3-D Convolutional Recurrent Neural Networks With Attention Model for Speech Emotion Recognition
The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.
Abstract
Speech emotion recognition (SER) is a difficult task due to the complexity of emotions. The SER performances are heavily dependent on the effectiveness of emotional features extracted from the speech. However, most emotional features are sensitive to emotionally irrelevant factors, such as the speaker, speaking styles, and environment. In this letter, we assume that calculating the deltas and delta-deltas for personalized features not only preserves the effective emotional information but also reduces the influence of emotionally irrelevant factors, leading to reduce misclassification. In addition, SER often suffers from the silent frames and emotionally irrelevant frames. Meanwhile, attention mechanism has exhibited outstanding performances in learning relevant feature representations for specific tasks. Inspired by this, we propose a three-dimensional attention-based convolutional recurrent neural networks to learn discriminative features for SER, where the Mel-spectrogram with deltas and delta-deltas are used as input. Experiments on IEMOCAP and Emo-DB corpus demonstrate the effectiveness of the proposed method and achieve the state-of-the-art performance in terms of unweighted average recall.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Another issue faced by the time-frequency representation of speech emotion is that the distribution of emotion information in an utterance is sparse in both frequency domain and time domain [19], [23].”
From Speech Emotion Recognition via an Attentive Time–Frequency Neural Network (2023) · cites this paper as [19]
In the citing paper
“However, these studies mainly embed attention into highlevel time-frequency features, leading to introduce the redundant information in the feature extraction and roughly locate the emotion-related regions in the time-frequency domain.”
From Speech Emotion Recognition via an Attentive Time–Frequency Neural Network (2023) · cites this paper as [19]
In the citing paper
“In addition, they mainly focus on the selection on the time frames while ignoring the selection on the frequency bands.”
From Speech Emotion Recognition via an Attentive Time–Frequency Neural Network (2023) · cites this paper as [19]
In the citing paper
“ignoring to capture the specific frequency bands associated with emotions”
From Speech Emotion Recognition via an Attentive Time–Frequency Neural Network (2023) · cites this paper as [19]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“toolkit [24], and the parameters of the model were optimized by minimizing the cross-entropy objective function, with a minibatch of 40 samples, using the Adam optimizer [25] with Nestorov momentum.”
MethodNeural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 1×
“proposed in [9] for machine translation and later applied for”
MethodTensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
Hierarchical Attention Networks for Document Classification
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., & Hovy, E. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1174 · Cited by 4,712 · cited 1×
“document classification [10] and speech recognition [11].”
Self-citationIEMOCAP: Interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C.-C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008) · Language Resources and Evaluation · doi:10.1007/s10579-008-9076-6 · Cited by 3,869 · cited 12×
“D ACRNN obtains an absolute improvement of 2.34% and 3.44% for IEMOCAP and Emo-DB, respectively.”
MethodInfluentialA database of German emotional speech
Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W. F., & Weiss, B. (2005) · Interspeech 2005 · doi:10.21437/interspeech.2005-446 · Cited by 2,365 · cited 1×
“form speaker-independent SER experiments on the Interactive Emotional Dyadic Motion Capture database (IEMOCAP) [21] and the Berlin Emotional Database (Emo-DB) [22].”
MethodAttention-Based Models for Speech Recognition
Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1506.07503 · Cited by 2,021
Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition
Graves, A., Fernández, S., & Schmidhuber, J. (2005) · Lecture Notes in Computer Science · doi:10.1007/11550907_126 · Cited by 925 · cited 1×
“bidirectional RNN with long short-term memory cells [19] for temporal summarization, and each direction contains 128 cells; then, we can obtain a sequence of 256-dimensional high-level”
MethodAdieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network
Trigeorgis, G., Ringeval, F., Brueckner, R., Marchi, E., Nicolaou, M. A., Schuller, B., & Zafeiriou, S. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7472669 · Cited by 904 · cited 1×
“In recent years, CNN has exhibited excellent performances in the field of SER [1], [4], [6].”
