---
title: "A New Amharic Speech Emotion Dataset and — Retta 2022"
description: "Amharic, the national language of Ethiopia, has had no corpus for speech emotion recognition (SER)."
authors: ["Ephrem A. Retta", "Eiad Almekhlafi", "Richard Sutcliffe", "Mustafa Mhamed", "Haider Ali", "Jun Feng"]
year: 2022
venue: "arXiv:2201.02710"
source: "https://arxiv.org/abs/2201.02710"
doi: "10.48550/arxiv.2201.02710"
arxiv: "2201.02710"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/retta-2022-new-amharic-speech-emotion-dataset/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/retta-2022-new-amharic-speech-emotion-dataset/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/) / A New Amharic Speech Emotion Dataset and Classification Benchmark

# A New Amharic Speech Emotion Dataset and Classification Benchmark

**Authors:** [Ephrem A. Retta](https://md.research.elamur.ai/free/en/authors/ephrem-a-retta/), [Eiad Almekhlafi](https://md.research.elamur.ai/free/en/authors/eiad-almekhlafi/), [Richard Sutcliffe](https://md.research.elamur.ai/free/en/authors/richard-sutcliffe/), [Mustafa Mhamed](https://md.research.elamur.ai/free/en/authors/mustafa-mhamed/), Haider Ali, [Jun Feng](https://md.research.elamur.ai/free/en/authors/jun-feng/) · **Year:** 2022 · **Venue:** arXiv:2201.02710 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2201.02710) · [PDF](https://arxiv.org/pdf/2201.02710) · [DOI 10.48550/arxiv.2201.02710](https://doi.org/10.48550/arxiv.2201.02710) · [arXiv 2201.02710](https://arxiv.org/abs/2201.02710) · [OpenAlex](https://openalex.org/W4221140133)

**Citations:** 22 citations (openalex-snapshot · 2026-10-14) · [1](#cited-by) in our library, of the 140884 papers whose bibliographies we read

## Summary
Amharic, the national language of Ethiopia, has had no corpus for speech emotion recognition (SER). The authors built ASED, which they describe as the first such resource. Sixty-five native speakers recorded short emotional utterances in the four main dialects, and dialect-matched judges validated the emotion labels. The dataset is freely downloadable. On top of it the authors propose VGGb, a slimmed VGG network with four convolutional layers, and run three experiments.

The first experiment compares Mel-spectrogram and MFCC input features. It uses ordinary cross-validation plus three splits that each hold out one factor: sentences, dialect or speaker group. The second experiment benchmarks VGGb against ResNet50, Alex-Net and LSTM. In the third, VGGb is trained not only on ASED but also on two corpora in other languages, RAVDESS (English) and EMO-DB (German).

The main findings:
- MFCC beats Mel-spectrograms under every split.
- VGGb nearly matches ResNet50 in accuracy and trains far faster.
- Accuracy across the three languages stays within a narrow band.

Together these results give low-resource Amharic a usable SER baseline and a reference dataset.

## Key points
- ASED contains 2,474 clips of two to four seconds from 65 speakers. They cover Gojjam, Wollo, Shewa and Gonder dialects and five emotions: neutral 522, fearful 510, happy 486, sad 470, angry 486.
- Eight judges labelled the clips, two per dialect, and their agreement reached Fleiss kappa = 0.8.
- In the speaker-group hold-out (professional, semi-professional, amateur), MFCC averaged 76.91% accuracy against 71.57% for Mel-spectrograms. MFCC also varied less across folds (std. dev. 1.53 vs 2.50).
- Model comparison on ASED with MFCC:
  - ResNet50: 91.13% accuracy, about 8h45m training.
  - VGGb: 90.73% accuracy, about 31 min training.
  - Alex-Net: 81.82%.
  - LSTM: 66.94%.
- VGGb's accuracy by corpus was 86.15% on RAVDESS, 88.71% on EMO-DB and 90.73% on ASED. All features were extracted with librosa v0.7.2, and results are averaged over five runs.

