mlsanityData to 7 Oct 2026

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

arXiv 2109.10179 ↗First posted 21 Sep 2021cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 21 Sep 2021.

Builds on

24 of 47 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2017Billion-scale similarity search with GPUscited by 2,477
  5. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  6. 2016Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learnercited by 68
  7. 2020Similarity Analysis of Contextual Word Representation Modelscited by 54
  8. 2019Blackbox meets blackbox: Representational Similarity and Stability Analysis of Neural Language Models and Brainscited by 37
  9. 2019Correlating neural and symbolic representations of languagecited by 32
  10. 2018Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder modelscited by 29
  11. 2015Deep convolutional acoustic word embeddings using word-pair side informationcited by 27
  12. 2017Encoding of phonology in a recurrent neural model of grounded speechcited by 27
12 more
  1. 2020Similarity Analysis of Self-Supervised Speech Representationscited by 26
  2. 2016Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approachescited by 25
  3. 2020Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysiscited by 18
  4. 2019What do Language Representations Really Represent?cited by 17
  5. 2020Analyzing analytical methods: The case of phonology in neural models of spoken languagecited by 16
  6. 2019Higher-order Comparisons of Sentence Encoder Representationscited by 10
  7. 2021Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Studycited by 8
  8. 2020Analyzing autoencoder-based acoustic word embeddingscited by 7
  9. 2021Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource languagecited by 7
  10. 2020Evaluating computational models of infant phonetic learning across languagescited by 6
  11. 2021A phonetic model of non-native spoken word processingcited by 5
  12. 2020Learning to Understand Child-directed and Adult-directed Speechcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 2; 2025: 1; 2026: 1.

8 papers.

  1. 2022Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifoldcited by 29
  2. 2024Encoding of lexical tone in self-supervised models of spoken languagecited by 22
  3. 2022Speech Sequence Embeddings using Nearest Neighbors Contrastive Learningcited by 7
  4. 2024Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representationscited by 3
  5. 2022Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddingscited by 2
  6. 2023Analyzing the Representational Geometry of Acoustic Word Embeddingscited by 2
  7. 2025A Technique for Isolating Lexically-Independent Phonetic Dependencies in Generative CNNscited by 0
  8. 2026Lost but not erased: Finding traces of a forgotten language in neural speech modelscited by 0