BackgroundSpeech emotion recognition using deep neural network and extreme learning machine
Han, K., Yu, D., & Tashev, I. (2014) · Interspeech 2014 · doi:10.21437/interspeech.2014-57 · Cited by 794 · cited 4×
“1) DNN-extreme learning machine (DNN-ELM) ( see [3]).”
MethodInfluential
Research works printed but not linked: 2
- wei, 2016, Attention assisted discovery of sub-utterance structure in speech emotion recognition, Proc INTERSPEECH, 1387
- frano, 2016, Normalization and batch correction methods for high-throughput glycomics, Proc Joint Meet Soc Glycobiol, 1160
Cited by
Items 401–500 of 549
Emovo: A real-time anger detector on the smartphone using acoustic signal
Tong, Y., Mo, W., & Sun, Y. (2023) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/3594806.3594833 · Cited by 3
“Methods based on HiddenMarkov-Models[7], Convolutional Neural Networks(CNN)[4] and self-attention neural networks[22] are among the various approaches used to extract features from the audio signal.”
MethodFI-Net: A Speech Emotion Recognition Framework with Feature Integration and Data Augmentation
Xia, G., Li, F., Zhao, D., Zhang, Q., & Yang, S. (2019) · International Conference on Big Data Computing and Communications (BigCom) · doi:10.1109/bigcom.2019.00035 · Cited by 3
An optimal model with a lower bound of recall for imbalanced speech emotion recognition
Ai, X., Sheng, V. S., Fang, W., & Ling, C. X. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09155-3 · Cited by 3
Multi-Channel 2-D Convolutional Recurrent Neural Networks for Speech Emotion Recognition
Zhou, W., Zhou, H., & Xia, P. (2020) · Chinese Automation Congress · doi:10.1109/cac51589.2020.9326970 · Cited by 3
“Mirsamadi[9] used the attention mechanism in Bi-LSTM to balance LLD and HSF. Chen[10] proposed a 3-”
MethodDeep Learning as Feature Encoding for Emotion RecognitionPreprint
Nagarajan, B., & Oruganti, V. R. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.12613 · Cited by 3
“Deep learning techniques [5], [7] are observed to perform poorer than handcrafted features [4], [9].”
BackgroundSpeech Emotion Recognition with Co-Attention based Multi-level Acoustic InformationPreprint
Zou, H., Si, Y., Chen, C., Rajan, D., & Chng, E. S. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.15326 · Cited by 3
“-ELM [14] 62.85 63.89 3D ACRNN[15] - 64.74 ± 5.44 BLSTM-CTC-CA[16] 69.0 67.0 CNN GRU-SeqCap[17] 72.73 59.71 CNN TF Att.pooling[18] 71.75 68.06 HNSD[5] 70.5 72.5 Ours 71.64 72.70 Here, we introduce a kind of co-attention module to combine different frames of W2E with frame weights generated by the features of MFCC and…”
MethodInfluentialYan, T., Meng, H., Parada‐Cabaleiro, E., Tao, J., & Schuller, B. W. (2022) · doi:10.36227/techrxiv.21309600.v1 · Cited by 3
Spatiotemporal Graph Convolutional Networks for EEG-Based Emotion Recognition
Li, W., Shi, W., & Yeh, C.-H. (2024) · IEEE International Conference on Signal, Information and Data Processing (ICSIDP) · doi:10.1109/icsidp62679.2024.10869131 · Cited by 2
“Emotion recognition methods are generally categorized into two types: detecting human emotional behaviors, such as speech recognition [1] [2] and facial expression recognition [3], and detecting physiological signals like EEG, respiration, and ECG.”
