-dependent sentiment analysis in user-generated videos,\u201d","volume-title":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (volume 1: Long papers)","author":"Poria","year":"2017"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050","article-title":"Meld: a multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2018","journal-title":"arXiv preprint"},{"key":"B51","doi-asserted-by":"publisher","first-page":"100943","DOI":"10.1109\/ACCESS.2019.2929050","article-title":"Emotion recognition in conversation: research challenges, datasets, and recent advances","volume":"7","author":"Poria","year":"2019","journal-title":"IEEE Access"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.16061","article-title":"Evaluation: from precision, recall and f-measure to roc, informedness, markedness and correlation","author":"Powers","year":"2020","journal-title":"arXiv preprint"},{"key":"B53","doi-asserted-by":"crossref","DOI":"10.1145\/3347320.3357688","article-title":"\u201cAVEC 2019 workshop and challenge: state-of-mind, detecting depression with ai, and cross-cultural affect recognition,\u201d","volume-title":"Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop","author":"Ringeval","year":"2019"},{"key":"B54","first-page":"749","article-title":"\u201cPerceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs,\u201d","volume-title":"2001 IEEE international conference on acoustics, speech, and signal processing. Proceedings (Cat. No. 01CH37221), volume 2","author":"Rix","year":"2001"},{"key":"B55","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1007\/978-3-030-36808-1_72","article-title":"\u201cMulti-task gated contextual cross-modal attention framework for sentiment and emotion analysis,\u201d","volume-title":"International Conference on Neural Information Processing","author":"Sangwan","year":"2019"},{"key":"B56","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1142\/9789812775320_0021","article-title":"Multimodal emotion recognition","volume":"4","author":"Sebe","year":"2005","journal-title":"Handbook Pattern Recogn. Comput. Vis"},{"key":"B57","doi-asserted-by":"publisher","first-page":"176274","DOI":"10.1109\/ACCESS.2020.3026823","article-title":"Multimodal emotion recognition with transformer-based self supervised feature fusion","volume":"8","author":"Siriwardhana","year":"2020","journal-title":"IEEE Access"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1145\/3475957.3484450","article-title":"The muse 2021 multimodal sentiment analysis challenge: sentiment, emotion, physiological-emotion, and stress","author":"Stappen","year":"2021","journal-title":"arXiv preprint"},{"key":"B59","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","article-title":"An algorithm for intelligibility prediction of time-frequency weighted noisy speech","volume":"19","author":"Taal","year":"2011","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.06316","article-title":"What do you learn from context? probing for sentence structure in contextualized word representations","author":"Tenney","year":"2019","journal-title":"arXiv preprint"},{"key":"B61","doi-asserted-by":"crossref","DOI":"10.1121\/1.4799597","article-title":"\u201cThe diverse environments multi-channel acoustic noise database (demand): a database of multichannel environmental noise recordings,\u201d","volume-title":"Proceedings of Meetings on Acoustics ICA2013, volume 19","author":"Thiemann","year":"2013"},{"key":"B62","first-page":"1691","article-title":"\u201cTowards robust speech emotion recognition using deep residual networks for speech enhancement,\u201d","volume-title":"Interspeech","author":"Triantafyllopoulos","year":"2019"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747003","article-title":"Importantaug: a data augmentation agent for speech","author":"Trinh","year":"2021","journal-title":"arXiv preprint"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.05788","article-title":"Multi-modal emotion recognition on iemocap dataset using deep learning","author":"Tripathi","year":"2018","journal-title":"arXiv preprint"},{"key":"B65","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1109\/JSTSP.2017.2764438","article-title":"End-to-end multimodal emotion recognition using deep neural networks","volume":"11","author":"Tzirakis","year":"2017","journal-title":"IEEE J. Sel. Top. Signal Process"},{"key":"B66","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/2988257.2988258","article-title":"\u201cAvec 2016: depression, mood, and emotion recognition workshop and challenge,\u201d","volume-title":"Proceedings of the 6th International Workshop on Audio\/Visual Emotion Challenge","author":"Valstar","year":"2016"},{"key":"B67","first-page":"5998","article-title":"\u201cAttention is all you need,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"B68","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","article-title":"Automatic speech emotion recognition using modulation spectral features","volume":"53","author":"Wu","year":"2011","journal-title":"Speech Commun"},{"key":"B69","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.jad.2020.08.001","article-title":"Impact of covid-19 pandemic on mental health in the general population: a systematic review","volume":"277","author":"Xiong","year":"2020","journal-title":"J. Affect. Disord"},{"key":"B70","doi-asserted-by":"crossref","first-page":"48","DOI":"10.21437\/SLaTE.2019-9","article-title":"\u201cAcoustic correlates of speech intelligibility: the usability of the egemaps feature set for atypical speech,\u201d","volume-title":"Proceedings of 8th ISCA Workshop on Speech and Language Technology in Education (SLaTE 2019)","author":"Xue","year":"2019"},{"key":"B71","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.11565","article-title":"Emotionx-ku: BERT-max based contextual emotion classifier","author":"Yang","year":"2019","journal-title":"arXiv preprint"},{"key":"B72","doi-asserted-by":"publisher","first-page":"1536","DOI":"10.3390\/e23111536","article-title":"Bert-enhanced text graph neural network for classification","volume":"23","author":"Yang","year":"2021","journal-title":"Entropy"},{"key":"B73","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/TMM.2006.886310","article-title":"Audio-visual affect recognition","volume":"9","author":"Zeng","year":"2007","journal-title":"IEEE Trans. Multimedia"},{"key":"B74","first-page":"5415","article-title":"\u201cModeling both context-and speaker-sensitive dependence for emotion detection in multi-speaker conversations,\u201d","volume-title":"IJCAI","author":"Zhang","year":"2019"},{"key":"B75","first-page":"285","article-title":"Sentiment classification based on piecewise pooling convolutional neural network","volume":"56","author":"Zhang","year":"2018","journal-title":"Comput. Mater. Continua"},{"key":"B76","doi-asserted-by":"crossref","first-page":"2401","DOI":"10.1109\/ICASSP.2018.8462155","article-title":"\u201cConvolutional-recurrent neural networks for speech enhancement,\u201d","volume-title":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Zhao","year":"2018"},{"key":"B77","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","article-title":"Speech emotion recognition using deep 1d and 2d cnn lstm networks","volume":"47","author":"Zhao","year":"2019","journal-title":"Biomed. Signal Process. Control"}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2023.1039261\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:25:15Z","timestamp":1679981115000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2023.1039261\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,28]]},"references-count":77,"alternative-id":["10.3389\/fcomp.2023.1039261"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2023.1039261","relation":{},"ISSN":["2624-9898"],"issn-type":[{"value":"2624-9898","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,28]]},"article-number":"1039261"}}