arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.01360cs.CL
收藏

零资源声学单元发现的实证评估

An Empirical Evaluation of Zero Resource Acoustic Unit Discovery

Johns Hopkins University(约翰斯·霍普金斯大学);University of Chinese Academy of Sciences(中国科学院大学);Amazon(亚马逊);International Institute of Information Technology(国际信息技术学院);Stanford University(斯坦福大学);Brno University of Technology(布尔诺理工大学)

Chunxi Liu, Jinyi Yang, Ming Sun, Santosh Kesiraju, Alena Rott, Lucas Ondel, Pegah Ghahremani, Najim Dehak, Lukas Burget, Sanjeev Khudanpur

摘要:

声学单元发现(AUD)是从语音中自动识别分类声学单元库存并产生相应声学单元标记的过程。AUD为零资源环境中的无监督声学模型训练提供了一条重要途径,在这种环境中,专家提供的语言知识和转录语音不可用。因此,为了进一步促进零资源AUD过程,在本文中,我们证明了声学特征表示可以通过以下方式显着改进:(i)以无监督的自训练方式执行线性判别分析(LDA),以及(ii)通过构建多语言瓶颈(BN)特征提取器来利用其他语言的资源,以提供有效的跨语言泛化。此外,我们对多个下游语音应用程序进行AUD功效的全面评估,其相关性能表明,AUD评估是可行的,使用不同的替代语言资源时,只有这些评估资源的一个子集可以在典型的零资源应用程序。

英文摘要:

Acoustic unit discovery (AUD) is a process of automatically identifying a categorical acoustic unit inventory from speech and producing corresponding acoustic unit tokenizations. AUD provides an important avenue for unsupervised acoustic model training in a zero resource setting where expert-provided linguistic knowledge and transcribed speech are unavailable. Therefore, to further facilitate zero-resource AUD process, in this paper, we demonstrate acoustic feature representations can be significantly improved by (i) performing linear discriminant analysis (LDA) in an unsupervised self-trained fashion, and (ii) leveraging resources of other languages through building a multilingual bottleneck (BN) feature extractor to give effective cross-lingual generalization. Moreover, we perform comprehensive evaluations of AUD efficacy on multiple downstream speech applications, and their correlated performance suggests that AUD evaluations are feasible using different alternative language resources when only a subset of these evaluation resources can be available in typical zero resource applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