Nithya, T., Ramkumar, M. S., Rajendran, T., Anitha, T., Munimathan, A., Khan, A., Naveed, Q. N., Khan, S., & Zewdie, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-16927-0 · Cited by 2
Emotion recognition using deep learning models in Chinese speech
Hung, K.-C., Amjad, A., Chao, Y., & Chang, H.-T. (2025) · Entertainment Computing · doi:10.1016/j.entcom.2025.101039 · Cited by 2
K-means++ guided multi-view CNN with channel attention for EEG emotion recognition
Zhou, Y., Jiang, R., & Zhang, J. (2026) · Brain Research · doi:10.1016/j.brainres.2026.150160 · Cited by 2
Robust speech emotion recognition under human speech noise
Mi, J., Shi, X., Ma, D., He, J., Fujimura, T., & Toda, T. (2026) · Computer Speech & Language · doi:10.1016/j.csl.2026.101987 · Cited by 2
Saliency-driven neural network for generalizable speech emotion recognition
Zheng, W., Tang, G., Yuan, Z., Zhang, H., Hou, D., Zhao, P., & Huang, H. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110504 · Cited by 2
Self-citationMulti-Task Learning-Based Speech Emotion Recognition Using Pre-Trained Acoustic Model
Wang, X., Yao, K., & Yi, Y. (2026) · Applied Sciences · doi:10.3390/app16105166 · Cited by 2
Speech Emotions Detection and Classification based on Speech Features using Deep Neural Network
Desai, P., Chakraborty, S., Sujatha, C., Desai, P., & Ansuman, S. (2023) · International Conference on Advances in Electrical, Electronics and Computational Intelligence (ICAEECI) · doi:10.1109/icaeeci58247.2023.10370971 · Cited by 2
“To extract significant information from the speech signal, the scientists adopted the BLSTM (bidirectional long-term and short-term memory) model[10].”
MethodParallel deep convolution neural network for speech-based sentiment recognition
Adagale, S. S., & Gupta, P. K. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20507-1 · Cited by 2
“Chen et al. [44] presented attention-based CNN (ACRNN) and 3-”
Analysis of Emotional Content in Indian Political Speeches
Goel, S., Pandey, S., & Shekhawat, H. S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68449-5_18 · Cited by 2
Upgraded Attention-Based Local Feature Learning Block for Speech Emotion Recognition
Zhao, H., Gao, Y., & Xiao, Y. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-75765-6_10 · Cited by 2
Speech Emotion Recognition Model with Time-Scale-Invariance MFCCs as Input
Xie, X., Lou, J., & Zhang, L. (2021) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc51323.2021.9498598 · Cited by 2
Automatic Speech Emotion Recognition Using Cochleagram Features
Borwankar, S., Shah, D., Verma, J. P. V., & Tanwar, S. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-8892-8_34 · Cited by 2
Advances Research in Speech Emotion Recognition Based on Multi-task Learning
Ma, Y., Di, G., & Wang, W. (2022) · International Workshop on Artificial Intelligence and Education (WAIE) · doi:10.1109/waie57417.2022.00013 · Cited by 2
“[5] proposed a 3D convolutional recurrent neural network based on an attention mechanism.”
BackgroundRoad Rage Recognition System Based on Speech Features
Li, Y., Wang, W., & Xu, X. (2022) · International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES) · doi:10.1109/dcabes57229.2022.00070 · Cited by 2
Speech Emotion Recognition Using Dual Global Context Attention and Time-Frequency Features
Zhang, P., Bai, X., Zhao, J., Liang, Y., Wang, F., & Wu, X.-M. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10192031 · Cited by 2
“utilized the attention mechanism to automatically focus on emotion-related frames, and design three-dimensional convolutional recurrent neural networks to learn these features [12].”
BackgroundMethodMulti-scale Aggregation Network for Speech Emotion Recognition
Dang, A., Linh, H. M., & Vu, D.-Q. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-0669-3_6 · Cited by 2
Feature Comparison for Speech Emotion Recognition on Hindi Language
Khurana, S., Dev, A., & Bansal, P. (2023) · International Conference on Speech Database and Assessments · doi:10.1109/o-cocosda60357.2023.10482951 · Cited by 2
“According to[21] .”
Huang, X., Sun, C., Yang, J., & Hou, X. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-73699-5_19 · Cited by 2
Self-citationKarnjanapatchara, T., Li, S., Mawalim, C. O., Komatani, K., & Okada, S. (2024) · International Conference on Affective Computing and Intelligent Interaction and workshops · doi:10.1109/acii63134.2024.00013 · Cited by 2
“DNNs outperform traditional methods in this field [6].”
