Singing Voice Melody Transcription Using Deep Neural Networks

This paper presents a system for the transcription of singing voice melodies in polyphonic music signals based on Deep Neural Network (DNN) models. In particular, a new DNN system is introduced for performing the f0 estimation of the melody, and another DNN, inspired from recent studies, is learned for segmenting vocal sequences. Preparation of the data and learning configurations related to the specificity of both tasks are described. The performance of the melody f0 estimation system is compared with a state-of-the-art method and exhibits highest accuracy through a better generalization on two different music databases. Insights into the global functioning of this DNN are proposed. Finally, an evaluation of the global system combining the two DNNs for singing voice melody transcription is presented.