Energy-Weighted Multi-Band Novelty Functions for Onset Detection in Piano Music

Subramani, Krishna; Sridhar, Srivatsan; Ma, Rohit; Rao, Preeti

doi:10.1109/ncc.2018.8599955

Cited by 4 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A primeira é composta por abordagens que usam somente técnicas de processamento digital de sinais. Geralmente exploram características como a amplitude, fase e/ou frequência do sinal [12], [13]. A segunda é composta por abordagens que usam modelos ou dados estatísticos.…”

Section: Introductionunclassified

Detecção de Onsets em Notas de Músicas Instrumentais de Piano utilizando Representação Pitch e Aprendizado de Máquina

Silva,

Araujo,

Pinagé

et al. 2023

Anais Do XLI Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

Resumo-Onsets são os instantes de tempo de início dos eventos musicais em sinal de música. A sua detecção automática serve de base para diversas aplicações tais como transcrição automática de música de um ou mais instrumentos musicais, alinhamento de áudio com score e estimação do tempo da música. Este artigo descreve um sistema de detecção automática de onsets em sinais musicais de piano usando a representação tempo-frequência pitch juntamente com classificadores SVM (Support vector machine), Gradient boosting ou CNN 1D (Onedimensional convolutional neural network). Os dois primeiros possuem desempenho similares no conjunto de dados BS1. O Gradient boosting apresenta maior sensibilidade, mas com mais detecções espurias.Palavras-Chave-Recuperação de informação, SVM, boosting, CNN 1D.

show abstract

Section: Introductionunclassified

Detecção de Onsets em Notas de Músicas Instrumentais de Piano utilizando Representação Pitch e Aprendizado de Máquina

Silva,

Araujo,

Pinagé

et al. 2023

Anais Do XLI Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

show abstract

“…[4] researching different hop size widths in STFT resulted in a hop size usage of 220, resulting in an average f-measure of 76.37%. In research conducted by [5] and [6] performed calculations of onset strength operations with spectrum flux features through spectrograms without normalization, while [7] using the STFT method obtained satisfactory results by performing energy-weighted band splitting separation was able to increase recall from 85% to 94%. This study will use various feature extraction methods for the extraction of kendang sound characteristics.…”

Section: Introductionmentioning

confidence: 99%

Neural Network Backpropagation for Kendang Tunggal Tone Classification

Brata,

Darmawan

2022

kursor

View full text Add to dashboard Cite

Kendang Bali is one of the instruments incorporated in this karawitan art. Balinese kendang can be played alone, called a kendang tunggal, where this type of game has a high level of difficulty understanding the tone of the Balinese drums played because some variations of the tone have similar sounds to other tones. Knowing the tone that is in the kendang song automatically can make it easier to learn it. The first approach method used to classify the tone of a kendang tunggal song is segmentation. The onset detection method is used to segment a kendang song with a variation of the hop size parameter. The segmented tone of the punch will be classified using the Backpropagation method. Feature values of autocorrelation, ZCR, STE, RMSE, Spectral Contrast, MFCC, and Mel spectrogram will be used in the classification process. This study performed variations in hop size values in onset detection and obtained the proper configuration at a value of 110. The addition of the normalization process to the onset detection method also helps the segmentation process of kendang songs correctly. The optimal backpropagation architecture obtained is learning rate 0.9, neuron hidden layer 10, and epoch 2000 produces an accuracy of 60.92%.

show abstract

Single and Double Element Dynamic Programming Algorithm for Melody Matching

Chen

Ding

2022

2022 IEEE International Conference on Consumer Electronics (ICCE)

View full text Add to dashboard Cite

Energy-Weighted Multi-Band Novelty Functions for Onset Detection in Piano Music

Cited by 4 publications

References 10 publications

Detecção de Onsets em Notas de Músicas Instrumentais de Piano utilizando Representação Pitch e Aprendizado de Máquina

Detecção de Onsets em Notas de Músicas Instrumentais de Piano utilizando Representação Pitch e Aprendizado de Máquina

Neural Network Backpropagation for Kendang Tunggal Tone Classification

Single and Double Element Dynamic Programming Algorithm for Melody Matching

Contact Info

Product

Resources

About