MooseNet:基于PLDA模块的可训练合成语音度量

Ondvrej Pl'atek, Ondrej Dusek
{"title":"MooseNet:基于PLDA模块的可训练合成语音度量","authors":"Ondvrej Pl'atek, Ondrej Dusek","doi":"10.21437/ssw.2023-8","DOIUrl":null,"url":null,"abstract":"We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic Linear Discriminative Analysis (PLDA) generative model is used on top of an embedding obtained from a self-supervised learning (SSL) neural network (NN) model. We show that PLDA works well with a non-finetuned SSL model when trained only on 136 utterances (ca. one minute training time) and that PLDA consistently improves various neural MOS prediction models, even state-of-the-art models with task-specific fine-tuning. Our ablation study shows PLDA training superiority over SSL model fine-tuning in a low-resource scenario. We also improve SSL model fine-tuning using a convenient optimizer choice and additional contrastive and multi-task training objectives. The fine-tuned MooseNet NN with the PLDA module achieves the best results, surpassing the SSL baseline on the VoiceMOS Challenge data.","PeriodicalId":346639,"journal":{"name":"12th ISCA Speech Synthesis Workshop (SSW2023)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module\",\"authors\":\"Ondvrej Pl'atek, Ondrej Dusek\",\"doi\":\"10.21437/ssw.2023-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic Linear Discriminative Analysis (PLDA) generative model is used on top of an embedding obtained from a self-supervised learning (SSL) neural network (NN) model. We show that PLDA works well with a non-finetuned SSL model when trained only on 136 utterances (ca. one minute training time) and that PLDA consistently improves various neural MOS prediction models, even state-of-the-art models with task-specific fine-tuning. Our ablation study shows PLDA training superiority over SSL model fine-tuning in a low-resource scenario. We also improve SSL model fine-tuning using a convenient optimizer choice and additional contrastive and multi-task training objectives. The fine-tuned MooseNet NN with the PLDA module achieves the best results, surpassing the SSL baseline on the VoiceMOS Challenge data.\",\"PeriodicalId\":346639,\"journal\":{\"name\":\"12th ISCA Speech Synthesis Workshop (SSW2023)\",\"volume\":\"43 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"12th ISCA Speech Synthesis Workshop (SSW2023)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.21437/ssw.2023-8\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"12th ISCA Speech Synthesis Workshop (SSW2023)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21437/ssw.2023-8","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

我们提出了MooseNet,一个可训练的语音指标,预测听众的平均意见得分(MOS)。我们提出了一种新的方法,在自监督学习(SSL)神经网络(NN)模型的嵌入上使用概率线性判别分析(PLDA)生成模型。我们表明,当只训练136个话语(大约一分钟的训练时间)时,PLDA与非微调SSL模型一起工作得很好,并且PLDA不断改进各种神经MOS预测模型,甚至是具有任务特定微调的最先进模型。我们的烧蚀研究表明,在低资源情况下,PLDA训练优于SSL模型微调。我们还使用方便的优化器选择和额外的对比和多任务训练目标来改进SSL模型微调。带有PLDA模块的经过微调的MooseNet NN达到了最佳效果,超过了VoiceMOS Challenge数据上的SSL基线。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module
We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic Linear Discriminative Analysis (PLDA) generative model is used on top of an embedding obtained from a self-supervised learning (SSL) neural network (NN) model. We show that PLDA works well with a non-finetuned SSL model when trained only on 136 utterances (ca. one minute training time) and that PLDA consistently improves various neural MOS prediction models, even state-of-the-art models with task-specific fine-tuning. Our ablation study shows PLDA training superiority over SSL model fine-tuning in a low-resource scenario. We also improve SSL model fine-tuning using a convenient optimizer choice and additional contrastive and multi-task training objectives. The fine-tuned MooseNet NN with the PLDA module achieves the best results, surpassing the SSL baseline on the VoiceMOS Challenge data.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Re-examining the quality dimensions of synthetic speech Synthesising turn-taking cues using natural conversational data Diffusion Transformer for Adaptive Text-to-Speech Adaptive Duration Modification of Speech using Masked Convolutional Networks and Open-Loop Time Warping Audiobook synthesis with long-form neural text-to-speech
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1