## Interesting ideas
- The authors hold out one factor at a time (a sentence set, a dialect, a speaker group) to check that a design choice wins regardless of who spoke what; this separates true superiority from memorised surface material. — For Mova (learn): Evaluation could hold out whole genres, source treebanks or text authors when deciding between two pipeline variants, and keep only changes that win on every held-out slice.
- They report the spread across folds, not just the mean, and treat lower variance as an extra sign that one option is more robust. — For Mova (learn): Repair rules and teacher tiers could be ranked by both mean gain and its standard deviation across held-out slices, so that brittle rules are flagged early.
- Annotators are matched to the dialect they judge, and a chance-corrected agreement score certifies the labels before any model sees them. — For Mova (learn): Silver data agreed by several witness parsers could carry a Fleiss-kappa-style agreement score per sentence or per relation type, so that low-agreement material is filtered before training.
- Accuracy is weighed together with training cost: a model 0.4 points worse but many times faster is preferred as the practical default. — For Mova (tree): Comparisons between the perceptron parser and gparse could report LAS alongside training and inference time, which makes the trade-off explicit when choosing a default parser.
- The same architecture and settings are run unchanged on corpora in several languages, to show that results come from the method rather than one dataset. — For Mova (tree): After UD dialect conversion, one fixed parser configuration could be trained on several treebanks to check that gains do not depend on a single corpus's annotation habits.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

## Cited by

Cited by

1 paper of our library cites it (of the 140884 whose bibliographies we read); each has a page here.

