Raag detection in music using supervised machine learning approach

Patel, Ekta; Chauhan, Savita

doi:10.19101/ijatee.2017.429009

Cited by 6 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to enhance the robustness of the PCP feature to the notes of piano scores played by different timbre instruments, Liang et al [ 14 ], based on the discrete cosine transform and the Mel frequency, proposed a Mel logarithmic PCP feature. A more practical type of multitone estimation method is the cyclic extraction method, which was first proposed by Patel and Chauhan [ 15 ]. Its idea is to regard the multitone signal as the superposition of multiple single-tone signals and then use a two-step loop to perform one by one estimate.…”

Section: Introductionmentioning

confidence: 99%

Recognition of Continuous Music Segments Based on the Phase Space Reconstruction Method

Huang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Piano score recognition is one of the important research contents in the field of music information retrieval, and it plays an important role in information processing. In order to reduce the influence of vocals on the progress of piano notes and restore the harmonic information corresponding to piano notes, the article models the harmonic information and vocal information corresponding to piano notes in the frequency spectrum. We use the phase space reconstruction method to extract the nonlinear feature parameters in the note audio and use some of the parameters as the training set to construct the support vector machine (SVM) classifier and the other part as the test set to test the recognition effect. Therefore, the method of adaptive signal decomposition and SVM is introduced into the signal preprocessing link, and the corresponding recognition process is established. In order to improve the performance of the support vector machine, the article uses measurement learning method to obtain the measurement learning and uses the measurement learning to replace the Euclidean distance of the Gaussian kernel function of the support vector machine. The SVM method of adaptive signal decomposition and the SVM method of principal component analysis are introduced into the preprocessing process of the note signal, and then the preprocessed signal is reconstructed in phase space, and the corresponding recognition process is established. The method of directly reconstructing the phase space of the original signal has higher accuracy and can be applied to the note recognition of continuous music segments. The final experimental results show that, compared with the current popular piano score recognition algorithm, the recognition accuracy of the proposed piano score recognition algorithm is improved by 3.5% to 12.2%.

show abstract

Section: Introductionmentioning

confidence: 99%

Recognition of Continuous Music Segments Based on the Phase Space Reconstruction Method

Huang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…A thorough study project was suggested by Ekta and Savita [9] that explores the crucial topic of rag detection methods. Their study's major goal is to provide efficient techniques for identifying and categorizing distinct kinds of rags in a variety of situations.…”

Section: Literature Surveymentioning

confidence: 99%

Acoustic Feature Identification to Recognize Rag Present in Borgit

Barthakur,

Sarma,

Baruah

2023

IJRITCC

View full text Add to dashboard Cite

In the world of Indian classical music, raga recognition is a crucial undertaking. Due to its particular sound qualities, the traditional wind instrument known as the borgit presents special difficulties for automatic raga recognition. In this research, we investigate the use of auditory feature identification methods to create a reliable raga recognition system for Borgit performances. Each of the Borgits, the devotional song of Assam is enriched with rag and each rag has unique melodious tune. This paper has carried out few experiments on the audio samples of rags and a few Borgits sung with those rugs. In this manuscript three mostly used rags and a few Borgits with these rags are considered for the experiment. Acoustic features considred here are FFT (Fast Fourier Transform), ZCR (Zero Crossing Rates), Mean and Standard deviation of pitch contour and RMS(Root Mean Square). After evaluation and analysis it is seen that FFT and ZCR are two noteworthy acoustic features that helps to identify the rag present in Borgits. At last K-means clustering was applied on the FFT and ZCR values of the Borgits and were able to find correct grouping according to rags present there. This research validates FFT and ZCR as most precise acoustic parameters for rag identification in Borgit. Here researchers had observed roles of Standard deviation of pitch contour and RMS values of the audio samples in rag identification.

show abstract