# Analyzing the Representational Geometry of Acoustic Word Embeddings

arXiv: https://arxiv.org/abs/2301.03012 · HTML: https://mlsanity.com/paper/2301.03012/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 8 Jan 2023.

## Builds on (most cited first, 22 of 22)

- [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)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [All-but-the-Top: Simple and Effective Postprocessing for Word Representations](https://mlsanity.com/paper/1702.01417/) (2017)
- [IsoScore: Measuring the Uniformity of Embedding Space Utilization](https://mlsanity.com/paper/2108.07344/) (2021)
- [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)
- [Evaluating the reliability of acoustic speech embeddings](https://mlsanity.com/paper/2007.13542/) (2020)
- [Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation](https://mlsanity.com/paper/2103.10731/) (2021)
- [Acoustically Grounded Word Embeddings for Improved Acoustics-to-Word Speech Recognition](https://mlsanity.com/paper/1903.12306/) (2019)
- [Leveraging pre-trained representations to improve access to untranscribed speech from endangered languages](https://mlsanity.com/paper/2103.14583/) (2021)
- [Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Study](https://mlsanity.com/paper/2106.08686/) (2021)
- [How Familiar Does That Sound? Cross-Lingual Representational Similarity Analysis of Acoustic Word Embeddings](https://mlsanity.com/paper/2109.10179/) (2021)
- [Analyzing autoencoder-based acoustic word embeddings](https://mlsanity.com/paper/2004.01647/) (2020)
- [A phonetic model of non-native spoken word processing](https://mlsanity.com/paper/2101.11332/) (2021)
- [Word forms - not just their lengths- are optimized for efficient communication](https://mlsanity.com/paper/1703.01694/) (2017)
- [Inferring exemplar discriminability in brain representations](https://mlsanity.com/paper/2205.09514/) (2022)

## Built on by (most cited first, 3 of 3)

- [Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations](https://mlsanity.com/paper/2406.09200/) (2024)
- [Analyzing the relationships between pretraining language, phonetic, tonal, and speaker information in self-supervised speech models](https://mlsanity.com/paper/2506.10855/) (2025)
- [Deep Speech Representations Track Word Timing along a Low-Dimensional Circular Trajectory](https://mlsanity.com/paper/2610.16273/) (2026)

## Abstract (arXiv)

Acoustic word embeddings (AWEs) are vector representations such that different acoustic exemplars of the same word are projected nearby in the embedding space. In addition to their use in speech technology applications such as spoken term discovery and keyword spotting, AWE models have been adopted as models of spoken-word processing in several cognitively motivated studies and have been shown to exhibit human-like performance in some auditory processing tasks. Nevertheless, the representational geometry of AWEs remains an under-explored topic that has not been studied in the literature. In this paper, we take a closer analytical look at AWEs learned from English speech and study how the choice of the learning objective and the architecture shapes their representational profile. To this end, we employ a set of analytic techniques from machine learning and neuroscience in three different analyses: embedding space uniformity, word discriminability, and representational consistency. Our main findings highlight the prominent role of the learning objective on shaping the representation profile compared to the model architecture.