AUDD: Audio Urdu Digits Dataset for Automatic Audio Urdu Digit Recognition
Source abstract
Abstract
The ongoing development of audio datasets for numerous languages has spurred research activities towards designing smart speech recognition systems. A typical speech recognition system can be applied in many emerging applications, such as smartphone dialing, airline reservations, and automatic wheelchairs, among others. Urdu is a national language of Pakistan and is also widely spoken in many other South Asian countries (e.g., India, Afghanistan). Therefore, we present a comprehensive dataset of spoken Urdu digits ranging from 0 to 9. Our dataset has 25,518 sound samples that are collected from 740 participants. To test the proposed dataset, we apply different existing classification algorithms on the datasets including Support Vector Machine (SVM), Multilayer Perceptron (MLP), and flavors of the EfficientNet. These algorithms serve as a baseline. Furthermore, we propose a convolutional neural network (CNN) for audio digit classification. We conduct the experiment using these networks, and the results show that the proposed CNN is efficient and outperforms the baseline algorithms in terms of classification accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Music and Audio Processing · Speech and Audio Processing · Speech Recognition and Synthesis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
ADAPT & Lero Research Centres, School of Computing, Dublin City University, Dublin 9, Ireland
Department of Software Engineering, School of Computing, National University of Computer and Emerging Sciences, Islamabad 44000, Pakistan
References (44)
Show source-provided references
1. Imagenet large scale visual recognition challenge10.1007/s11263-015-0816-y ↗
2. Khan, L., Saad, W., Han, Z., and Hong, C. (2020). Dispersed federated learning: Vision, taxonomy, and future directions. arXiv.10.1109/MWC.011.2100003 ↗
3. Federated learning for internet of things: Recent advances, taxonomy, and open challenges10.1109/COMST.2021.3090430 ↗
4. Kowsari, K., Jafari Meimandi, K., Heidarysafa, M., Mendu, S., Barnes, L., and Brown, D. (2019). Text classification algorithms: A survey. Information, 10.10.3390/info10040150 ↗
5. Techniques for text classification: Literature review and current trends
6. Piczak, K. (2015, January 17–20). Environmental sound classification with convolutional neural networks. Proceedings of the 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP), Boston, MA, USA.10.1109/MLSP.2015.7324337 ↗
7. Diez Gaspon, I., Saratxaga, I., and Ipiña, K. (2019, January 16–19). Deep Learning For Natural Sound Classification. Proceedings of the INTER-NOISE and NOISE-CON Congress and Conference Proceedings, Madrid, Spain.
8. Lu, H., Zhang, H., and Nayak, A. (2020). A deep neural network for audio classification with a classifier attention mechanism. arXiv.
9. Heaton, J. (2020). Applications of deep neural networks. arXiv.
10. Meng, J., Zhang, J., and Zhao, H. (2020, January 17–19). Overview of the speech recognition technology. Proceedings of the 2012 Fourth International Conference on Computational And Information Sciences, Chongqing, China.10.1109/ICCIS.2012.202 ↗
11. Ali, H., Ahmad, N., and Hafeez, A. (2016, January 2–5). Urdu speech corpus and preliminary results on speech recognition. Proceedings of the International Conference on Engineering Applications of Neural Networks, Aberdeen, UK.10.1007/978-3-319-44188-7_24 ↗
12. Ashraf, J., Iqbal, N., Khattak, N., and Zaidi, A. (2010, January 28–30). Speaker independent Urdu speech recognition using HMM. Proceedings of the 2010 the 7th International Conference on Informatics And Systems (INFOS), Cairo, Egypt.
13. Ahad, A., Fayyaz, A., and Mehmood, T. (2002, January 16–17). Speech recognition using multilayer perceptron. Proceedings of the IEEE Students Conference (ISCON’02 Proceedings), Lahore, Pakistan.
14. Sarfraz, H., Hussain, S., Bokhari, R., Raza, A., Ullah, I., Sarfraz, Z., Pervez, S., Mustafa, A., Javed, I., and Parveen, R. (2010, January 24). Speech corpus development for a speaker independent spontaneous Urdu speech recognition system. Proceedings of the O-COCOSDA, Kathmandu, Nepal.
15. Raza, A., Hussain, S., Sarfraz, H., Ullah, I., and Sarfraz, Z. (2009, January 10–12). Design and development of phonetically rich Urdu speech corpus. Proceedings of the 2009 Oriental COCOSDA International Conference on Speech Database and Assessments, Urumqi, China.10.1109/ICSDA.2009.5278380 ↗
16. Akram, M., and Arif, M. (2004, January 24–26). Design of an Urdu Speech Recognizer based upon acoustic phonetic modeling approach. Proceedings of the 8th International Multitopic Conference, (Proceedings of INMIC 2004), Lahore, Pakistan.
17. Hasnain, S., and Awan, M. (2008, January 25–26). Recognizing spoken Urdu numbers using fourier descriptor and neural networks with Matlab. Proceedings of the 2008 Second International Conference on Electrical Engineering, Lahore, Pakistan.10.1109/ICEE.2008.4553937 ↗
18. Ittoo, A., Bouma, G., Maruster, L., and Wortmann, H. (2010, January 23–25). Extracting meronymy relationships from domain-specific, textual corporate databases. Proceedings of the International Conference on Application of Natural Language to Information Systems, Cardiff, UK.10.1007/978-3-642-13881-2_5 ↗
19. DWT features performance analysis for automatic speech recognition of Urdu10.1186/2193-1801-3-204 ↗
20. Faisal, M., and Manzoor, S. (2018). Deep learning for lip reading using audio-visual information for urdu language. arXiv.
