---
title: "YMIR: A new Benchmark Dataset and Model for Arabic Yemeni Music Genre — AL-Makhlafi 2026"
description: "The authors build YMIR, a balanced corpus of 1,475 thirty-second clips from five Yemeni genres: Sana'ani, Hadhrami, Lahji… 98.8% accuracy. 38 references."
authors: ["Moeen AL-Makhlafi", "Abdulrahman A. AlKannad", "Eiad Almekhlafi", "Nawaf Q. Othman Ahmed Mohammed", "Saher Qaid"]
year: 2026
venue: "arXiv:2604.05011"
source: "https://arxiv.org/abs/2604.05011"
doi: "10.48550/arxiv.2604.05011"
arxiv: "2604.05011"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/al-makhlafi-2026-ymir-new-benchmark-dataset-model/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/al-makhlafi-2026-ymir-new-benchmark-dataset-model/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/11/) / YMIR: A new Benchmark Dataset and Model for Arabic Yemeni Music Genre Classification Using Convolutional Neural Networks

# YMIR: A new Benchmark Dataset and Model for Arabic Yemeni Music Genre Classification Using Convolutional Neural Networks

**Authors:** Moeen AL-Makhlafi, Abdulrahman A. AlKannad, [Eiad Almekhlafi](https://md.research.elamur.ai/free/en/authors/eiad-almekhlafi/), Nawaf Q. Othman Ahmed Mohammed and Saher Qaid · **Year:** 2026 · **Venue:** arXiv:2604.05011 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2604.05011) · [PDF](https://arxiv.org/pdf/2604.05011) · [DOI 10.48550/arxiv.2604.05011](https://doi.org/10.48550/arxiv.2604.05011) · [arXiv 2604.05011](https://arxiv.org/abs/2604.05011) · [OpenAlex](https://openalex.org/W7151881470)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Most music genre classification research targets Western collections, so regional traditions such as Yemeni music have almost no labeled data. The authors build YMIR, a balanced corpus of 1,475 thirty-second clips from five Yemeni genres: Sana'ani, Hadhrami, Lahji, Tihami and Adeni. The clips were gathered from online sources such as YouTube. Five Yemeni music experts labeled them under a structured protocol, and the reported agreement is high (Fleiss' κ = 0.85).

They also design YMCM, a CNN with five convolutional layers that reads time–frequency representations. They then run a controlled grid of 30 experiments: six audio feature types fed to five architectures (YMCM, AlexNet, VGG16, MobileNet and a plain CNN), all with the same preprocessing and stratified splits. YMCM on Mel-spectrograms scores best, at about 98.8% accuracy. The comparison also shows how the choice of features interacts with model size.

The work gives an underrepresented musical tradition its first expert-annotated benchmark and a reproducible baseline for future comparisons.

## Key points
- YMIR has 295 clips per genre (1,475 total), each 30 s, stored as 48 kHz WAV, with metadata for title, artist, genre and file name.
- A clip was kept only when at least three of the five annotators chose the same genre. Annotators could reject tracks that fit no category or leave unclear ones unlabeled.
- The six feature sets tested were Mel-spectrogram, Chroma, FilterBank, MFCC13, MFCC20 and MFCC40.
- The four comparison models were AlexNet, VGG16, MobileNet and a baseline CNN, giving 6 × 5 = 30 runs under identical settings.
- The best result was YMCM with Mel-spectrograms at 98.83% accuracy.

