Abstract
Speech emotion recognition (SER), which has gained greater attention in recent years, is a key aspect of the human–computer interaction process. However, a wide range of strategies has been offered in SER, and these approaches have yet to increase performance. In this study, a deep neural network model for classifying voice emotions is suggested. It is divided into three stages: feature extraction, normalization, and emotion recognition. The Librosa Python Toolkit is used to acquire the MFCC, Mel-Spectrogram Frequency, Chroma, and Poly Features during feature extraction. Data augmentation for the minority class using SMOTE (synthetic minority oversampling technique) and the Min–Max scaler for the normalization process were used. The model was evaluated on three frequently used languages: German, English, and French, using the Berlin Emotional Speech Database (EMODB), Surrey Audio-Visual Expressed Emotion Dataset (SAVEE), and the Canadian French Emotional (CaFE) speech datasets. The recognition rates of unweighted accuracy of 95% on EMODB, 90% on SAVEE, and 92% on CaFE are gained in speaker-dependent experiments. The results show that the suggested method is capable of efficiently recognizing emotions and outperformed the other approaches utilized for comparison in terms of performance indicators.
Similar content being viewed by others
Data Availability and Materials
Available upon request.
References
L. Chen et al., Two-layer fuzzy multiple random forest for speech emotion recognition in human-robot interaction. Inf. Sci. 509, 150–163 (2020)
H. Ibrahim, C.K. Loo, Reservoir computing with truncated normal distribution for speech emotion recognition. Malays. J. Comput. Sci. 35, 128–141 (2022)
N. Truong Pham, Hybrid data augmentation and deep attention-based dilated convolutional-recurrent neural networks for speech emotion recognition. ArXiv arXiv:2109.09026 (2021).
L.-N. Do et al., Deep neural network-based fusion model for emotion recognition using visual data. J. Supercomput. 77, 10773–10790 (2021)
L. Rowlands, Emotions: how humans regulate them and why some people can’t | News and Events | Bangor University. https://www.bangor.ac.uk/news/archive/emotions-how-humans-regulate-them-and-why-some-people-can-t-38444
B. McFee et al. Librosa: audio and music signal analysis in python. In Proceedings of the 14th Python in Science Conference 18–24 (SciPy, 2015). doi:https://doi.org/10.25080/majora-7b98e3ed-003.
M.C. Sezgin, B. Gunsel, G.K. Kurt, Perceptual audio features for emotion detection. EURASIP J. Audio Speech Music Process. 2012, 16 (2012)
C. Albon, Machine learning with Python Cookbook: Practical Solutions from Preprocessing to Deep Learning (O’Reilly Media, Sebastopol, 2018)
S. Kanwal, S. Asghar, Speech emotion recognition using clustering based GA-optimized feature set. IEEE Access 9, 125830–125842 (2021)
K. Chauhan, K.K. Sharma, T. Varma, Speech emotion recognition using convolution neural networks. Proc. Int. Conf. Artif. Intell. Smart Syst. 2021, 1176–1181 (2021). https://doi.org/10.1109/ICAIS50930.2021.9395844
H. Ibrahim, C.K. Loo, F. Alnajjar, Speech emotion recognition by late fusion for bidirectional reservoir computing with random projection. IEEE Access 9, 122855–122871 (2021)
N. Liu et al., Transfer subspace learning for unsupervised cross-corpus speech emotion recognition. IEEE Access 9, 95925–95937 (2021)
S.M. Mustaqeem, S. Kwon, Clustering-Based Speech Emotion Recognition by Incorporating Learned Features and Deep BiLSTM. IEEE Access 8, 79861–79875 (2020)
N.T. Pham, D.N.M. Dang, N.D. Nguyen, T.T. Nguyen, H. Nguyen, B. Manavalan, C.P. Lim, S.D. Nguyen, Hybrid data augmentation and deep attention-based dilated convolutional-recurrent neural networks for speech emotion recognition. Expert Syst. Appl. (2023). https://doi.org/10.48550/arxiv.2109.09026
M. Seknedy El, S. Fawzi, Speech emotion recognition system for human interaction applications. In: Proceedings—2021 IEEE 10th International Conference on Intelligent Computing and Information Systems, ICICIS 2021 361–368 (2021) doi:https://doi.org/10.1109/ICICIS52592.2021.9694246.
