# An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages

arXiv: https://arxiv.org/abs/1609.08139 · HTML: https://mlsanity.com/paper/1609.08139/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2016.

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

- [Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation](https://mlsanity.com/paper/2103.10731/) (2021)
- [End-to-End Speech-to-Text Translation: A Survey](https://mlsanity.com/paper/2312.01053/) (2023)
- [Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation](https://mlsanity.com/paper/2205.07100/) (2022)

## Abstract (arXiv)

For many low-resource languages, spoken language resources are more likely to be annotated with translations than with transcriptions. Translated speech data is potentially valuable for documenting endangered languages or for training speech translation systems. A first step towards making use of such data would be to automatically align spoken words with their translations. We present a model that combines Dyer et al.'s reparameterization of IBM Model 2 (fast-align) and k-means clustering using Dynamic Time Warping as a distance metric. The two components are trained jointly using expectation-maximization. In an extremely low-resource scenario, our model performs significantly better than both a neural model and a strong baseline.