## Interesting ideas
- The paper accepts a label only when a clear majority of independent judges agree, and drops ambiguous items rather than forcing a label; this trades size for cleaner data, which suits any noisy labeling setup.
- Every representation is crossed with every architecture under one fixed preprocessing and split, so differences come from the factor under study rather than from setup drift.
- Agreement among labelers is quantified with a chance-corrected statistic before any model is trained, so the ceiling of label quality is known up front.
- The same signal is tried at several resolutions (13, 20 and 40 MFCC coefficients), which shows how richer inputs interact with model capacity.
- The corpus keeps classes balanced and uses fixed-length excerpts, which serves fair evaluation and also limits copyright exposure for the source works.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): Silver trees could keep an arc or sentence only when, say, three of five witness parsers agree, and route the rest to an LLM teacher instead of training on them.
- **I2** (learn): Evaluation could run a full grid of input variants (gold vs. predicted tags, different tokenizations) against perceptron and gparse parsers, so each component's real contribution is isolated.
- **I3** (tree): Computing κ-style agreement between witness parsers per dependency relation would show which UD relations are inherently unstable and need conversion rules or extra checks.
- **I4** (tokens): The tagger and morphology features could be swept at several granularities (e.g., suffix lengths, context window sizes) to find where extra detail stops helping a small model.
- **I5** (answer): QA sets built from fables and tales could store short, balanced excerpts with separate metadata, keeping test categories even and licensing manageable.

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

📚 Shelves (1): [🗣️ Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) · 4,876 works · 20,420.2

🧭 Topics (1): [🐪 Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 1,334 works · 2,090.4

## Cite

Cite as: Moeen AL-Makhlafi, Abdulrahman A. AlKannad, Eiad Almekhlafi, Nawaf Q. Othman Ahmed Mohammed and Saher Qaid. 2026. YMIR: A new Benchmark Dataset and Model for Arabic Yemeni Music Genre Classification Using Convolutional Neural Networks. arXiv:2604.05011.

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

```bibtex
@misc{almakhlafi2026ymir,
  title = {{YMIR: A new Benchmark Dataset and Model for Arabic Yemeni Music Genre Classification Using Convolutional Neural Networks}},
  author = {Moeen AL-Makhlafi, Abdulrahman A. AlKannad, Eiad Almekhlafi, Nawaf Q. Othman Ahmed Mohammed and Saher Qaid},
  year = {2026},
  doi = {10.48550/arxiv.2604.05011},
  eprint = {2604.05011},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2604.05011}
}
```

- [← previous Yeswa-Stories: A Three-Way Parallel Dataset of Female African Figures in Low-Web Data Languages](https://md.research.elamur.ai/free/en/papers/mamo-2026-yeswa-stories-three-way-parallel/)
- [next → Yoysef Meyer Yavets (1832–1914), Yiddish Translator of Sacred Jewish Books](https://md.research.elamur.ai/free/en/papers/hever-chybowski-2026-yoysef-meyer-yavets-18321914-yiddish/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/11/)

