# Streaming Translation and Transcription Through Speech-to-Text Causal Alignment

arXiv: https://arxiv.org/abs/2603.11578 · HTML: https://mlsanity.com/paper/2603.11578/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 68 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 30 of 37)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection](https://mlsanity.com/paper/2310.10482/) (2023)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [Monotonic Infinite Lookback Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/1906.05218/) (2019)
- [Learning to Translate in Real-time with Neural Machine Translation](https://mlsanity.com/paper/1610.00388/) (2016)
- [SimulEval: An Evaluation Toolkit for Simultaneous Translation](https://mlsanity.com/paper/2007.16193/) (2020)
- [Monotonic Multihead Attention](https://mlsanity.com/paper/1909.12406/) (2019)
- [Can neural machine translation do simultaneous translation?](https://mlsanity.com/paper/1606.02012/) (2016)
- [Online and Linear-Time Attention by Enforcing Monotonic Alignments](https://mlsanity.com/paper/1704.00784/) (2017)
- [Monotonic Chunkwise Attention](https://mlsanity.com/paper/1712.05382/) (2017)
- [MinMo: A Multimodal Large Language Model for Seamless Voice Interaction](https://mlsanity.com/paper/2501.06282/) (2025)
- [Earnings-21: A Practical Benchmark for ASR in the Wild](https://mlsanity.com/paper/2104.11348/) (2021)
- [Efficient Sequence Transduction by Jointly Predicting Tokens and Durations](https://mlsanity.com/paper/2304.06795/) (2023)
- [Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection](https://mlsanity.com/paper/2005.11185/) (2020)
- [AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation](https://mlsanity.com/paper/2305.11408/) (2023)
- [TransLLaMa: LLM-based Simultaneous Translation System](https://mlsanity.com/paper/2402.04636/) (2024)
- [Attention as a Guide for Simultaneous Speech Translation](https://mlsanity.com/paper/2212.07850/) (2022)
- [CUNI-KIT System for Simultaneous Speech Translation Task at IWSLT 2022](https://mlsanity.com/paper/2204.06028/) (2022)
- [Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling](https://mlsanity.com/paper/2509.08753/) (2025)
- [SHAS: Approaching optimal Segmentation for End-to-End Speech Translation](https://mlsanity.com/paper/2202.04774/) (2022)
- [StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection](https://mlsanity.com/paper/2406.06097/) (2024)
- [Learning Optimal Policy for Simultaneous Machine Translation via Binary Search](https://mlsanity.com/paper/2305.12774/) (2023)
- [High-Fidelity Simultaneous Speech-To-Speech Translation](https://mlsanity.com/paper/2502.03382/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026](https://mlsanity.com/paper/2606.03948/) (2026)

## Abstract (arXiv)

Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, end-to-end model for simultaneous speech-to-text translation and streaming transcription. We also introduce Decoder Time Dilation, a mechanism that counteracts the overrepresentation of WAIT tokens in training. We present a supervised fine-tuning strategy that trains the model to recover from delays, significantly improving the quality-latency trade-off. Despite its modest size, Hikari delivers competitive translation quality at consistently low latency, comparing favorably with published IWSLT 2026 submissions up to 38x larger and with proprietary API systems across en-ja, en-de, and en-ru. We release our model weights and code to facilitate further research.