Latent Regression Bayesian Network for Speech Representation

Latent Regression Bayesian Network for Speech Representation
复制标题

用于语音表示的潜在回归贝叶斯网络

DOI:
10.3390/electronics12153342
复制
发表时间:
2023
期刊:
影响因子:
2.9
通讯作者:
Qiang Ji
Qiang Ji
中科院分区:
工程技术3区
文献类型:
--
作者:
Liang Xu;Yue Zhao;Xiaona Xu;Yigang Liu;Qiang Ji

文献摘要

参考文献

相似文献

针对低资源语言语音系统性能差的问题,提出了一种基于潜在回归贝叶斯网络(LRBN)的语音表示方法。LRBN是一种轻量级的无监督学习模型,它学习数据分布和高级特征,不像Wav2vec 2.0等计算昂贵的大型模型。为了评估LRBN在学习语音表征方面的有效性,我们在五种不同的低资源语言上进行了实验,并将它们应用于两个后续任务:音素分类和语音识别。我们的实验结果表明,LRBN在这两个任务中的表现都优于主流的语音表示方法,这突出了它在低资源语言的语音表示学习领域的潜力。
In this paper, we present a novel approach for speech representation using latent regression Bayesian networks (LRBN) to address the issue of poor performance in low-resource language speech systems. LRBN, a lightweight unsupervised learning model, learns data distribution and high-level features, unlike computationally expensive large models, such as Wav2vec 2.0. To evaluate the effectiveness of LRBN in learning speech representations, we conducted experiments on five different low-resource languages and applied them to two downstream tasks: phoneme classification and speech recognition. Our experimental results demonstrate that LRBN outperforms prevailing speech representation methods in both tasks, highlighting its potential in the realm of speech representation learning for low-resource languages.
使用 wav2vec 2.0 对脑瘫患者使用未标记语音进行语音识别
DOI: --
发表时间: 2022
期刊:
影响因子: --
作者:
松坂 勇樹;高島 遼一;滝口 哲也
通讯作者: 滝口 哲也