Emotional Security for Sustainable Future: Multimodal Affective Computing
Rathi, N., Saran, P., & Shrivastava, S. (2025) · Advances in intelligent systems research/Advances in Intelligent Systems Research · doi:10.2991/978-94-6463-716-8_47 · Cited by 2
Conditional Transformer-Based U-Net Architecture for Speech Emotion Recognition
Chung, H., & Yoo, H. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097450 · Cited by 2
“In [16], the mel-spectral coefficients with their derivatives are used for training a 3-”
Sonar, Y., Wajage, P., Sunke, K., & Bidkar, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-7502-9_2 · Cited by 2
On Realizing Distributed Deep Neural Networks: An Astrophysics Case Study
Aspri, M., Tsagkatakis, G., Πανουσοπούλου, Α., & Tsakalides, P. (2019) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2019.8902592 · Cited by 2
Ses Tanıma için Derin Öğrenme Mimarileri Üzerine Derleme
DOKUZ, Y., & TÜFEKCİ, Z. (2020) · European Journal of Science and Technology · doi:10.31590/ejosat.araconf22 · Cited by 2
“Chen et al. (2018) proposed a 3D attention-based CRNN deep learning architecture which takes MFCC with deltas and delta-deltas as input for speech emotion recognition.”
BackgroundSpeech Emotion Recognition Based on Image Enhancement
Wang, D., Dong, J., Zhou, D., Wei, X., & Zhang, Q. (2019) · International Conference on Intelligent Systems and Knowledge Engineering (ISKE) · doi:10.1109/iske47853.2019.9170442 · Cited by 2
A Statistical Based Modeling Approach for Deep Learning Based Speech Emotion Recognition
Sekkate, S., Khalil, M., & Adib, A. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-71187-0_114 · Cited by 2
Survey of Transfer Learning and a Case Study of Emotion Recognition Using Inductive Approach
Abhinand, P., & Jayashree, R. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-5619-7_9 · Cited by 2
Emotion recognition from spontaneous speech using emotional vowel-like regions
Fahad, M. S., Singh, S., Abhinav, A., Ranjan, A., & Deepak, A. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12453-7 · Cited by 2
“The proposed approach is compared with the following state-of-the-art approaches developed using the same dataset and settings: Satt et al. [28], Lee et al. [17], Shruti et al. [13], and Chen et al. [8].”
BackgroundMethodRESERVOIR COMPUTING WITH TRUNCATED NORMAL DISTRIBUTION FOR SPEECH EMOTION RECOGNITION
Ibrahim, H., & Loo, C. K. (2022) · Malaysian Journal of Computer Science · doi:10.22452/mjcs.vol35no2.3 · Cited by 2
“Some studies that used deep learning obtained remarkable results, for example researchers in [11] [13] [44] [45] have used the EMODB dataset to evaluate the deep learning approach and they achieved distinguished results.”
ResultImproved Feature Fusion by Branched 1-D CNN for Speech Emotion Recognition
Medha, Chhabra, J. K., & Kumar, D. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-1648-1_15 · Cited by 2
Wen, G., Ye, S., Li, H., Wen, P., & Zhang, Y. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/3662839 · Cited by 2
“Tey focus on the innovative design of the neural network structures [11, 12], such as by adding the attention mechanism [13] and the transfer learning to solve problems of SER [14].”
BackgroundWang, Y. (2019) · Digital Repository Service (Northeastern University) · doi:10.17760/d20328716 · Cited by 2
How Speech is Recognized to Be Emotional - A Study Based on Information DecompositionPreprint
Sun, H., Li, L., Zheng, T. F., & Wang, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12324 · Cited by 2
“Other configurations were the same as in [10].”
