Music Onset Detection Using Convolution Neural Network
Yagya Raj Pandey1, Prem Singh Bist1, Sudan Jha1,
Guru Technology Pvt. Ltd.
ww.gurutech.com.np | info@gurutech.com.np
Kathmandu, Nepal
Abstract. Onset detection is a primary task in audio processing for any higher-level audio processing such as music information retrieval (MIR) or automatic speech recognition (ASR). Onset detection using data driven approach is hard due to labeled data scarcity. In this work we use some in build dataset for training our convolutional neural network (CNN) work and make some test data for Nepalese traditional music. The CNN with raw waveform of input audio signal performs well in this study for onset detection. This network performs well in diversified audio type where 50 millisecond windows are set in each audio file to identify the presence or absence of onset.
Keywords: Onset detection, MIR, ASR, raw waveform
View or Download paper
Should be more interested to get this research paper, kindly contact us at research@gurutech.com.np