Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Yu-Fei, Ai, Yang, Lu, Ye-Xin, Du, Hui-Peng, Ling, Zhen-Hua
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915076634574848
author Shi, Yu-Fei
Ai, Yang
Lu, Ye-Xin
Du, Hui-Peng
Ling, Zhen-Hua
author_facet Shi, Yu-Fei
Ai, Yang
Lu, Ye-Xin
Du, Hui-Peng
Ling, Zhen-Hua
contents We participated in track 2 of the VoiceMOS Challenge 2024, which aimed to predict the mean opinion score (MOS) of singing samples. Our submission secured the first place among all participating teams, excluding the official baseline. In this paper, we further improve our submission and propose a novel Pitch-and-Spectrum-aware Singing Quality Assessment (PS-SQA) method. The PS-SQA is designed based on the self-supervised-learning (SSL) MOS predictor, incorporating singing pitch and spectral information, which are extracted using pitch histogram and non-quantized neural codec, respectively. Additionally, the PS-SQA introduces a bias correction strategy to address prediction biases caused by low-resource training samples, and employs model fusion technology to further enhance prediction accuracy. Experimental results confirm that our proposed PS-SQA significantly outperforms all competing systems across all system-level metrics, confirming its strong sing quality assessment capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11123
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion
Shi, Yu-Fei
Ai, Yang
Lu, Ye-Xin
Du, Hui-Peng
Ling, Zhen-Hua
Sound
Audio and Speech Processing
We participated in track 2 of the VoiceMOS Challenge 2024, which aimed to predict the mean opinion score (MOS) of singing samples. Our submission secured the first place among all participating teams, excluding the official baseline. In this paper, we further improve our submission and propose a novel Pitch-and-Spectrum-aware Singing Quality Assessment (PS-SQA) method. The PS-SQA is designed based on the self-supervised-learning (SSL) MOS predictor, incorporating singing pitch and spectral information, which are extracted using pitch histogram and non-quantized neural codec, respectively. Additionally, the PS-SQA introduces a bias correction strategy to address prediction biases caused by low-resource training samples, and employs model fusion technology to further enhance prediction accuracy. Experimental results confirm that our proposed PS-SQA significantly outperforms all competing systems across all system-level metrics, confirming its strong sing quality assessment capabilities.
title Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2411.11123