BackgroundMethodInfluentialNeural Conversion of Social Attitudes in Speech Signals
Veillon, C. L. M. (2023) · theses.fr (ABES) · doi:10.70675/26188a9az8183z44bez8209z26e91c50ae8f · Cited by 2
Emerging Features and Classification Algorithms for Speaker Emotion Recognition: A Survey
Jagtap, S., & Mali, S. N. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-7985-8_93 · Cited by 1
A Hierarchical Speech Emotion Classification Framework based on Joint Triplet-Center Loss
Yang, X., Xia, X., & Dong, Y. (2020) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip49896.2020.9339353 · Cited by 1
“…[7], [8] or deep features [9]-[11] with machine learning models such as Hidden Markov model (HMM) [12], Gaussian Mixture model (GMM) [13], Support Vector Machine (SVM) [7], [14], Artificial Neural Network (ANN) [14], and Deep Neural Networks (DNN) [8], [15], they have achieved encouraging results.”
MethodLiu, Y., Xia, Y., Sun, H., Xiaolei, M. E. N. G., Jianxiong, B. A. I., Guan, W., Zhen, Z. H. A. O., & Yongwei, L. I. (2022) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2022eap1091 · Cited by 1
Adversarial Domain Adaptation for Noisy Speech Emotion Recognition
Cho, S., Yoon, S., & Song, H.-S. (2022) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas55662.2022.10003883 · Cited by 1
“Several methods [25, 26, 27] improve SER based on deep learning.”
BackgroundMethodSemantic Enhancement Network Integrating Label Knowledge for Multi-modal Emotion Recognition
Zheng, H., Miao, S., Qian, Y., Mu, Y., Jin, X., & Yan, K. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5675-9_40 · Cited by 1
Cross-Attention Dual-Stream Fusion for Speech Emotion Recognition
Yu, S., Meng, J., Zhu, B., & Sun, Q. (2024) · IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM) · doi:10.1109/pacrim61180.2024.10690221 · Cited by 1
“It is much better than several SER models, such as full training or fine tuning Wav2Vec [16], [34] and some single-or dual-stream representation models [9], [21], [29], [31].”
BackgroundMethodInfluentialLiu, H., Huang, X. S., & Xu, N. (2024) · International Conference on Telecommunications and Power Electronics (TELEPE) · doi:10.1109/telepe64216.2024.00159 · Cited by 1
“…text and speech emotion recognition, recurrent neural networks (RNN) and their variants, such as long short-term memory networks (LSTM) and gated recurrent units (GRU), have also been proven to be very effective models due to their ability to capture temporal dependencies in sequential data [4-5].”
BackgroundLearnable Deep Wavelet Packet Transform for Speech Emotion Recognition in High-Risk Suicide Calls
Nfissi, A., Bouachir, W., Bouguila, N., & Mishara, B. L. (2024) · International Conference on Machine Learning and Applications · doi:10.1109/icmla61862.2024.00035 · Cited by 1
“Chen et al.’s [31] method performs moderately, with a test accuracy of 59.6% and an F1-score of 60.2%.”
InfluentialA filtering approach for speech emotion recognition using wavelet approximation coefficient
Ravi, & Taran, S. (2025) · Measurement · doi:10.1016/j.measurement.2025.118165 · Cited by 1
Falahzadeh, M. R., Vakili, Y. Z., Harimi, A., Farsa, E. Z., Ahmadi, A., & Abraham, A. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20956-2 · Cited by 1
Shen, Z., Li, X., Bai, J., Wang, K., & Xu, Y. (2025) · IET Biometrics · doi:10.1049/bme2/7626919 · Cited by 1
“Chen et al. [8] proposed a 3D attention mechanism that processes an entire speech sample into small segments and uses delta and delta-deltas Mel spectral features for speech emotion recognition, and achieved good recognition results.”
Hassani, S. M., & Kangavari, M. R. (2025) · ETRI Journal · doi:10.4218/etrij.2025-0058 · Cited by 1
“We use an emotional speech recognition model [47] to predict the output of the emotions.”
Gan, C., Zhou, D., Zhu, Q., Wang, X., Jain, D. K., & Štruc, V. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3645933 · Cited by 1
“We then compute logarithmic Mel filter bank (MFB) energyfeatures[43],[44],using40Melfilters,a40msHamming window,anda10msframeshift.”
