期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：96-102
DOI：10.18653/v1/2021.eacl-srw.14
语种：English
出版社：ACL Anthology
摘要：We present a deep neural model of spoken word recognition which is trained to retrieve the meaning of a word (in the form of a word embedding) given its spoken form, a task which resembles that faced by a human listener. Furthermore, we investigate the influence of variability in speech signals on the model’s performance. To this end, we conduct of set of controlled experiments using word-aligned read speech data in German. Our experiments show that (1) the model is more sensitive to dialectical variation than gender variation, and (2) recognition performance of word cognates from related languages reflect the degree of relatedness between languages in our study. Our work highlights the feasibility of modeling human speech perception using deep neural networks.