H. Zhang, H. Huang, H. Han, A novel heterogeneous parallel convolution bi-LSTM for speech emotion recognition. Appl. Sci. 11, 9897 (2021)
H. Aouani, Y.B. Ayed, Speech emotion recognition with deep learning. Procedia Comput. Sci. 176, 251–260 (2020)
S. Huang et al., Multi-layer hybrid fuzzy classification based on SVM and improved PSO for speech emotion recognition. Electronics 10, 2891 (2021)
Z.T. Liu, A. Rehman, M. Wu, W.H. Cao, M. Hao, Speech emotion recognition based on formant characteristics feature extraction and phoneme type convergence. Inf. Sci. 563, 309–325 (2021)
W. Zehra, A.R. Javed, Z. Jalil, H.U. Khan, T.R. Gadekallu, Cross corpus multi-lingual speech emotion recognition using ensemble learning. Complex Intell. Syst. 7, 1845–1854 (2021)
M.D. Pawar, R.D. Kokate, Convolution neural network based automatic speech emotion recognition using Mel-frequency Cepstrum coefficients. Multimed. Tools Appl. 80, 15563–15587 (2021)
M.H. Pham, F.M. Noori, J.Torresen, Emotion recognition using speech data with convolutional neural network. In: 2021 IEEE 2nd International Conference on Signal, Control and Communication, SCC 2021 182–187 (2021) doi:https://doi.org/10.1109/SCC53769.2021.9768372.
K.K. Sahoo, I. Dutta, M.F. Ijaz, M. Wozniak, P.K. Singh, TLEFuzzyNet: fuzzy rank-based ensemble of transfer learning models for emotion recognition from human speeches. IEEE Access 9, 166518–166530 (2021)
A.K. Sahoo, C. Pradhan, H. Das, Performance evaluation of different machine learning methods and deep-learning based convolutional neural network for health decision making, in Nature Inspired Computing for Data Science. In Studies in Computational Intelligence. (Springer, Cham, 2020), pp.201–212
B.T. Atmaja, A. Sasou, M. Akagi, Survey on bimodal speech emotion recognition from acoustic and linguistic information fusion. Speech Commun. 140, 11–28 (2022)
K.S. Rao, S.G. Koolagudi, Emotion Recognition using Speech Features (Springer, Cham, 2013). https://doi.org/10.1007/978-1-4614-5143-3
M. Swain, A. Routray, P. Kabisatpathy, Databases, features and classifiers for speech emotion recognition: a review. Int. J. Speech Technol. 21, 93–120 (2018)
G. Degottex, J. Kane, T. Drugman, T. Raitio, S. Scherer, COVAREP—A collaborative voice analysis repository for speech technologies. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 960–964 (2014) doi:https://doi.org/10.1109/ICASSP.2014.6853739.
Eyben F., B. Schuller. openSMILE:. ACM SIGMultimedia Records 6, (2015).
Kejriwal J., Benus, S. & Trnka, M. Stress detection using non-semantic speech representation. 2022 32nd International Conference Radioelektronika, RADIOELEKTRONIKA 2022 - Proceedings (2022) doi:https://doi.org/10.1109/RADIOELEKTRONIKA54537.2022.9764916.
S. Mai, S. Xing, H. Hu, Analyzing multimodal sentiment via acoustic- and visual-LSTM with channel-aware temporal convolution network. IEEE/ACM Trans. Audio Speech Lang. Process. 29, 1424–1437 (2021)
M. Mueller, B. McFee, Interactive learning of signal processing through music: making fourier analysis concrete for students. IEEE Signal Process Mag. 38, 73–84 (2021)
M. Muthumari, V. Akash, K. Prudhvicharan, P. Akhil, A novel model for emotion detection with multilayer perceptron neural network. Proceedings—2022 6th International Conference on Intelligent Computing and Control Systems, ICICCS 2022 1126–1131 (2022) doi:https://doi.org/10.1109/ICICCS53718.2022.9788269.
V.S. Nallanthighal, A. Härmä, H. Strik, Detection of COPD exacerbation from speech: comparison of acoustic features and deep learning based speech breathing models. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 2022-May, 2505–2509 (2022).