## References

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

1. A. Elbir and N. Aydin, “Music genre classification and music recommendation by using deep learning,” Electronics Letters, vol. 56, no. 12, pp. 627–629, 2020. [find](https://scholar.google.com/scholar?q=A%2E+Elbir+and+N%2E+Aydin%2C+%E2%80%9CMusic+genre+classification+and+music+recommendation+by+using+deep+learning%2C%E2%80%9D+Electronics+Letters%2C+vol%2E+56%2C+no%2E+12%2C+pp%2E+627%E2%80%93629%2C+2020%2E)
2. J.-J. Aucouturier and F. Pachet, “Representing musical genre: A state of the art,” Journal of New Music Research, vol. 32, no. 1, pp. 83–93, 2003. [find](https://scholar.google.com/scholar?q=J%2E%2DJ%2E+Aucouturier+and+F%2E+Pachet%2C+%E2%80%9CRepresenting+musical+genre%3A+A+state+of+the+art%2C%E2%80%9D+Journal+of+New+Music+Research%2C+vol%2E+32%2C+no%2E+1%2C+pp%2E+83%E2%80%9393%2C+2003%2E)
3. A. Elbir, H. B. Çam, M. E. İyican, B. Öztürk, and N. Aydın, “Music genre classification and recommendation by using machine learning techniques,” in 2018 Innovations in Intelligent Systems and Applications Conference (ASYU). IEEE, 2018, pp. 1–5. [find](https://scholar.google.com/scholar?q=A%2E+Elbir%2C+H%2E+B%2E+C%CC%A7am%2C+M%2E+E%2E+I%CC%87yican%2C+B%2E+O%CC%88ztu%CC%88rk%2C+and+N%2E+Ayd%C4%B1n%2C+%E2%80%9CMusic+genre+classification+and+recommendation+by+using+machine+learning+techniques%2C%E2%80%9D+in+2018+Innovations+in+Intelligent+Systems+and+App)
4. M. Serwach and B. Stasiak, “Ga-based parameterization and feature selection for automatic music genre recognition,” in Proceedings of 2016 17th International Conference Computational Problems of Electrical Engineering (CPEE), 2016. [find](https://scholar.google.com/scholar?q=M%2E+Serwach+and+B%2E+Stasiak%2C+%E2%80%9CGa%2Dbased+parameterization+and+feature+selection+for+automatic+music+genre+recognition%2C%E2%80%9D+in+Proceedings+of+2016+17th+International+Conference+Computational+Problems+of+Elect)
5. G. Tzanetakis and P. Cook, “Musical genre classification of audio signals,” IEEE Transactions on Speech and Audio Processing, vol. 10, no. 5, pp. 293–302, 2002. [find](https://scholar.google.com/scholar?q=G%2E+Tzanetakis+and+P%2E+Cook%2C+%E2%80%9CMusical+genre+classification+of+audio+signals%2C%E2%80%9D+IEEE+Transactions+on+Speech+and+Audio+Processing%2C+vol%2E+10%2C+no%2E+5%2C+pp%2E+293%E2%80%93302%2C+2002%2E)
6. E. Wold, T. Blum, D. Keislar, and J. Wheaton, “Content-based classification, search, and retrieval of audio,” IEEE Multimedia, vol. 3, no. 3, pp. 27–36, 1996. [find](https://scholar.google.com/scholar?q=E%2E+Wold%2C+T%2E+Blum%2C+D%2E+Keislar%2C+and+J%2E+Wheaton%2C+%E2%80%9CContent%2Dbased+classification%2C+search%2C+and+retrieval+of+audio%2C%E2%80%9D+IEEE+Multimedia%2C+vol%2E+3%2C+no%2E+3%2C+pp%2E+27%E2%80%9336%2C+1996%2E)
7. J. Lambert, “A historical glimpse of music in yemen in the 1930s: The cylinders recorded by hans helfritz,” The World of Music (new series), vol. 9, no. 2, pp. 49–66, 2020. [Online]. Available: [https://journals.uni-goettingen.de/wom/article/view/1426](https://journals.uni-goettingen.de/wom/article/view/1426) [↗](https://journals.uni-goettingen.de/wom/article/view/1426)
