How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings

Badr Abdullah, Iuliia Zaitova, Tania Avgustinova, Bernd Möbius, Dietrich Klakow


Abstract
How do neural networks “perceive” speech sounds from unknown languages? Does the typological similarity between the model’s training language (L1) and an unknown language (L2) have an impact on the model representations of L2 speech signals? To answer these questions, we present a novel experimental design based on representational similarity analysis (RSA) to analyze acoustic word embeddings (AWEs)—vector representations of variable-duration spoken-word segments. First, we train monolingual AWE models on seven Indo-European languages with various degrees of typological similarity. We then employ RSA to quantify the cross-lingual similarity by simulating native and non-native spoken-word processing using AWEs. Our experiments show that typological similarity indeed affects the representational similarity of the models in our study. We further discuss the implications of our work on modeling speech processing and language similarity with neural networks.
Anthology ID:
2021.blackboxnlp-1.32
Volume:
Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Jasmijn Bastings, Yonatan Belinkov, Emmanuel Dupoux, Mario Giulianelli, Dieuwke Hupkes, Yuval Pinter, Hassan Sajjad
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
407–419
Language:
URL:
https://aclanthology.org/2021.blackboxnlp-1.32
DOI:
10.18653/v1/2021.blackboxnlp-1.32
Bibkey:
Cite (ACL):
Badr Abdullah, Iuliia Zaitova, Tania Avgustinova, Bernd Möbius, and Dietrich Klakow. 2021. How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings. In Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 407–419, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings (Abdullah et al., BlackboxNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2021.blackboxnlp-1.32.pdf
Code
 uds-lsv/xrsa-awes