- [Cross-Corpus Multilingual Speech Emotion Recognition: Amharic vs. Other Languages](https://md.research.elamur.ai/free/en/papers/retta-2023-cross-corpus-multilingual-speech-emotion/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{retta2022new,
  title = {{A New Amharic Speech Emotion Dataset and Classification Benchmark}},
  author = {Retta, Ephrem A. and Almekhlafi, Eiad and Sutcliffe, Richard and Mhamed, Mustafa and Ali, Haider and Feng, Jun},
  year = {2022},
  doi = {10.48550/arxiv.2201.02710},
  eprint = {2201.02710},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2201.02710}
}
```

- [← previous A Multimodal Corpus for Emotion Recognition in Sarcasm](https://md.research.elamur.ai/free/en/papers/ray-2022-multimodal-corpus-emotion-recognition-sarcasm/)
- [next → A Paradigm Change for Formal Syntax: Computational Algorithms in the Grammar of English](https://md.research.elamur.ai/free/en/papers/ninio-2022-paradigm-change-formal-syntax-computational/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/)

## References

36 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. T. Anberbir, M. Gasser, T. Takara, and K. D. Yoon. Grapheme-to-phoneme conversion for amharic text-to-speech system. In Proceedings of conference on human language technology for development, Bibliotheca Alexandrina, Alexandria, 2011. [find](https://scholar.google.com/scholar?q=T%2E+Anberbir%2C+M%2E+Gasser%2C+T%2E+Takara%2C+and+K%2E+D%2E+Yoon%2E+Grapheme%2Dto%2Dphoneme+conversion+for+amharic+text%2Dto%2Dspeech+system%2E+In+Proceedings+of+conference+on+human+language+technology+for+development%2C+Biblioth)
2. audacity. audacity, 2020. [Online; accessed 31-October-2020]. [find](https://scholar.google.com/scholar?q=audacity%2E+audacity%2C+2020%2E+%5BOnline%3B+accessed+31%2DOctober%2D2020%5D%2E)
3. S. Basu, A. Bag, M. Aftabuddin, M. Mahadevappa, J. Mukherjee, and R. Guha. Effects of emotion on physiological signals. In 2016 IEEE Annual India Conference (INDICON), pages 1–6. IEEE, 2016. [find](https://scholar.google.com/scholar?q=S%2E+Basu%2C+A%2E+Bag%2C+M%2E+Aftabuddin%2C+M%2E+Mahadevappa%2C+J%2E+Mukherjee%2C+and+R%2E+Guha%2E+Effects+of+emotion+on+physiological+signals%2E+In+2016+IEEE+Annual+India+Conference+%28INDICON%29%2C+pages+1%E2%80%936%2E+IEEE%2C+2016%2E)
4. B. Belay, T. Habtegebrial, M. Meshesha, M. Liwicki, G. Belay, and D. Stricker. Amharic ocr: An end-to-end learning. Applied Sciences, 10(3):1117, 2020. [find](https://scholar.google.com/scholar?q=B%2E+Belay%2C+T%2E+Habtegebrial%2C+M%2E+Meshesha%2C+M%2E+Liwicki%2C+G%2E+Belay%2C+and+D%2E+Stricker%2E+Amharic+ocr%3A+An+end%2Dto%2Dend+learning%2E+Applied+Sciences%2C+10%283%29%3A1117%2C+2020%2E)
5. F. Burkhardt, A. Paeschke, M. Rolfes, W. F. Sendlmeier, and B. Weiss. A database of german emotional speech. In Ninth European Conference on Speech Communication and Technology, 2005. [find](https://scholar.google.com/scholar?q=F%2E+Burkhardt%2C+A%2E+Paeschke%2C+M%2E+Rolfes%2C+W%2E+F%2E+Sendlmeier%2C+and+B%2E+Weiss%2E+A+database+of+german+emotional+speech%2E+In+Ninth+European+Conference+on+Speech+Communication+and+Technology%2C+2005%2E)
6. C. Busso, M. Bulut, C.-C. Lee, A. Kazemzadeh, E. Mower, S. Kim, J. N. Chang, S. Lee, and S. S. Narayanan. Iemocap: Interactive emotional dyadic motion capture database. Language resources and evaluation, 42(4):335– 359, 2008. [find](https://scholar.google.com/scholar?q=C%2E+Busso%2C+M%2E+Bulut%2C+C%2E%2DC%2E+Lee%2C+A%2E+Kazemzadeh%2C+E%2E+Mower%2C+S%2E+Kim%2C+J%2E+N%2E+Chang%2C+S%2E+Lee%2C+and+S%2E+S%2E+Narayanan%2E+Iemocap%3A+Interactive+emotional+dyadic+motion+capture+database%2E+Language+resources+and+evaluati)
