PurposeDue to the continuous and rapid evolution of telecommunication equipment, the demand for more efficient and noise-robust detection of dual-tone multi-frequency (DTMF) signals is most significant.Design/methodology/approachA novel machine learning-based approach to detect DTMF tones affected 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 that estimates the absolute discrete Fourier transform (DFT) coefficient values for the fundamental DTMF frequencies with or without considering their second 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 the inclusion of second harmonic frequency DFT coefficient values as features.FindingsIt is found that the model which is trained using the augmented data set and additionally includes the absolute DFT values of the second harmonic frequency values for the eight fundamental DTMF frequencies as the features, achieved the best performance with a macro classification F1 score of 0.980835, a five-fold stratified cross-validation accuracy of 98.47% and test data set detection accuracy of 98.1053%.Originality/valueThe generated DTMF signal has been classified and detected using the proposed KNN classifier which utilizes the DFT coefficient along with second harmonic frequencies for better classification. Additionally, the proposed KNN classifier has been compared with existing models to ascertain its superiority and proclaim its state-of-the-art performance.
The requirement for an efficient method for noise-robust detection of Dual-tone Multi-frequency (DTMF) signals keeping in mind the continuous evolution of telecommunication equipment is conspicuous. A machine learning based approach has been proposed in this research article to detect DTMF tones under the influence of various noises and frequency variations by employing the K-Nearest Neighbor (KNN) Algorithm. In order to meet accurate classification/detection requirements for various real-world requirements, a total of four KNN models have been created and compared, and the best one proposed for real-time deployment. Two datasets have been amassed, a clean dataset without noise and a noisy augmented dataset with perturbations that are observed in telecommunication channels such as additive white gaussian noise (AWGN), amplitude attenuation, time shift/stretch etc. Mel-Frequency Cepstral Coefficients (MFCC) and Goertzel’s Algorithm (used to estimate the absolute Discrete Fourier Transform (DFT) values for the fundamental DTMF frequencies) are employed to calculate features to be fed to the KNN models. The four models differ in being trained with and without the augmented data using the two aforementioned feature extraction algorithms, namely MFCCs calculation and the Goertzel’s algorithm. The proposed models have been verified and validated with unseen noisy testing data and it was found that the proposed KNN model D outperformed all the other models with a macro recall, precision and F1 classification score of 97.7, 97.70625 and 97.70046 respectively. The proposed model is also computationally inexpensive and showcases relatively low computing time and complexity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.