8. G. Lavin, “Music in colonial aden: Globalization, cultural politics and the record industry in an indian ocean port city, c. 1937–1960,” SOAS Musicology Series, 2020. [Online]. Available: [https://www.academia.edu/73304097](https://www.academia.edu/73304097) [↗](https://www.academia.edu/73304097)
9. J. A. Ahmed, From the Yemeni Music Scene. Cultural Affairs Publishing House, 2007. [find](https://scholar.google.com/scholar?q=J%2E+A%2E+Ahmed%2C+From+the+Yemeni+Music+Scene%2E+Cultural+Affairs+Publishing+House%2C+2007%2E)
10. M. Altwaiji, “Cultural heritage of yemeni folk song: The importance of singing,” International Journal of Sociology and Political Science, vol. 6, no. 1, 2024. [Online]. Available: [https://www.sociologyjournal.in/assets/archives/2024/vol6issue1/6001.pdf](https://www.sociologyjournal.in/assets/archives/2024/vol6issue1/6001.pdf) [↗](https://www.sociologyjournal.in/assets/archives/2024/vol6issue1/6001.pdf)
11. UNESCO, “Al-ghina al-san’ani, traditional sanaa-style singing,” [https://ich.unesco.org/en/RL/](https://ich.unesco.org/en/RL/) al-ghina-al-sanani-traditional-sanaa-style-singing-00161, 2003. [↗](https://ich.unesco.org/en/RL/)
12. H. Ding, L. Zhai, C. Zhao, F. Wang, G. Wang, W. Xi, Z. Wang, and J. Zhao, “Genre classification empowered by knowledge-embedded music representation,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 2764–2776, 2024. [find](https://scholar.google.com/scholar?q=H%2E+Ding%2C+L%2E+Zhai%2C+C%2E+Zhao%2C+F%2E+Wang%2C+G%2E+Wang%2C+W%2E+Xi%2C+Z%2E+Wang%2C+and+J%2E+Zhao%2C+%E2%80%9CGenre+classification+empowered+by+knowledge%2Dembedded+music+representation%2C%E2%80%9D+IEEE%2FACM+Transactions+on+Audio%2C+Speech%2C+and+Langu)
13. O. E. Oguike and M. Primus, “Multimodal music genre classification of sotho-tswana musical videos,” IEEE Access, 2025. [find](https://scholar.google.com/scholar?q=O%2E+E%2E+Oguike+and+M%2E+Primus%2C+%E2%80%9CMultimodal+music+genre+classification+of+sotho%2Dtswana+musical+videos%2C%E2%80%9D+IEEE+Access%2C+2025%2E)
14. J. Shen and G. Xiao, “Music genre classification based on functional data analysis,” IEEE Access, 2024. [find](https://scholar.google.com/scholar?q=J%2E+Shen+and+G%2E+Xiao%2C+%E2%80%9CMusic+genre+classification+based+on+functional+data+analysis%2C%E2%80%9D+IEEE+Access%2C+2024%2E)
15. M. Ahmed, U. Rozario, M. M. Kabir, Z. Aung, J. Shin, and M. Mridha, “Musical genre classification using advanced audio analysis and deep learning techniques,” IEEE Open Journal of the Computer Society, 2024. [find](https://scholar.google.com/scholar?q=M%2E+Ahmed%2C+U%2E+Rozario%2C+M%2E+M%2E+Kabir%2C+Z%2E+Aung%2C+J%2E+Shin%2C+and+M%2E+Mridha%2C+%E2%80%9CMusical+genre+classification+using+advanced+audio+analysis+and+deep+learning+techniques%2C%E2%80%9D+IEEE+Open+Journal+of+the+Computer+Society)
16. T. C. Ba, T. D. T. Le, and L. T. Van, “Music genre classification using deep neural networks and data augmentation,” Entertainment Computing, vol. 53, p. 100929, 2025. [find](https://scholar.google.com/scholar?q=T%2E+C%2E+Ba%2C+T%2E+D%2E+T%2E+Le%2C+and+L%2E+T%2E+Van%2C+%E2%80%9CMusic+genre+classification+using+deep+neural+networks+and+data+augmentation%2C%E2%80%9D+Entertainment+Computing%2C+vol%2E+53%2C+p%2E+100929%2C+2025%2E)