7. K. Dupuis and M. K. Pichora-Fuller. Recognition of emotional speech for younger and older talkers: behavioural findings from the toronto emotional speech set. Canadian Acoustics, 39(3):182–183, 2011. [find](https://scholar.google.com/scholar?q=K%2E+Dupuis+and+M%2E+K%2E+Pichora%2DFuller%2E+Recognition+of+emotional+speech+for+younger+and+older+talkers%3A+behavioural+findings+from+the+toronto+emotional+speech+set%2E+Canadian+Acoustics%2C+39%283%29%3A182%E2%80%93183%2C+2011%2E)
8. D. George, H. Shen, and E. Huerta. Deep transfer learning: A new deep learning glitch classification method for advanced ligo. arXiv preprint arXiv:1706.07446, 2017. [↗](https://arxiv.org/abs/1706.07446)
9. K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. [find](https://scholar.google.com/scholar?q=K%2E+He%2C+X%2E+Zhang%2C+S%2E+Ren%2C+and+J%2E+Sun%2E+Deep+residual+learning+for+image+recognition%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+recognition%2C+pages+770%E2%80%93778%2C+2016%2E)
10. D. Issa, M. F. Demirci, and A. Yazici. Speech emotion recognition with deep convolutional neural networks. Biomedical Signal Processing and Control, 59:101894, 2020. [find](https://scholar.google.com/scholar?q=D%2E+Issa%2C+M%2E+F%2E+Demirci%2C+and+A%2E+Yazici%2E+Speech+emotion+recognition+with+deep+convolutional+neural+networks%2E+Biomedical+Signal+Processing+and+Control%2C+59%3A101894%2C+2020%2E)
11. P. Jackson and S. Haq. Surrey audio-visual expressed emotion (savee) database. University of Surrey: Guildford, UK, 2014. [find](https://scholar.google.com/scholar?q=P%2E+Jackson+and+S%2E+Haq%2E+Surrey+audio%2Dvisual+expressed+emotion+%28savee%29+database%2E+University+of+Surrey%3A+Guildford%2C+UK%2C+2014%2E)
12. L. Kerkeni, Y. Serrestou, M. Mbarki, K. Raoof, M. A. Mahjoub, and C. Cleder. Automatic speech emotion recognition using machine learning. In Social Media and Machine Learning. IntechOpen, 2019. [find](https://scholar.google.com/scholar?q=L%2E+Kerkeni%2C+Y%2E+Serrestou%2C+M%2E+Mbarki%2C+K%2E+Raoof%2C+M%2E+A%2E+Mahjoub%2C+and+C%2E+Cleder%2E+Automatic+speech+emotion+recognition+using+machine+learning%2E+In+Social+Media+and+Machine+Learning%2E+IntechOpen%2C+2019%2E)
13. R. A. Khalil, E. Jones, M. I. Babar, T. Jan, M. H. Zafar, and T. Alhussain. Speech emotion recognition using deep learning techniques: A review. IEEE Access, 7:117327–117345, 2019. [find](https://scholar.google.com/scholar?q=R%2E+A%2E+Khalil%2C+E%2E+Jones%2C+M%2E+I%2E+Babar%2C+T%2E+Jan%2C+M%2E+H%2E+Zafar%2C+and+T%2E+Alhussain%2E+Speech+emotion+recognition+using+deep+learning+techniques%3A+A+review%2E+IEEE+Access%2C+7%3A117327%E2%80%93117345%2C+2019%2E)
14. S. G. Koolagudi, R. Reddy, J. Yadav, and K. S. Rao. Iitkgp-sehsc: Hindi speech corpus for emotion analysis. In 2011 International conference on devices and communications (ICDeCom), pages 1–5. IEEE, 2011. [find](https://scholar.google.com/scholar?q=S%2E+G%2E+Koolagudi%2C+R%2E+Reddy%2C+J%2E+Yadav%2C+and+K%2E+S%2E+Rao%2E+Iitkgp%2Dsehsc%3A+Hindi+speech+corpus+for+emotion+analysis%2E+In+2011+International+conference+on+devices+and+communications+%28ICDeCom%29%2C+pages+1%E2%80%935%2E+IEEE%2C+2)
15. A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105, 2012. [find](https://scholar.google.com/scholar?q=A%2E+Krizhevsky%2C+I%2E+Sutskever%2C+and+G%2E+E%2E+Hinton%2E+Imagenet+classification+with+deep+convolutional+neural+networks%2E+In+Advances+in+neural+information+processing+systems%2C+pages+1097%E2%80%931105%2C+2012%2E)
16. H. S. Kumbhar and S. U. Bhandari. Speech emotion recognition using mfcc features and lstm network. In 2019 5th International Conference On Computing, Communication, Control And Automation (ICCUBEA), pages 1–3. IEEE, 2019. [find](https://scholar.google.com/scholar?q=H%2E+S%2E+Kumbhar+and+S%2E+U%2E+Bhandari%2E+Speech+emotion+recognition+using+mfcc+features+and+lstm+network%2E+In+2019+5th+International+Conference+On+Computing%2C+Communication%2C+Control+And+Automation+%28ICCUBEA%29%2C+p)