72‐3: Fully Convolutional Transformer‐Based Speech Emotion Recognition for Automotive Systems
Chung, H., & Yoo, H. (2025) · SID Symposium Digest of Technical Papers · doi:10.1002/sdtp.18336 · Cited by 1
Fractal-Based Speech Analysis for Emotional Content Estimation
Abrol, A., Kapoor, N., & Lehana, P. K. (2021) · Circuits Systems and Signal Processing · doi:10.1007/s00034-021-01737-2 · Cited by 1
Fractal-Based Speech Emotion Detection Using CNN
Borwankar, S., Dogra, M., & Verma, J. P. V. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-981-16-2709-5_56 · Cited by 1
Syllable Level Speech Emotion Recognition Based on Formant Attention
Rehman, A., Liu, Z., & Xu, J.-M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-93049-3_22 · Cited by 1
Constructing Speech Emotion Recognition Model Based on Convolutional Neural Network
Kuo, J.-Y., Chen, Z., & Lin, H.-C. (2021) · doi:10.1109/apsecw53869.2021.00020 · Cited by 1
A Prior-knowledge guided Multi-scale Deep Network for Speech Emotion Recognition
He, J. Y. D., Zhong, Y., Rao, P., Sun, B., & Zhang, Y. (2022) · Asia Pacific Information Technology Conference (APIT) · doi:10.1145/3512353.3512380 · Cited by 1
“Chen et al. [10] proposed attention-based convolutional recurrent neural network (ACRNN) which showed that convolution layers could extract high-level features from the log-Mel spectrogram.”
BackgroundMethodInfluentialSwetha, K., & Joseph, B. S. (2022) · International Conference on Breakthrough in Heuristics and Reciprocation of Advanced Technologies (BHARAT) · doi:10.1109/bharat53139.2022.00042 · Cited by 1
“Furthermore, the classifying ability of the recurrent neural network (RNN) system is enhanced by adapting multi-learning (ML) strategy [25].”
MethodSpeech Emotion Recognition Based on Multi-feature Fusion and DCNN
Yi-fei, M., Guo, J., & Fang, L. (2022) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1145/3573428.3573684 · Cited by 1
“In this paper, the pitch frequency of the speech waveform sequence is obtained by using the autocorrelation function method, and the period of the speech signal is found by looking for the delay of the peak of the autocorrelation function [10].”
BackgroundMethodInfluentialFahad, M. S., Raj, R., Ranjan, A., & Deepak, A. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-0085-5_71 · Cited by 1
Evidence-Based Research on Multimodal Fusion Emotion Recognition
Huang, Z., & Liao, M. (2023) · Atlantis Highlights in Intelligent Systems/Atlantis highlights in intelligent systems · doi:10.2991/978-94-6463-200-2_61 · Cited by 1
Emotional Feature Extraction for Depression Recognition Using SCAR-NET
Wang, Y., Mao, K., Ren, L., Qiu, J., & Dai, G. (2022) · IEEE Smart World Congress (SWC) · doi:10.1109/smartworld-uic-atc-scalcom-digitaltwin-pricomp-metaverse56740.2022.00276 · Cited by 1
“[12] proposed a convolutional recurrent neural network based on a 3D attention mechanism, which can better preserve contextual emotion-related information.”
Background2-D Attention Based Convolutional Recurrent Neural Network for Speech Emotion Recognition
Akalya, D. C., Karthika Renuka, D., Winy, A. E., Kruthikkha, P., Ramya, P. N., & Soundarya, S. (2022) · International Journal of Informatics Information System and Computer Engineering (INJIISCOM) · doi:10.34010/injiiscom.v3i2.8409 · Cited by 1
“Recognition of speech emotions is a technique that uses a processor to extract emotional information from speech signals (Chen et al., 2018).”
