Automatic Estimation of Singing Voice Musical Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Narang, Jyoti, Tamer, Nazif Can, De La Vega, Viviana, Serra, Xavier
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916456765063168
author Narang, Jyoti
Tamer, Nazif Can
De La Vega, Viviana
Serra, Xavier
author_facet Narang, Jyoti
Tamer, Nazif Can
De La Vega, Viviana
Serra, Xavier
contents Musical dynamics form a core part of expressive singing voice performances. However, automatic analysis of musical dynamics for singing voice has received limited attention partly due to the scarcity of suitable datasets and a lack of clear evaluation frameworks. To address this challenge, we propose a methodology for dataset curation. Employing the proposed methodology, we compile a dataset comprising 509 musical dynamics annotated singing voice performances, aligned with 163 score files, leveraging state-of-the-art source separation and alignment techniques. The scores are sourced from the OpenScore Lieder corpus of romantic-era compositions, widely known for its wealth of expressive annotations. Utilizing the curated dataset, we train a multi-head attention based CNN model with varying window sizes to evaluate the effectiveness of estimating musical dynamics. We explored two distinct perceptually motivated input representations for the model training: log-Mel spectrum and bark-scale based features. For testing, we manually curate another dataset of 25 musical dynamics annotated performances in collaboration with a professional vocalist. We conclude through our experiments that bark-scale based features outperform log-Mel-features for the task of singing voice dynamics prediction. The dataset along with the code is shared publicly for further research on the topic.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20540
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automatic Estimation of Singing Voice Musical Dynamics
Narang, Jyoti
Tamer, Nazif Can
De La Vega, Viviana
Serra, Xavier
Sound
Information Retrieval
Audio and Speech Processing
Musical dynamics form a core part of expressive singing voice performances. However, automatic analysis of musical dynamics for singing voice has received limited attention partly due to the scarcity of suitable datasets and a lack of clear evaluation frameworks. To address this challenge, we propose a methodology for dataset curation. Employing the proposed methodology, we compile a dataset comprising 509 musical dynamics annotated singing voice performances, aligned with 163 score files, leveraging state-of-the-art source separation and alignment techniques. The scores are sourced from the OpenScore Lieder corpus of romantic-era compositions, widely known for its wealth of expressive annotations. Utilizing the curated dataset, we train a multi-head attention based CNN model with varying window sizes to evaluate the effectiveness of estimating musical dynamics. We explored two distinct perceptually motivated input representations for the model training: log-Mel spectrum and bark-scale based features. For testing, we manually curate another dataset of 25 musical dynamics annotated performances in collaboration with a professional vocalist. We conclude through our experiments that bark-scale based features outperform log-Mel-features for the task of singing voice dynamics prediction. The dataset along with the code is shared publicly for further research on the topic.
title Automatic Estimation of Singing Voice Musical Dynamics
topic Sound
Information Retrieval
Audio and Speech Processing
url https://arxiv.org/abs/2410.20540