# Multilingual Jointly Trained Acoustic and Written Word Embeddings

arXiv: https://arxiv.org/abs/2006.14007 · HTML: https://mlsanity.com/paper/2006.14007/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2020.

## Built on by (most cited first, 16 of 16)

- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [What Do Self-Supervised Speech Models Know About Words?](https://mlsanity.com/paper/2307.00162/) (2023)
- [Cross-modal Contrastive Learning for Speech Translation](https://mlsanity.com/paper/2205.02444/) (2022)
- [Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models](https://mlsanity.com/paper/2210.16043/) (2022)
- [Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation](https://mlsanity.com/paper/2103.10731/) (2021)
- [DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon](https://mlsanity.com/paper/2206.11332/) (2022)
- [Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language](https://mlsanity.com/paper/2106.12834/) (2021)
- [PWESuite: Phonetic Word Embeddings and Tasks They Facilitate](https://mlsanity.com/paper/2304.02541/) (2023)
- [Understanding Shared Speech-Text Representations](https://mlsanity.com/paper/2304.14514/) (2023)
- [Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition](https://mlsanity.com/paper/2201.11207/) (2022)
- [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)
- [AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination](https://mlsanity.com/paper/2210.14564/) (2022)
- [Relational Proxy Loss for Audio-Text based Keyword Spotting](https://mlsanity.com/paper/2406.05314/) (2024)
- [Leveraging multilingual transfer for unsupervised semantic acoustic word embeddings](https://mlsanity.com/paper/2307.02083/) (2023)
- [Text-Aware Adapter for Few-Shot Keyword Spotting](https://mlsanity.com/paper/2412.18142/) (2024)
- [Adversarial Deep Metric Learning for Cross-Modal Audio-Text Alignment in Open-Vocabulary Keyword Spotting](https://mlsanity.com/paper/2505.16735/) (2025)

## Abstract (arXiv)

Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically grounded word embeddings (AGWEs). Such embeddings have been used to improve speech retrieval, recognition, and spoken term discovery. In this work, we extend this idea to multiple low-resource languages. We jointly train an AWE model and an AGWE model, using phonetically transcribed data from multiple languages. The pre-trained models can then be used for unseen zero-resource languages, or fine-tuned on data from low-resource languages. We also investigate distinctive features, as an alternative to phone labels, to better share cross-lingual information. We test our models on word discrimination tasks for twelve languages. When trained on eleven languages and tested on the remaining unseen language, our model outperforms traditional unsupervised approaches like dynamic time warping. After fine-tuning the pre-trained models on one hour or even ten minutes of data from a new language, performance is typically much better than training on only the target-language data. We also find that phonetic supervision improves performance over character sequences, and that distinctive feature supervision is helpful in handling unseen phones in the target language.