AL-anazi, R. G., AL-DOBAIAN, A. S., Hassan, A. A., Almanea, M. M., ALGHAMDI, A. A., ASKLANY, S. A., Sultan, H. A., & Majdoubi, J. (2024) · Fractals · doi:10.1142/s0218348x25400298 · Cited by 1
Deep Multiresolution Wavelet Transform for Speech Emotion Assessment of High-Risk Suicide Callers
Nfissi, A., Bouachir, W., Bouguila, N., & Mishara, B. L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-71602-7_22 · Cited by 1
Speech Emotion Recognition Using Deep Learning
Vidhya, R., Pendyala, A., Parkav, K. S., & Nagadevi, S. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-4650-7_35 · Cited by 1
Expressive Text-to-Speech with Contextual Background for ICAGC 2024
Jiang, Y., Wang, T., Wang, H., Gong, C., Liu, Q., Huang, Z., Wang, L., & Dang, J. (2024) · International Symposium on Chinese Spoken Language Processing (ISCSLP) · doi:10.1109/iscslp63861.2024.10800495 · Cited by 1
“…background audio descriptions, and AudioLDM 2 for generating the corresponding background audio. accuracy of soft labels through cross-domain training by us-ing pre-trained Speech Emotion Recognition (SER) [13] and Speech Emotion Diarization (SED) [14] to extract multi-level emotional features.”
Research and Applications of Digital Signal Processing
Mayer, J., Karaim, M. O., & Noureldin, A. M. (2025) · IntechOpen eBooks · doi:10.5772/intechopen.1005988 · Cited by 1
Emotions and Artificial Intelligence
(2026) · Frontiers research topics · doi:10.3389/978-2-8325-7327-3 · Cited by 1
Datastore Design for Analysis of Police Broadcast Audio at ScalePreprint
Ahmad, A., Graziul, C., & Spencer, M. B. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.16956 · Cited by 1
“While no model that we examined fulfilled all three requirements, [3] was perhapsthe closest.”
BackgroundSpeech-based Sentiment Recognition System using PDCNN and LSTM AlgorithmsPreprint
Adagale, S. S., & Gupta, P. K. (2024) · Research Square · doi:10.21203/rs.3.rs-4018342/v1 · Cited by 1
Zhang, K. (2025) · Research Square · doi:10.21203/rs.3.rs-7289832/v1 · Cited by 1
Análisis de la voz y clasificación de emociones mediante técnicas de Deep Learning
Hernández Calabrés, E. (2020) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 1
Voice Activity Detection Scheme by Combining DNN Model with GMM ModelPreprint
Ma, L., Zhang, X., Zhao, P., & Su, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.08184
“For DNN model, 29 dimensions of Fbank features are first extracted and then differential between consecutive frames is performed to obtain the 1 and the 2 delta features [6], followed by the cepstrum mean normalization (CMN) [7], resulting a di-”
MethodEt.al, S. I. J. (2021) · Türk bilgisayar ve matematik eğitimi dergisi · doi:10.17762/turcomat.v12i6.1277
Qiao, Y., Qian, K., Zhao, Z., & Xiaojing, Z. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-1649-5_14
Development of a Neural Network Algorithm to Detect Soldier Load from Environmental Speech
Scharine, A. A. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-79763-8_7
Silence Elimination for Robust Speaker Detection in Large Database
Rao, S. V. A., & Rao, P. R. K. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-3660-8_47
Hindi Songs Genre Classification Using Deep Learning
Fahad, M. S., Raj, R., Ranjan, A., & Deepak, A. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-9089-1_12
2018 Index IEEE Signal Processing Letters Vol. 25
(2018) · IEEE Signal Processing Letters · doi:10.1109/lsp.2018.2881640
Yan, T., Meng, H., Parada‐Cabaleiro, E., Tao, J., & Schuller, B. W. (2022) · doi:10.36227/techrxiv.21309600
Recurrent Neural Networks With Conformer for Speech Emotion RecognitionPreprint
Sun, C., Yang, J., Huang, X. M., & Hou, X. (2022) · doi:10.22541/au.166658945.58688710/v1
Self-citationCascaded Adversarial Learning for Speaker Independent Emotion Recognition
Lekamalage, C. K. L., Lin, Z., Huang, G.-B., & Rajapakse, J. C. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892223
“Table I shows performance of CAL relative to other AL algorithms [2], [3] in SIER, and non-AL algorithms [6], [8].”
