# Speech-to-Speech Translation Pipelines for Conversations in Low-Resource Languages

arXiv: https://arxiv.org/abs/2506.01406 · HTML: https://mlsanity.com/paper/2506.01406/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 10 of 10)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Speech Translation and the End-to-End Promise: Taking Stock of Where We Are](https://mlsanity.com/paper/2004.06358/) (2020)
- [Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?](https://mlsanity.com/paper/2106.01045/) (2021)
- [Findings of the IWSLT 2024 Evaluation Campaign](https://mlsanity.com/paper/2411.05088/) (2024)
- [Recent Advances in Direct Speech-to-text Translation](https://mlsanity.com/paper/2306.11646/) (2023)
- [Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation](https://mlsanity.com/paper/2305.07455/) (2023)
- [Strategies for improving low resource speech to text translation relying on pre-trained ASR models](https://mlsanity.com/paper/2306.00208/) (2023)

## Abstract (arXiv)

The popularity of automatic speech-to-speech translation for human conversations is growing, but the quality varies significantly depending on the language pair. In a context of community interpreting for low-resource languages, namely Turkish and Pashto to/from French, we collected fine-tuning and testing data, and compared systems using several automatic metrics (BLEU, COMET, and BLASER) and human assessments. The pipelines included automatic speech recognition, machine translation, and speech synthesis, with local models and cloud-based commercial ones. Some components have been fine-tuned on our data. We evaluated over 60 pipelines and determined the best one for each direction. We also found that the ranks of components are generally independent of the rest of the pipeline.