17. T. Li, “Optimizing the configuration of deep learning models for music genre classification,” Heliyon, p. e24892, 2024. [find](https://scholar.google.com/scholar?q=T%2E+Li%2C+%E2%80%9COptimizing+the+configuration+of+deep+learning+models+for+music+genre+classification%2C%E2%80%9D+Heliyon%2C+p%2E+e24892%2C+2024%2E)
18. P. Wu, W. Gao, Y. Chen, F. Xu, Y. Ji, J. Tu, and H. Lin, “An improved vit model for music genre classification based on mel spectrogram,” PLOS ONE, vol. 20, no. 3, p. e0319027, 2025. [find](https://scholar.google.com/scholar?q=P%2E+Wu%2C+W%2E+Gao%2C+Y%2E+Chen%2C+F%2E+Xu%2C+Y%2E+Ji%2C+J%2E+Tu%2C+and+H%2E+Lin%2C+%E2%80%9CAn+improved+vit+model+for+music+genre+classification+based+on+mel+spectrogram%2C%E2%80%9D+PLOS+ONE%2C+vol%2E+20%2C+no%2E+3%2C+p%2E+e0319027%2C+2025%2E)
19. 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%2C+%E2%80%9CFree%2Dmarginal+multirater+kappa+%28multirater+k+%5Bfree%5D%29%3A+An+alternative+to+fleiss%E2%80%99+fixed%2Dmarginal+multirater+kappa%2C%E2%80%9D+Online+submission%2C+2005%2E)
20. S. Chillara, A. Kavitha, S. A. Neginhal, S. Haldia, and K. Vidyul-latha, “Music genre classification using machine learning algorithms: a comparison,” International Research Journal of Engineering and Technology, vol. 6, no. 5, pp. 851–858, 2019. [find](https://scholar.google.com/scholar?q=S%2E+Chillara%2C+A%2E+Kavitha%2C+S%2E+A%2E+Neginhal%2C+S%2E+Haldia%2C+and+K%2E+Vidyul%2Dlatha%2C+%E2%80%9CMusic+genre+classification+using+machine+learning+algorithms%3A+a+comparison%2C%E2%80%9D+International+Research+Journal+of+Engineering+and)
21. A. Dhall, Y. S. Murthy, and S. G. Koolagudi, “Music genre classification with convolutional neural networks and comparison with f, q, and mel spectrogram-based images,” in Advances in Speech and Music Technology. Springer, 2021, pp. 235–248. [find](https://scholar.google.com/scholar?q=A%2E+Dhall%2C+Y%2E+S%2E+Murthy%2C+and+S%2E+G%2E+Koolagudi%2C+%E2%80%9CMusic+genre+classification+with+convolutional+neural+networks+and+comparison+with+f%2C+q%2C+and+mel+spectrogram%2Dbased+images%2C%E2%80%9D+in+Advances+in+Speech+and+Music)
22. H. Tang and N. Chen, “Combining cnn and broad learning for music classification,” IEICE Transactions on Information and Systems, vol. 103, no. 3, pp. 695–701, 2020. [find](https://scholar.google.com/scholar?q=H%2E+Tang+and+N%2E+Chen%2C+%E2%80%9CCombining+cnn+and+broad+learning+for+music+classification%2C%E2%80%9D+IEICE+Transactions+on+Information+and+Systems%2C+vol%2E+103%2C+no%2E+3%2C+pp%2E+695%E2%80%93701%2C+2020%2E)
23. A. Ghildiyal, K. Singh, and S. Sharma, “Music genre classification using machine learning,” in 2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA). IEEE, 2020, pp. 1368–1372. [find](https://scholar.google.com/scholar?q=A%2E+Ghildiyal%2C+K%2E+Singh%2C+and+S%2E+Sharma%2C+%E2%80%9CMusic+genre+classification+using+machine+learning%2C%E2%80%9D+in+2020+4th+International+Conference+on+Electronics%2C+Communication+and+Aerospace+Technology+%28ICECA%29%2E+IEEE%2C+2)
24. H. Fayek, “Speech processing for machine learning: Filter banks, mel-frequency cepstral coefficients (mfccs) and what’s in-between,” URL: [https://haythamfayek.com/2016/04/21/speech-processingfor-machine-learning](https://haythamfayek.com/2016/04/21/speech-processingfor-machine-learning). html, 2016. [↗](https://haythamfayek.com/2016/04/21/speech-processingfor-machine-learning)