S. Suman, K.S. Sahoo, C. Das, N.Z. Jhanjhi, A. Mitra, Visualization of Audio Files Using Librosa (Springer Nature Singapore, Singapore, 2022), pp.409–418. https://doi.org/10.1007/978-981-19-0182-9_41
M. Tomprou, Y.J. Kim, P. Chikersal, A.W. Woolley, L.A. Dabbish, Speaking out of turn: How video conferencing reduces vocal synchrony and collective intelligence. PLoS ONE 16, e0247655 (2021)
Y.H.H. Tsai et al., Multimodal transformer for unaligned multimodal language sequences. Proc. Conf. Assoc. Comput. Linguist. Meet. 2019, 6558 (2019)
J. Krzywanski et al., Multi-stream convolution-recurrent neural networks based on attention mechanism fusion for speech emotion recognition. Entropy 24, 1025 (2022)
C. Zhang, L. Xue, Autoencoder with emotion embedding for speech emotion recognition. IEEE Access 9, 51231–51241 (2021)
S.M. Mustaqeem, S. Kwon, Optimal feature selection based speech emotion recognition using two-stream deep convolutional neural network. Int. J. Intell. Syst. 36, 5116–5135 (2021)
N. Senthilkumar, S. Karpakam, M. Gayathri Devi, R. Balakumaresan, P. Dhilipkumar, Speech emotion recognition based on Bi-directional LSTM architecture and deep belief networks. Mater. Today Proc. (2022). https://doi.org/10.1016/j.matpr.2021.12.246
B. Maji, M. Swain, M. Mustaqeem, Advanced fusion-based speech emotion recognition system using a dual-attention mechanism with conv-caps and bi-GRU features. Electronics 11, 1328 (2022)
M. Rayhan Ahmed, S. Islam, A.K.M. Muzahidul Islam, S. Shatabda, An ensemble 1D-CNN-LSTM-GRU model with data augmentation for speech emotion recognition. Expert Syst. Appl. 218, 119633 (2023)
Y.L. Prasanna, Y. Tarakaram, Y. Mounika, S. Palaniswamy, S. Vekkot, Comparative deep network analysis of speech emotion recognition models using data augmentation. Int. Conf. Disruptive Technol. Multi-Discipl. Res. Appl. 2, 185–190 (2023). https://doi.org/10.1109/CENTCON56610.2022.10051557
P. Jackson, S. Haq, Surrey Audio-Visual Expressed Emotion (Savee) Database (University of Surrey, Guildford, 2014)
F. Burkhardt, A. Paeschke, M. Rolfes, W.F. Sendlmeier, B. Weiss, A database of German emotional speech. In INTERSPEECH (2005).
Gournay P, O. Lahaie, R. Lefebvre, A Canadian French emotional speech dataset. Proc. 9th ACM Multimed. Syst. Conf. (2018). https://doi.org/10.5281/ZENODO.1478765
S. Goel, H. Beigi, Cross lingual cross corpus speech emotion recognition. arXiv preprint (2020). https://doi.org/10.48550/arxiv.2003.07996
S.R. Krothapalli, Koolagudi, S. G. Emotion Recognition Using Vocal Tract Information. in 67–78 (2013). doi:https://doi.org/10.1007/978-1-4614-5143-3_4.
K.S. Rao, K.E. Manjunath, Speech Recognition Using Articulatory and Excitation Source Features (Springer International Publishing, Cham, 2017). https://doi.org/10.1007/978-3-319-49220-9
S. Guha et al., Hybrid feature selection method based on harmony search and naked mole-rat algorithms for spoken language identification from audio signals. IEEE Access 8, 182868–182887 (2020)
M. Müller, D.P.W. Ellis, A. Klapuri, G. Richard, Signal processing for music analysis. IEEE J. Sel. Top. Sign. Proces. 5, 1088–1110 (2011)
A. Lerch, An Introduction to Audio Content Analysis: Applications in Signal Processing and Music Informatics (Wiley, New York, 2012)
J. Brownlee, Data Preparation for Machine Learning: Data Cleaning, Feature Selection, and Data Transforms in Python. (2020).
J. Brownlee, Imbalanced Classification with Python—Choose Better Metrics, Balance Skewed Classes, and Apply Cost-Sensitive Learning. Machine Learning Mastery (2020).
A. Géron, Hands-on Machine Learning with Scikit-Learn, Keras and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (O’Reilly Media, Sebastopol, 2019)
L. Long, X. Zeng, Beginning deep learning with tensorflow. Begin. Deep Learn. TensorFlow (2022). https://doi.org/10.1007/978-1-4842-7915-1
F. Daneshfar, S.J. Kabudian, Speech Emotion Recognition Using a New Hybrid Quaternion-Based Echo State Network-Bilinear Filter, Proceedings - 2021 7th International Conference on Signal Processing and Intelligent Systems, ICSPIS (2021). https://doi.org/10.1109/ICSPIS54653.2021.9729337
A. Thakur, S.K. Dhull, Language-independent hyperparameter optimization based speech emotion recognition system. Int J Inform Technol 2022, 1–9 (2022). https://doi.org/10.1007/S41870-022-00996-9
J. Ancilin, A. Milton, Improved speech emotion recognition with Mel frequency magnitude coefficient. Applied Acoustics 179, 108046 (2021). https://doi.org/10.1016/J.APACOUST.2021.108046
Funding
No funding source was received.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hama Saeed, M. Improved Speech Emotion Classification Using Deep Neural Network. Circuits Syst Signal Process 42, 7357–7376 (2023). https://doi.org/10.1007/s00034-023-02446-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-023-02446-8