17. S. Kwon et al. Clstm: Deep feature-based speech emotion recognition using the hierarchical convlstm network. Mathematics, 8(12):2133, 2020. [find](https://scholar.google.com/scholar?q=S%2E+Kwon+et+al%2E+Clstm%3A+Deep+feature%2Dbased+speech+emotion+recognition+using+the+hierarchical+convlstm+network%2E+Mathematics%2C+8%2812%29%3A2133%2C+2020%2E)
18. S. Kwon et al. A cnn-assisted enhanced audio signal processing for speech emotion recognition. Sensors, 20(1):183, 2020. [find](https://scholar.google.com/scholar?q=S%2E+Kwon+et+al%2E+A+cnn%2Dassisted+enhanced+audio+signal+processing+for+speech+emotion+recognition%2E+Sensors%2C+20%281%29%3A183%2C+2020%2E)
19. Y. Li, J. Tao, L. Chao, W. Bao, and Y. Liu. Cheavd: a chinese natural emotional audio–visual database. Journal of Ambient Intelligence and Humanized Computing, 8(6):913–924, 2017. [find](https://scholar.google.com/scholar?q=Y%2E+Li%2C+J%2E+Tao%2C+L%2E+Chao%2C+W%2E+Bao%2C+and+Y%2E+Liu%2E+Cheavd%3A+a+chinese+natural+emotional+audio%E2%80%93visual+database%2E+Journal+of+Ambient+Intelligence+and+Humanized+Computing%2C+8%286%29%3A913%E2%80%93924%2C+2017%2E)
20. S. R. Livingstone and F. A. Russo. The ryerson audio-visual database of emotional speech and song (ravdess): A dynamic, multimodal set of facial and vocal expressions in north american english. PloS one, 13(5):e0196391, 2018. [find](https://scholar.google.com/scholar?q=S%2E+R%2E+Livingstone+and+F%2E+A%2E+Russo%2E+The+ryerson+audio%2Dvisual+database+of+emotional+speech+and+song+%28ravdess%29%3A+A+dynamic%2C+multimodal+set+of+facial+and+vocal+expressions+in+north+american+english%2E+PloS+o)
21. A. D. Mengistu and M. A. Bedane. Text independent amharic language dialect recognition using neuro-fuzzy gaussian membership function. International Journal of Advanced Studies in Computers, Science and Engineering, 6(6):30, 2017. [find](https://scholar.google.com/scholar?q=A%2E+D%2E+Mengistu+and+M%2E+A%2E+Bedane%2E+Text+independent+amharic+language+dialect+recognition+using+neuro%2Dfuzzy+gaussian+membership+function%2E+International+Journal+of+Advanced+Studies+in+Computers%2C+Science+a)
22. P. Molchanov, S. Tyree, T. Karras, T. Aila, and J. Kautz. Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440, 2016. [↗](https://arxiv.org/abs/1611.06440)
23. Z. Mossie and J.-H. Wang. Social network hate speech detection for amharic language. Computer Science & Information Technology, pages 41–55, 2018. [find](https://scholar.google.com/scholar?q=Z%2E+Mossie+and+J%2E%2DH%2E+Wang%2E+Social+network+hate+speech+detection+for+amharic+language%2E+Computer+Science+%26+Information+Technology%2C+pages+41%E2%80%9355%2C+2018%2E)
24. W. Mulugeta and M. Gasser. Learning morphological rules for amharic verbs using inductive logic programming. Language Technology for Normalisation of Less-Resourced Languages, 7, 2012. [find](https://scholar.google.com/scholar?q=W%2E+Mulugeta+and+M%2E+Gasser%2E+Learning+morphological+rules+for+amharic+verbs+using+inductive+logic+programming%2E+Language+Technology+for+Normalisation+of+Less%2DResourced+Languages%2C+7%2C+2012%2E)
25. M. K. Pichora-Fuller and K. Dupuis. Toronto emotional speech set (TESS), 2010. [find](https://scholar.google.com/scholar?q=M%2E+K%2E+Pichora%2DFuller+and+K%2E+Dupuis%2E+Toronto+emotional+speech+set+%28TESS%29%2C+2010%2E)
26. J. J. Randolph. Free-marginal multirater kappa (multirater k [free]): An alternative to fleiss’ fixed-marginal multirater kappa. Online submission, 2005. [find](https://scholar.google.com/scholar?q=J%2E+J%2E+Randolph%2E+Free%2Dmarginal+multirater+kappa+%28multirater+k+%5Bfree%5D%29%3A+An+alternative+to+fleiss%E2%80%99+fixed%2Dmarginal+multirater+kappa%2E+Online+submission%2C+2005%2E)
