HpRNet : Incorporating Residual Noise Modeling for Violin in a Variational Parametric Synthesizer

Abstract

Generative Models for Audio Synthesis have been gaining momentum in the last few years. More recently, parametric representations of the audio signal have been incorporated to facilitate better musical control of the synthesized output. In this work, we investigate a parametric model for violin tones, in particular the generative modeling of the residual bow noise to make for more natural tone quality. To aid in our analysis, we introduce a dataset of Carnatic Violin Recordings where bow noise is an integral part of the playing style of higher pitched notes in specific gestural contexts. We obtain insights about each of the harmonic and residual components of the signal, as well as their interdependence, via observations on the latent space derived in the course of variational encoding of the spectral envelopes of the sustained sounds.

arXiv commenthttps://github.com/SubramaniKrishna/HpRNet

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Tutorial on Variational Autoencoders
• Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
• Autoencoders for music sound modeling: a comparison of linear, shallow, deep, recurrent and variational models
• Generative timbre spaces: regularizing variational auto-encoders with perceptual metrics
• Real-valued parametric conditioning of an RNN for interactive sound synthesis
• VaPar Synth -- A Variational Parametric Model for Audio Synthesis

Cited by in corpus (2)

• The Ethical Implications of Generative Audio Models: A Systematic Literature Review
• CCOM-HuQin: an Annotated Multimodal Chinese Fiddle Performance Dataset