@inproceedings{wang-etal-2023-mospc,
title = "{MOSPC}: {MOS} Prediction Based on Pairwise Comparison",
author = "Wang, Kexin and
Zhao, Yunlong and
Dong, Qianqian and
Ko, Tom and
Wang, Mingxuan",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.132",
doi = "10.18653/v1/2023.acl-short.132",
pages = "1547--1556",
abstract = "As a subjective metric to evaluate the quality of synthesized speech, Mean opinion score(MOS) usually requires multiple annotators to score the same speech. Such an annotation approach requires a lot of manpower and is also time-consuming. MOS prediction model for automatic evaluation can significantly reduce labor cost. In previous works, it is difficult to accurately rank the quality of speech when the MOS scores are close. However, in practical applications, it is more important to correctly rank the quality of synthesis systems or sentences than simply predicting MOS scores. Meanwhile, as each annotator scores multiple audios during annotation, the score is probably a relative value based on the first or the first few speech scores given by the annotator. Motivated by the above two points, we propose a general framework for MOS prediction based on pair comparison (MOSPC), and we utilize C-Mixup algorithm to enhance the generalization performance of MOSPC.The experiments on BVCC and VCC2018 show that our framework outperforms the baselines on most of the correlation coefficient metrics, especially on the metric KTAU related to quality ranking. And our framework also surpasses the strong baseline in ranking accuracy on each fine-grained segment. These results indicate that our framework contributes to improving the ranking accuracy of speech quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2023-mospc">
<titleInfo>
<title>MOSPC: MOS Prediction Based on Pairwise Comparison</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kexin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunlong</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qianqian</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As a subjective metric to evaluate the quality of synthesized speech, Mean opinion score(MOS) usually requires multiple annotators to score the same speech. Such an annotation approach requires a lot of manpower and is also time-consuming. MOS prediction model for automatic evaluation can significantly reduce labor cost. In previous works, it is difficult to accurately rank the quality of speech when the MOS scores are close. However, in practical applications, it is more important to correctly rank the quality of synthesis systems or sentences than simply predicting MOS scores. Meanwhile, as each annotator scores multiple audios during annotation, the score is probably a relative value based on the first or the first few speech scores given by the annotator. Motivated by the above two points, we propose a general framework for MOS prediction based on pair comparison (MOSPC), and we utilize C-Mixup algorithm to enhance the generalization performance of MOSPC.The experiments on BVCC and VCC2018 show that our framework outperforms the baselines on most of the correlation coefficient metrics, especially on the metric KTAU related to quality ranking. And our framework also surpasses the strong baseline in ranking accuracy on each fine-grained segment. These results indicate that our framework contributes to improving the ranking accuracy of speech quality.</abstract>
<identifier type="citekey">wang-etal-2023-mospc</identifier>
<identifier type="doi">10.18653/v1/2023.acl-short.132</identifier>
<location>
<url>https://aclanthology.org/2023.acl-short.132</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1547</start>
<end>1556</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MOSPC: MOS Prediction Based on Pairwise Comparison
%A Wang, Kexin
%A Zhao, Yunlong
%A Dong, Qianqian
%A Ko, Tom
%A Wang, Mingxuan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wang-etal-2023-mospc
%X As a subjective metric to evaluate the quality of synthesized speech, Mean opinion score(MOS) usually requires multiple annotators to score the same speech. Such an annotation approach requires a lot of manpower and is also time-consuming. MOS prediction model for automatic evaluation can significantly reduce labor cost. In previous works, it is difficult to accurately rank the quality of speech when the MOS scores are close. However, in practical applications, it is more important to correctly rank the quality of synthesis systems or sentences than simply predicting MOS scores. Meanwhile, as each annotator scores multiple audios during annotation, the score is probably a relative value based on the first or the first few speech scores given by the annotator. Motivated by the above two points, we propose a general framework for MOS prediction based on pair comparison (MOSPC), and we utilize C-Mixup algorithm to enhance the generalization performance of MOSPC.The experiments on BVCC and VCC2018 show that our framework outperforms the baselines on most of the correlation coefficient metrics, especially on the metric KTAU related to quality ranking. And our framework also surpasses the strong baseline in ranking accuracy on each fine-grained segment. These results indicate that our framework contributes to improving the ranking accuracy of speech quality.
%R 10.18653/v1/2023.acl-short.132
%U https://aclanthology.org/2023.acl-short.132
%U https://doi.org/10.18653/v1/2023.acl-short.132
%P 1547-1556
Markdown (Informal)
[MOSPC: MOS Prediction Based on Pairwise Comparison](https://aclanthology.org/2023.acl-short.132) (Wang et al., ACL 2023)
ACL
- Kexin Wang, Yunlong Zhao, Qianqian Dong, Tom Ko, and Mingxuan Wang. 2023. MOSPC: MOS Prediction Based on Pairwise Comparison. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1547–1556, Toronto, Canada. Association for Computational Linguistics.