arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.01647cs.CL
收藏

基于自动编码器的声学词嵌入分析

Analyzing autoencoder-based acoustic word embeddings

University of Edinburgh(爱丁堡大学);Stellenbosch University(斯泰伦博斯大学)

Yevgen Matusevych, Herman Kamper, Sharon Goldwater

摘要:

最近的研究介绍了学习声学词嵌入(AWE)的方法--固定大小的矢量表示的单词编码其声学特征。尽管AWE在语音处理研究中被广泛使用,但它们仅在区分整个单词标记的能力方面进行了定量评估。为了更好地理解AWE在各种下游任务和认知建模中的应用,我们需要分析AWE的表示空间。在这里,我们分析了AWE空间的基本属性学习序列到序列编码器-解码器模型在六个类型不同的语言。我们首先表明,这些AWE保留了一些关于单词的绝对持续时间和扬声器的信息。同时,这些AWE的表示空间被组织成使得词的嵌入之间的距离随着那些词的语音相异性而增加。最后,AWE表现出一个词的起始偏差,类似于人类语音处理和词汇访问的各种研究中报道的模式。我们认为,这是一个有前途的结果,并鼓励进一步评估AWE作为一个潜在的有用的工具,在认知科学,它可以提供语音处理和词汇记忆之间的联系。

英文摘要:

Recent studies have introduced methods for learning acoustic word embeddings (AWEs)---fixed-size vector representations of words which encode their acoustic features. Despite the widespread use of AWEs in speech processing research, they have only been evaluated quantitatively in their ability to discriminate between whole word tokens. To better understand the applications of AWEs in various downstream tasks and in cognitive modeling, we need to analyze the representation spaces of AWEs. Here we analyze basic properties of AWE spaces learned by a sequence-to-sequence encoder-decoder model in six typologically diverse languages. We first show that these AWEs preserve some information about words' absolute duration and speaker. At the same time, the representation space of these AWEs is organized such that the distance between words' embeddings increases with those words' phonetic dissimilarity. Finally, the AWEs exhibit a word onset bias, similar to patterns reported in various studies on human speech processing and lexical access. We argue this is a promising result and encourage further evaluation of AWEs as a potentially useful tool in cognitive science, which could provide a link between speech processing and lexical memory.

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。

↑