# Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling

arXiv: https://arxiv.org/abs/2306.02153 · HTML: https://mlsanity.com/paper/2306.02153/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 3 Jun 2023.

## Builds on (most cited first, 24 of 24)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [The Zero Resource Speech Challenge 2017](https://mlsanity.com/paper/1712.04313/) (2017)
- [Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder models](https://mlsanity.com/paper/1811.00403/) (2018)
- [A segmental framework for fully-unsupervised large-vocabulary speech recognition](https://mlsanity.com/paper/1606.06950/) (2016)
- [Query-by-Example Search with Discriminative Neural Acoustic Word Embeddings](https://mlsanity.com/paper/1706.03818/) (2017)
- [Evaluating the reliability of acoustic speech embeddings](https://mlsanity.com/paper/2007.13542/) (2020)
- [Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models](https://mlsanity.com/paper/2210.16043/) (2022)
- [Semantic speech retrieval with a visually grounded model of untranscribed speech](https://mlsanity.com/paper/1710.01949/) (2017)
- [Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation](https://mlsanity.com/paper/2103.10731/) (2021)
- [Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining](https://mlsanity.com/paper/2301.07295/) (2023)
- [A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings](https://mlsanity.com/paper/2012.02221/) (2020)
- [Deciphering Speech: a Zero-Resource Approach to Cross-Lingual Transfer in ASR](https://mlsanity.com/paper/2111.06799/) (2021)
- [A comparison of self-supervised speech representations as input features for unsupervised acoustic word embeddings](https://mlsanity.com/paper/2012.07387/) (2020)
- [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)
- [Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning](https://mlsanity.com/paper/2204.05148/) (2022)
- [Unsupervised neural and Bayesian models for zero-resource speech processing](https://mlsanity.com/paper/1701.00851/) (2017)

## Built on by (most cited first, 2 of 2)

- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models](https://mlsanity.com/paper/2506.01133/) (2025)

## Abstract (arXiv)

Acoustic word embeddings are typically created by training a pooling function using pairs of word-like units. For unsupervised systems, these are mined using k-nearest neighbor (KNN) search, which is slow. Recently, mean-pooled representations from a pre-trained self-supervised English model were suggested as a promising alternative, but their performance on target languages was not fully competitive. Here, we explore improvements to both approaches: we use continued pre-training to adapt the self-supervised model to the target language, and we use a multilingual phone recognizer (MPR) to mine phone n-gram pairs for training the pooling function. Evaluating on four languages, we show that both methods outperform a recent approach on word discrimination. Moreover, the MPR method is orders of magnitude faster than KNN, and is highly data efficient. We also show a small improvement from performing learned pooling on top of the continued pre-trained representations.