Abstract
Owing to the continuous and rapid evolution of telecommunication equipment, the demand for a more efficient and noise-robust detection of Dual-tone multi-frequency (DTMF) signals is conspicuous. In this research article, a novel machine learning based approach to detect DTMF tones perturbed by noise, frequency and time variations by employing the K-Nearest Neighbour (KNN) algorithm is proposed. The features required for training the proposed KNN classifier are extracted using Goertzel’s Algorithm employed to estimate the absolute Discrete Fourier Transform (DFT) coefficient values for the fundamental DTMF frequencies with or without their secondary harmonic frequencies. The proposed KNN classifier model is configured in four different manners which differ in being trained with or without augmented data, as well as, with or without inclusion of secondary harmonic frequency DFT coefficient values as features. These models are validated with an unseen test data set created to simulate real-time noise as observed in telecommunication channels. We found that the model which is trained using the augmented dataset and additionally includes the absolute DFT values pertaining to the secondary harmonic frequency values of the eight fundamental DTMF frequencies as the features, achieved the best performance with a macro classification F1 score of 0.980835, a 5-fold stratified cross-validation accuracy of 98.47% and test dataset detection accuracy of 98.1053%. Additionally, the proposed KNN classifier has been compared with existing models to ascertain its superiority and proclaim its state-of-the-art performance. It has proven itself utterly reliable and accurate whilst being relatively lightweight.
Similar content being viewed by others
References
Ali N, Neagu D, Trundle P (2019) Evaluation of k-nearest neighbour classifier performance for heterogeneous data sets. SN Appl Sci 1:1559. https://doi.org/10.1007/s42452-019-1356-9
Bhavanam SN (2014) Goertzel algorithm based DTMF detection. Am Int J Res Sci Technol Eng Mathematics 1:6–12
Bhavanam SN Siddaiah P Reddy PR (2014) FPGA based efficient DTMF detection using Split Goertzel algorithm with optimized resource sharing approach, eleventh IEEE international conference on wireless and optical communications networks (WOCN), 1-8.
Boudraa AO, Khaldi K, Chonavel T, Hadj-Alouane MT, Komaty A (2020) Audio coding via EMD. Digital Signal Process 104:102770. https://doi.org/10.1016/j.dsp.2020.102770
Daponte P, Grimaldi D, Michaeli L (2000) Neural network and DSP based decoder for DTMF signals, proceedings of IEEE international conference on science. Measurement Technol 147(1):34–40
Deosthali AA, McCaslin SR, Evans BL (2000) A low-complexity ITU-compliant dual tone multiple frequency detector. IEEE Trans Signal Process 48(3):911–917
Esmaeilpour M, Cardinal P, Koerich AL (2020) A robust approach for securing audio classification against adversarial attacks. IEEE Trans Inform Forensics Secur 15:2147–2159
Gunawan T, Zain M, Muin F, Kartiwi M (2017) Investigation of lossless audio compression using IEEE 1857.2 advanced audio coding. Indonesian J Electric Eng Comput Sci 6:422–430
International Telecommunication Union (1993) ITU-T Recommendation Q.23, Technical features of push-button telephone sets, Fascicle VI.1, Blue Book
Joseph T Tyagi K Kumbhare DR (2019) Quantitative analysis of DTMF tone detection using DFT, FFT and Goertzel algorithm, proceedings of global conference for advancement in technology, 1-4.
Karim D, Adnen C, Salah H (2018) An optimisation of audio classification and segmentation using GASOM algorithm. Int J Adv Comput Sci Appl 09(04):143–157
Mirri S, Delnevo G, Roccetti M (2020) Is a COVID-19 second wave possible in Emilia-Romagna (Italy)? Forecasting a future outbreak with particulate pollution and machine learning. Computation 8(3):74. https://doi.org/10.3390/computation8030074
Nagi J Tiong SK Yap KS Ahmed SK (2008) Dual-tone multifrequency signal detection using support vector machines, 6th National Conference on telecommunication technologies and 2nd Malaysia conference on photonics, 350-355.
