# Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Study

arXiv: https://arxiv.org/abs/2106.08686 · HTML: https://mlsanity.com/paper/2106.08686/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 38 references that are in the map.
- First posted on arXiv 16 Jun 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner](https://mlsanity.com/paper/1607.08723/) (2016)
- [Unsupervised Learning of Semantic Audio Representations](https://mlsanity.com/paper/1711.02209/) (2017)
- [Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models](https://mlsanity.com/paper/1811.00403/) (2018)
- [Deep convolutional acoustic word embeddings using word-pair side information](https://mlsanity.com/paper/1510.01032/) (2015)
- [Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches](https://mlsanity.com/paper/1611.02550/) (2016)
- [Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings](https://mlsanity.com/paper/1706.03818/) (2017)
- [Multi-view Recurrent Neural Acoustic Word Embeddings](https://mlsanity.com/paper/1611.04496/) (2016)
- [Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition](https://mlsanity.com/paper/1903.12306/) (2019)
- [Multilingual acoustic word embedding models for processing zero-resource languages](https://mlsanity.com/paper/2002.02109/) (2020)
- [Learning Acoustic Word Embeddings with Temporal Context for Query-by-Example Speech Search](https://mlsanity.com/paper/1806.03621/) (2018)
- [Evaluating computational models of infant phonetic learning across languages](https://mlsanity.com/paper/2008.02888/) (2020)
- [A phonetic model of non-native spoken word processing](https://mlsanity.com/paper/2101.11332/) (2021)

## Built on by (most cited first, 8 of 8)

- [Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations](https://mlsanity.com/paper/2406.09200/) (2024)
- [How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings](https://mlsanity.com/paper/2109.10179/) (2021)
- [Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili](https://mlsanity.com/paper/2306.00410/) (2023)
- [Analyzing the Representational Geometry of Acoustic Word Embeddings](https://mlsanity.com/paper/2301.03012/) (2023)
- [Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations](https://mlsanity.com/paper/2403.08738/) (2024)
- [Modeling Orthographic Variation Improves NLP Performance for Nigerian Pidgin](https://mlsanity.com/paper/2404.18264/) (2024)
- [Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings](https://mlsanity.com/paper/2209.06633/) (2022)
- [Probing in the Wild: A Case Study of Self-Supervised Speech Representations on Mandarin Sub-dialects with Unsupervised Articulatory Analysis](https://mlsanity.com/paper/2606.25459/) (2026)

## Abstract (arXiv)

Several variants of deep neural networks have been successfully employed for building parametric models that project variable-duration spoken word segments onto fixed-size vector representations, or acoustic word embeddings (AWEs). However, it remains unclear to what degree we can rely on the distance in the emerging AWE space as an estimate of word-form similarity. In this paper, we ask: does the distance in the acoustic embedding space correlate with phonological dissimilarity? To answer this question, we empirically investigate the performance of supervised approaches for AWEs with different neural architectures and learning objectives. We train AWE models in controlled settings for two languages (German and Czech) and evaluate the embeddings on two tasks: word discrimination and phonological similarity. Our experiments show that (1) the distance in the embedding space in the best cases only moderately correlates with phonological distance, and (2) improving the performance on the word discrimination task does not necessarily yield models that better reflect word phonological similarity. Our findings highlight the necessity to rethink the current intrinsic evaluations for AWEs.