Expressive Acoustic Guitar Sound Synthesis with an Instrument-Specific Input Representation and Diffusion Outpainting

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Hounsu, Choi, Soonbeom, Nam, Juhan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916104205500416
author Kim, Hounsu
Choi, Soonbeom
Nam, Juhan
author_facet Kim, Hounsu
Choi, Soonbeom
Nam, Juhan
contents Synthesizing performing guitar sound is a highly challenging task due to the polyphony and high variability in expression. Recently, deep generative models have shown promising results in synthesizing expressive polyphonic instrument sounds from music scores, often using a generic MIDI input. In this work, we propose an expressive acoustic guitar sound synthesis model with a customized input representation to the instrument, which we call guitarroll. We implement the proposed approach using diffusion-based outpainting which can generate audio with long-term consistency. To overcome the lack of MIDI/audio-paired datasets, we used not only an existing guitar dataset but also collected data from a high quality sample-based guitar synthesizer. Through quantitative and qualitative evaluations, we show that our proposed model has higher audio quality than the baseline model and generates more realistic timbre sounds than the previous leading work.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13498
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Expressive Acoustic Guitar Sound Synthesis with an Instrument-Specific Input Representation and Diffusion Outpainting
Kim, Hounsu
Choi, Soonbeom
Nam, Juhan
Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
Signal Processing
Synthesizing performing guitar sound is a highly challenging task due to the polyphony and high variability in expression. Recently, deep generative models have shown promising results in synthesizing expressive polyphonic instrument sounds from music scores, often using a generic MIDI input. In this work, we propose an expressive acoustic guitar sound synthesis model with a customized input representation to the instrument, which we call guitarroll. We implement the proposed approach using diffusion-based outpainting which can generate audio with long-term consistency. To overcome the lack of MIDI/audio-paired datasets, we used not only an existing guitar dataset but also collected data from a high quality sample-based guitar synthesizer. Through quantitative and qualitative evaluations, we show that our proposed model has higher audio quality than the baseline model and generates more realistic timbre sounds than the previous leading work.
title Expressive Acoustic Guitar Sound Synthesis with an Instrument-Specific Input Representation and Diffusion Outpainting
topic Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2401.13498