Pamuk N, Pamuk Z (2015) Dual Tone Multi Frequency (DTMF) signal generation and detection using MATLAB software. Proc UBT Int Conference 97:109–114
Pao T Liao W Chen Y (2007) Audio-visual speech recognition with weighted KNN-based classification in mandarin database, proceedings of 3rd international conference on intelligent information hiding and multimedia signal processing, 39-42
Park MJ, Lee SJ, Yoon DH (2004) Signal detection and analysis of DTMF receiver with quick Fourier transform. Proc 30th Annual Confer IEEE Indust Electronics Soc 3:2058–2064
Popovic VM (2013) Efficient decoding of digital DTMF and R2 tone signalization. Facta universitatis - series: Electronics and Energetics. 16: Doi:https://doi.org/10.2298/FUEE0303389P
Rahmani MH, Almasganj F, Seyyedsalehi SA (2018) Audio-visual feature fusion via deep neural networks for automatic speech recognition. Digital Signal Process 82:54–63
Rehman B.K., Kumar A., Mohammad S., Basha M., Venkata Siva Reddy K. (2020) Detection of DTMF by using Goertzel algorithm and optimized resource-sharing approach. In: Choudhury S., Mishra R., Mishra R., Kumar A. (eds) intelligent communication, control and devices. Advances in Intelligent Systems and Computing, 989: 851–856.
Salamon J, Bello JP (2017) Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process Lett 24(3):279–283
Satu S Nur A (2014) Classification of dual-tone multi frequency tones using Counterpropagation neural network. 1st National Conference on electrical & communication engineering and renewable energy, 66-70
Toman SH, Sahib MGB, Hussein ZH (2017) Content-based audio retrieval by using elitism GA-KNN approach. J Al-Qadisiyah Comput Sci Mathematics 9(1):153–168
Trittler SH, FA. (2009) Near optimum sampling design and an efficient algorithm for single tone frequency estimation. Digital Signal Process 19(4):628–639
Unar S, Wang X, Zhang C (2018) Visual and textual information fusion using kernel method for content based image retrieval. Information Fusion 44:176–187
Unar S, Wang X, Zhang C, Wang C (2019) Detected text-based image retrieval approach for textual images. IET Image Process 13(3):515–521
Unar S, Wang X, Wang C, Wang Y (2019) A decisive content based image retrieval approach for feature fusion in visual and textual images. Knowl-Based Syst 179:08–20
Wang X, Wang Z (2014) The method for image retrieval based on multi-factors correlation utilizing block truncation coding. Pattern Recogn 47(10):3293–3303
Wang C, Wang X, Xia Z, Zhang C (2019) Ternary radial harmonic Fourier moments based robust stereo image zero-watermarking algorithm. Inf Sci 470:109–120
Wang C, Wang X, Xia Z, Ma B, Shi YQ (2020) Image description with polar harmonic Fourier moments. IEEE Trans Circuits Syst Video Technol 30(12):4440–4452
Yang XK, Qu D, Zhang WL, Zhang WQ (2018) An adapted data selection for deep learning-based audio segmentation in multi-genre broadcast channel. Digital Signal Process 81:08–15
Yeh CY, Hwang SH (2019) Efficient detection approach for DTMF signal detection. Appl Sci 9(3). https://doi.org/10.3390/app9030422
Availability of data and material
NA
Code availability
Custom Code
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that there is no conflict of interest regarding the publication of this paper and that the work presented in this article is not supported by any funding agency.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Maity, A., Prakasam, P. & Bhargava, S. Machine learning based KNN classifier: towards robust, efficient DTMF tone detection for a Noisy environment. Multimed Tools Appl 80, 29765–29784 (2021). https://doi.org/10.1007/s11042-021-11194-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11194-3