25. X. Zhang, N. Li, and W. Li, “Verification for robustness of chroma feature,” Computer Science, p. S1, 2014. [find](https://scholar.google.com/scholar?q=X%2E+Zhang%2C+N%2E+Li%2C+and+W%2E+Li%2C+%E2%80%9CVerification+for+robustness+of+chroma+feature%2C%E2%80%9D+Computer+Science%2C+p%2E+S1%2C+2014%2E)
26. M. Singh, S. K. Jha, B. Singh, and B. Rajput, “Deep learning neural networks for music information retrieval,” in 2021 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE). IEEE, 2021, pp. 500–503. [find](https://scholar.google.com/scholar?q=M%2E+Singh%2C+S%2E+K%2E+Jha%2C+B%2E+Singh%2C+and+B%2E+Rajput%2C+%E2%80%9CDeep+learning+neural+networks+for+music+information+retrieval%2C%E2%80%9D+in+2021+International+Conference+on+Computational+Intelligence+and+Knowledge+Economy+%28ICC)
27. S. Pulipati, C. P. Sai, K. S. Krishna, and C. Akhil, “Music genre classification using convolutional neural networks,” Design Engineering, pp. 2727–2732, 2021. [find](https://scholar.google.com/scholar?q=S%2E+Pulipati%2C+C%2E+P%2E+Sai%2C+K%2E+S%2E+Krishna%2C+and+C%2E+Akhil%2C+%E2%80%9CMusic+genre+classification+using+convolutional+neural+networks%2C%E2%80%9D+Design+Engineering%2C+pp%2E+2727%E2%80%932732%2C+2021%2E)
28. M. A. Kızrak, K. S. Bayram, and B. Bolat, “Classification of classic turkish music makams,” in 2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings. IEEE, 2014, pp. 394–397. [find](https://scholar.google.com/scholar?q=M%2E+A%2E+K%C4%B1zrak%2C+K%2E+S%2E+Bayram%2C+and+B%2E+Bolat%2C+%E2%80%9CClassification+of+classic+turkish+music+makams%2C%E2%80%9D+in+2014+IEEE+International+Symposium+on+Innovations+in+Intelligent+Systems+and+Applications+%28INISTA%29+Proceed)
29. R. Thiruvengatanadhan, “Music genre classification using mfcc and aann,” International Research Journal of Engineering and Technology (IRJET), 2018. [find](https://scholar.google.com/scholar?q=R%2E+Thiruvengatanadhan%2C+%E2%80%9CMusic+genre+classification+using+mfcc+and+aann%2C%E2%80%9D+International+Research+Journal+of+Engineering+and+Technology+%28IRJET%29%2C+2018%2E)
30. P. Mandal, I. Nath, N. Gupta, K. Jha Madhav, G. Ganguly Dev, and S. Pal, “Automatic music genre detection using artificial neural networks,” Intelligent Computing in Engineering, pp. 17–24, 2020. [find](https://scholar.google.com/scholar?q=P%2E+Mandal%2C+I%2E+Nath%2C+N%2E+Gupta%2C+K%2E+Jha+Madhav%2C+G%2E+Ganguly+Dev%2C+and+S%2E+Pal%2C+%E2%80%9CAutomatic+music+genre+detection+using+artificial+neural+networks%2C%E2%80%9D+Intelligent+Computing+in+Engineering%2C+pp%2E+17%E2%80%9324%2C+2020%2E)
31. A. K. Sharma, G. Aggarwal, S. Bhardwaj, P. Chakrabarti, T. Chakrabarti, J. H. Abawajy et al., “Classification of indian classical music with time-series matching deep learning approach,” IEEE Access, vol. 9, pp. 102 041–102 052, 2021. [find](https://scholar.google.com/scholar?q=A%2E+K%2E+Sharma%2C+G%2E+Aggarwal%2C+S%2E+Bhardwaj%2C+P%2E+Chakrabarti%2C+T%2E+Chakrabarti%2C+J%2E+H%2E+Abawajy+et+al%2E%2C+%E2%80%9CClassification+of+indian+classical+music+with+time%2Dseries+matching+deep+learning+approach%2C%E2%80%9D+IEEE+Access%2C+)