BackgroundMethodResultInfluentialAn Improved Capsule Network for Speech Emotion Recognition
Zhang, H., & Huang, H. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-23387-6_10
Self-citationDevelopment of Techniques for Speech Emotion Recognition (SER) In the Context of Deep Learning
Triandi, B., Mawengkang, H., Efendi, S., & Syawaluddin (2022) · International Conference on Cybernetics and Intelligent System (ICORIS) · doi:10.1109/icoris56080.2022.10031385
Attention-based Mechanism of LSTM network for Speech Emotion Recognition
He, J., Liu, P., Kejia, Z., Shenke, W., Rao, F., & Xu, Q. (2022) · International Conference on Machine Learning, Control, and Robotics (MLCR) · doi:10.1109/mlcr57210.2022.00027
A Systematic Approach of Advanced Dilated Convolution Network for Speaker Identification
Pentapati, H. K., & Sridevi, K. (2023) · International Journal of Electrical and Electronics Research · doi:10.37391/ijeer.110104
Improving information fusion in deep learning
Don, D. P. M. K. (2023) · Queensland University of Technology · doi:10.5204/thesis.eprints.241291
Efficient Channel Attention for Speech Emotion Recognition With Asymmetric Convolution Module
Wu, T., Wang, L., Cheng, S., & Zhang, J. (2023) · IEEE International Conference on Pattern Recognition and Machine Learning (PRML) · doi:10.1109/prml59573.2023.10348239
Hayakawa, D., Kagoshima, T., Iwata, K., Braunschweiler, N., & Doddipatla, R. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389714
Research on Speech Emotion Recognition Analysis Based on Deep Learning
Li, C., & Yin, A. (2024) · Academic Journal of Science and Technology · doi:10.54097/nkzgwh08
An Extensive Investigation of Deep Learning Techniques for Audio-Visual Speech Recognition
Kuriakose, L. K., & Dhas, J. P. M. (2024) · International Conference on Emerging Trends in Information Technology and Engineering (ICETITE) · doi:10.1109/ic-etite58242.2024.10493813
“…Attention Mechanisms, Transformer-Based Models, Hybrid Models, End-to-End Models, Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs)[41], Long Short-Term Memory (LSTM)[42], Gated Recurrent Unit (GRU), Convolutional Neural Networks (CNNs), Hidden Markov Models (HMMs) and…”
BackgroundA NOVEL SPEECH RECOGNITION SYSTEM USING FUZZY NEURAL NETWORK
Babu, B. K., & Mutukuru, R. (2020) · Türk bilgisayar ve matematik eğitimi dergisi · doi:10.61841/turcomat.v11i3.14608
“Features of a speaker's speech or voice, such as their identity, age, gender, and emotions, might reveal information about person [11].”
BackgroundSpeech Emotion Detection Using Fusion on Multi-Source Low-Level Information Based Recurrent Branches
Jiaxin, W. U., Li, B., Zhao, L., & Xu, X. (2024) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.2024eap1034
Metadata
- Authors
- Chen, M., He, X., Yang, J., & Zhang, H.
- Affiliations
- Central South University (CN)
- Venue
- IEEE Signal Processing Letters
- Published
- 2018-10
- Volume
- 25
- Issue
- 10
- Pages
- 1440-1444
- ISSN
- 1070-9908 (ISSN-L)
- 1558-2361
- OpenAlex
- W2885005742
- Cited by
- 503
- References
- 23
- Citations by year
- 2026: 21 · 2025: 50 · 2024: 70 · 2023: 85 · 2022: 91 · 2021: 94 · 2020: 60 · 2019: 27 · 2018: 5
- FWCI
- 60.91
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Signal Processing Letters (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- speech emotion recognition, attention mechanism, Mel spectrogram, IEMOCAP, EMO-DB
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.