A model structure integration based on a Bayesian framework for speech recognition

Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, K. Tokuda
{"title":"A model structure integration based on a Bayesian framework for speech recognition","authors":"Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, K. Tokuda","doi":"10.1109/ICASSP.2012.6288996","DOIUrl":null,"url":null,"abstract":"This paper proposes an acoustic modeling technique based on Bayesian framework using multiple model structures for speech recognition. The Bayesian approach is a statistical technique for estimating reliable predictive distributions by marginalizing model parameters, and its effectiveness in HMM-based speech recognition has been reported. Although the basic idea underlying the Bayesian approach is to treat all parameters as random variables, only one model structure is still selected in the conventional method. Multiple model structures are treated as latent variables in the proposed method and integrated based on the Bayesian framework. Furthermore, we applied deterministic annealing to the training algorithm to estimate appropriate acoustic models. The proposed method effectively utilizes multiple model structures, especially in the early stage of training and this leads to better predictive distributions and improvement of recognition performance.","PeriodicalId":6443,"journal":{"name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2012-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASSP.2012.6288996","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

This paper proposes an acoustic modeling technique based on Bayesian framework using multiple model structures for speech recognition. The Bayesian approach is a statistical technique for estimating reliable predictive distributions by marginalizing model parameters, and its effectiveness in HMM-based speech recognition has been reported. Although the basic idea underlying the Bayesian approach is to treat all parameters as random variables, only one model structure is still selected in the conventional method. Multiple model structures are treated as latent variables in the proposed method and integrated based on the Bayesian framework. Furthermore, we applied deterministic annealing to the training algorithm to estimate appropriate acoustic models. The proposed method effectively utilizes multiple model structures, especially in the early stage of training and this leads to better predictive distributions and improvement of recognition performance.
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
基于贝叶斯框架的语音识别模型结构集成
提出了一种基于贝叶斯框架的多模型结构声学建模技术,用于语音识别。贝叶斯方法是一种通过边缘化模型参数来估计可靠预测分布的统计技术,它在基于hmm的语音识别中的有效性已经得到了报道。尽管贝叶斯方法的基本思想是将所有参数视为随机变量,但传统方法仍然只选择一种模型结构。该方法将多个模型结构作为潜在变量,并基于贝叶斯框架进行集成。此外,我们将确定性退火应用到训练算法中,以估计合适的声学模型。该方法有效地利用了多种模型结构,特别是在训练的早期阶段,从而获得了更好的预测分布,提高了识别性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Scalable Multilevel Quantization for Distributed Detection Linear Model-Based Intra Prediction in VVC Test Model Practical Concentric Open Sphere Cardioid Microphone Array Design for Higher Order Sound Field Capture Embedding Physical Augmentation and Wavelet Scattering Transform to Generative Adversarial Networks for Audio Classification with Limited Training Resources Improving ASR Robustness to Perturbed Speech Using Cycle-consistent Generative Adversarial Networks
×
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