32. M. A. Bartsch and G. H. Wakefield, “To catch a chorus: Using chroma-based representations for audio thumbnailing,” in Proceedings of the 2001 IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics (Cat. No. 01TH8575). IEEE, 2001, pp. 15–18. [find](https://scholar.google.com/scholar?q=M%2E+A%2E+Bartsch+and+G%2E+H%2E+Wakefield%2C+%E2%80%9CTo+catch+a+chorus%3A+Using+chroma%2Dbased+representations+for+audio+thumbnailing%2C%E2%80%9D+in+Proceedings+of+the+2001+IEEE+Workshop+on+the+Applications+of+Signal+Processing+to+)
33. J. Dutta and D. Chanda, “Music emotion recognition in assamese songs using mfcc features and mlp classifier,” in 2021 International Conference on Intelligent Technologies (CONIT). IEEE, 2021, pp. 1–5. [find](https://scholar.google.com/scholar?q=J%2E+Dutta+and+D%2E+Chanda%2C+%E2%80%9CMusic+emotion+recognition+in+assamese+songs+using+mfcc+features+and+mlp+classifier%2C%E2%80%9D+in+2021+International+Conference+on+Intelligent+Technologies+%28CONIT%29%2E+IEEE%2C+2021%2C+pp%2E+1%E2%80%935%2E)
34. A. X. Glittas, L. Gopalakrishnan et al., “A low latency modular-level deeply integrated mfcc feature extraction architecture for speech recognition,” Integration, vol. 76, pp. 69–75, 2021. [find](https://scholar.google.com/scholar?q=A%2E+X%2E+Glittas%2C+L%2E+Gopalakrishnan+et+al%2E%2C+%E2%80%9CA+low+latency+modular%2Dlevel+deeply+integrated+mfcc+feature+extraction+architecture+for+speech+recognition%2C%E2%80%9D+Integration%2C+vol%2E+76%2C+pp%2E+69%E2%80%9375%2C+2021%2E)
35. T. L. Li and A. B. Chan, “Genre classification and the invariance of mfcc features to key and tempo,” in International Conference on MultiMedia Modeling. Springer, 2011, pp. 317–327. [find](https://scholar.google.com/scholar?q=T%2E+L%2E+Li+and+A%2E+B%2E+Chan%2C+%E2%80%9CGenre+classification+and+the+invariance+of+mfcc+features+to+key+and+tempo%2C%E2%80%9D+in+International+Conference+on+MultiMedia+Modeling%2E+Springer%2C+2011%2C+pp%2E+317%E2%80%93327%2E)
36. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Advances in neural information processing systems, vol. 25, 2012. [find](https://scholar.google.com/scholar?q=A%2E+Krizhevsky%2C+I%2E+Sutskever%2C+and+G%2E+E%2E+Hinton%2C+%E2%80%9CImagenet+classification+with+deep+convolutional+neural+networks%2C%E2%80%9D+Advances+in+neural+information+processing+systems%2C+vol%2E+25%2C+2012%2E)
37. A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: Efficient convolutional neural networks for mobile vision applications,” arXiv preprint arXiv:1704.04861, 2017. [↗](https://arxiv.org/abs/1704.04861) [our card](https://md.research.elamur.ai/free/en/papers/howard-2017-mobilenets-efficient-convolutional-neural-networks/)
38. B. McFee, C. Raffel, D. Liang, D. P. Ellis, M. McVicar, E. Battenberg, and O. Nieto, “librosa: Audio and music signal analysis in python.” SciPy, vol. 2015, pp. 18–24, 2015. [find](https://scholar.google.com/scholar?q=B%2E+McFee%2C+C%2E+Raffel%2C+D%2E+Liang%2C+D%2E+P%2E+Ellis%2C+M%2E+McVicar%2C+E%2E+Battenberg%2C+and+O%2E+Nieto%2C+%E2%80%9Clibrosa%3A+Audio+and+music+signal+analysis+in+python%2E%E2%80%9D+SciPy%2C+vol%2E+2015%2C+pp%2E+18%E2%80%9324%2C+2015%2E)