27. M. Sajjad, S. Kwon, et al. Clustering-based speech emotion recognition by incorporating learned features and deep bilstm. IEEE Access, 8:79861–79875, 2020. [find](https://scholar.google.com/scholar?q=M%2E+Sajjad%2C+S%2E+Kwon%2C+et+al%2E+Clustering%2Dbased+speech+emotion+recognition+by+incorporating+learned+features+and+deep+bilstm%2E+IEEE+Access%2C+8%3A79861%E2%80%9379875%2C+2020%2E)
28. B. W. Schuller. Speech emotion recognition: Two decades in a nutshell, benchmarks, and ongoing trends. Communications of the ACM, 61(5):90–99, 2018. [find](https://scholar.google.com/scholar?q=B%2E+W%2E+Schuller%2E+Speech+emotion+recognition%3A+Two+decades+in+a+nutshell%2C+benchmarks%2C+and+ongoing+trends%2E+Communications+of+the+ACM%2C+61%285%29%3A90%E2%80%9399%2C+2018%2E)
29. R. Sharmin, S. K. Rahut, and M. R. Huq. Bengali spoken digit classification: A deep learning approach using convolutional neural network. Procedia Computer Science, 171:1381–1388, 2020. [find](https://scholar.google.com/scholar?q=R%2E+Sharmin%2C+S%2E+K%2E+Rahut%2C+and+M%2E+R%2E+Huq%2E+Bengali+spoken+digit+classification%3A+A+deep+learning+approach+using+convolutional+neural+network%2E+Procedia+Computer+Science%2C+171%3A1381%E2%80%931388%2C+2020%2E)
30. A. Shaw, R. K. Vardhan, and S. Saxena. Emotion recognition and classification in speech using artificial neural networks. International Journal of Computer Applications, 145(8):5–9, 2016. [find](https://scholar.google.com/scholar?q=A%2E+Shaw%2C+R%2E+K%2E+Vardhan%2C+and+S%2E+Saxena%2E+Emotion+recognition+and+classification+in+speech+using+artificial+neural+networks%2E+International+Journal+of+Computer+Applications%2C+145%288%29%3A5%E2%80%939%2C+2016%2E)
31. K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014. [↗](https://arxiv.org/abs/1409.1556) [our card](https://md.research.elamur.ai/free/en/papers/simonyan-2014-very-deep-convolutional-networks-large/)
32. C. Stanislavski. An actor prepares (new york. Theatre Arts, page 38, 1936. [find](https://scholar.google.com/scholar?q=C%2E+Stanislavski%2E+An+actor+prepares+%28new+york%2E+Theatre+Arts%2C+page+38%2C+1936%2E)
33. R. N. Tak, D. M. Agrawal, and H. A. Patil. Novel phase encoded mel filterbank energies for environmental sound classification. In International Conference on Pattern Recognition and Machine Intelligence, pages 317–325. Springer, 2017. [find](https://scholar.google.com/scholar?q=R%2E+N%2E+Tak%2C+D%2E+M%2E+Agrawal%2C+and+H%2E+A%2E+Patil%2E+Novel+phase+encoded+mel+filterbank+energies+for+environmental+sound+classification%2E+In+International+Conference+on+Pattern+Recognition+and+Machine+Intelligen)
34. V. P. Tank and S. Hadia. Creation of speech corpus for emotion analysis in gujarati language and its evaluation by various speech parameters. International Journal of Electrical and Computer Engineering, 10(5):4752, 2020. [find](https://scholar.google.com/scholar?q=V%2E+P%2E+Tank+and+S%2E+Hadia%2E+Creation+of+speech+corpus+for+emotion+analysis+in+gujarati+language+and+its+evaluation+by+various+speech+parameters%2E+International+Journal+of+Electrical+and+Computer+Engineeri)
35. G. S. Tomas. Speech Emotion Recognition Using Convolutional Neural Networks. PhD thesis, Institute of Language and Communication, Technical University of Berlin, 2019. [find](https://scholar.google.com/scholar?q=G%2E+S%2E+Tomas%2E+Speech+Emotion+Recognition+Using+Convolutional+Neural+Networks%2E+PhD+thesis%2C+Institute+of+Language+and+Communication%2C+Technical+University+of+Berlin%2C+2019%2E)
36. N. Vryzas, R. Kotsakis, A. Liatsou, C. A. Dimoulas, and G. Kalliris. Speech emotion recognition for performance interaction. Journal of the Audio Engineering Society, 66(6):457–467, 2018. [find](https://scholar.google.com/scholar?q=N%2E+Vryzas%2C+R%2E+Kotsakis%2C+A%2E+Liatsou%2C+C%2E+A%2E+Dimoulas%2C+and+G%2E+Kalliris%2E+Speech+emotion+recognition+for+performance+interaction%2E+Journal+of+the+Audio+Engineering+Society%2C+66%286%29%3A457%E2%80%93467%2C+2018%2E)