21. Automatic speech recognition of Urdu digits with optimal classification approach
22. Azam, S., Mansoor, Z., Mughal, M., and Mohsin, S. (2007, January 14–17). Urdu spoken digits recognition using classified MFCC and backpropgation neural network. Proceedings of the Computer Graphics, Imaging and Visualisation (CGIV 2007), Bangkok, Thailand.10.1109/CGIV.2007.85 ↗
23. Long short-term memory recurrent neural network architectures for Urdu acoustic modeling10.1007/s10772-018-09573-7 ↗
24. Messer, K., Matas, J., Kittler, J., Jonsson, K., Luettin, J., and Maître, G. (1999, January 22–23). XM2VTSDB: The extended M2VTS database. Proceedings of the Second International Conference on Audio and Video-Based Biometric Person Authentication, Washington, DC, USA.
25. Bailly-Bailliére, E., Bengio, S., Bimbot, F., Hamouz, M., Kittler, J., Mariéthoz, J., Matas, J., Messer, K., Popovici, V., and Porée, F. (2003, January 9–11). The BANCA database and evaluation protocol. Proceedings of the International Conference on Audio-and Video-Based Biometric Person Authentication, Guildford, UK.10.1007/3-540-44887-X_74 ↗
26. Abhilash, J., and Rathna, G.N. (2019, January 14–16). Visual speech recognition for isolated digits using discrete cosine transform and local binary pattern features. Proceedings of the 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Montreal, QC, Canada.
27. Brahme, A., and Bhadade, U. (2017, January 5–8). Marathi digit recognition using lip geometric shape features and dynamic time warping. Proceedings of the TENCON 2017—2017 IEEE Region 10 Conference, Penang, Malaysia.10.1109/TENCON.2017.8227999 ↗
28. Wazir, A.S.M.B.A., and Chuah, H.J. (2019, January 29). Spoken arabic digits recognition using deep learning. Proceedings of the 2019 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS), Selangor, Malaysia.
29. Dalsaniya, N., Mankad, S.H., Garg, S., and Shrivastava, D. (2019, January 18–21). Development of a novel database in Gujarati language for spoken digits classification. Proceedings of the International Symposium on Signal Processing and Intelligent Recognition Systems, Trivandrum, India.10.1007/978-981-15-4828-4_18 ↗
30. McFee, B., Raffel, C., Liang, D., Ellis, D., McVicar, M., Battenberg, E., and Nieto, O. (2015, January 6–12). librosa: Audio and music signal analysis in python. Proceedings of the 14th Python in Science Conference, Austin, TX, USA.10.25080/Majora-7b98e3ed-003 ↗
31. Multiclass and binary SVM classification: Implications for training and classification users10.1109/LGRS.2008.915597 ↗
32. MLP neural network based gas classification system on Zynq SoC10.1109/ACCESS.2016.2619181 ↗
33. Tan, M., and Le, Q. (2019, January 9–15). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach Convention & Entertainment Center, Long Beach, CA, USA.
34. Oo, M., and Oo, L. (2019, January 29–31). Fusion of Log-Mel Spectrogram and GLCM feature in acoustic scene classification. Proceedings of the International Conference on Software Engineering Research, Management and Applications, Honolulu, HI, USA.10.1007/978-3-030-24344-9_11 ↗
35. Mel frequency cepstral coefficients (MFCC) feature extraction enhancement in the application of speech recognition: A comparison study
36. The OpenCV Library
37. Scikit-learn: Machine Learning in Python
38. Buitinck, L., Louppe, G., Blondel, M., Pedregosa, F., Mueller, A., Grisel, O., Niculae, V., Prettenhofer, P., Gramfort, A., and Grobler, J. (2013, January 23–27). API design for machine learning software: Experiences from the scikit-learn project. Proceedings of the ECML PKDD Workshop: Languages for Data Mining and Machine Learning, Prague, Czech Republic.
39. Chollet, F., Rahman, F., Zhu, Q.S., Lee, T., Marmiesse, G.D., Zabluda, O., Pumperla, M., Santana, E., McColgan, T., and Snelgrove, X. (2021, July 20). Available online: https://github.com/fchollet/keras.
40. Kingma, D., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
41. Nasr, S., Quwaider, M., and Qureshi, R. (2021, January 14–15). Text-independent Speaker Recognition using Deep Neural Networks. Proceedings of the 2021 International Conference on Information Technology (ICIT), Amman, Jordan.10.1109/ICIT52682.2021.9491705 ↗
42. Jackson, Z., Souza, C., Flaks, J., Pan, Y., Nicolas, H., and Thite, A. (2021, September 03). Jakobovski/Free-Spoken-Digit-Dataset: V1. 0.8. Available online: https://zenodo.org/record/1342401#.YUdDMLhKjIV.
43. (2021, September 08). Oscar, CNNDigitReco-Speakerindependent 2020. Available online: https://www.kaggle.com/saztorralba/cnndigitreco-speakerindependent.
44. (2021, September 13). Inam Ul Haq, Classification on FSDD Using Spectograms. Available online: https://www.kaggle.com/iinaam/classification-on-fsdd-using-spectograms Inam ur Rehman.