# PHRASED: Phrase Dictionary Biasing for Speech Translation

arXiv: https://arxiv.org/abs/2506.09175 · HTML: https://mlsanity.com/paper/2506.09175/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 22 of 22)

- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Achieving Human Parity on Automatic Chinese to English News Translation](https://mlsanity.com/paper/1803.05567/) (2018)
- [Speech Translation and the End-to-End Promise: Taking Stock of Where We Are](https://mlsanity.com/paper/2004.06358/) (2020)
- [Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting](https://mlsanity.com/paper/2309.15649/) (2023)
- [Can Generative Large Language Models Perform ASR Error Correction?](https://mlsanity.com/paper/2307.04172/) (2023)
- [Code-Switching for Enhancing NMT with Pre-Specified Translation](https://mlsanity.com/paper/1904.09107/) (2019)
- [Linguistic Input Features Improve Neural Machine Translation](https://mlsanity.com/paper/1606.02892/) (2016)
- [Large-Scale Streaming End-to-End Speech Translation with Neural Transducers](https://mlsanity.com/paper/2204.05352/) (2022)
- [Chain-of-Thought Prompting for Speech Translation](https://mlsanity.com/paper/2409.11538/) (2024)
- [Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent](https://mlsanity.com/paper/2407.21646/) (2024)
- [A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability](https://mlsanity.com/paper/2211.02499/) (2022)
- [Exploiting Linguistic Resources for Neural Machine Translation Using Multi-task Learning](https://mlsanity.com/paper/1708.00993/) (2017)
- [Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation](https://mlsanity.com/paper/2410.13198/) (2024)
- [Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm](https://mlsanity.com/paper/2310.00178/) (2023)
- [Neural Name Translation Improves Neural Machine Translation](https://mlsanity.com/paper/1607.01856/) (2016)
- [Who Are We Talking About? Handling Person Names in Speech Translation](https://mlsanity.com/paper/2205.06755/) (2022)
- [Joint Speech Translation and Named Entity Recognition](https://mlsanity.com/paper/2210.11987/) (2022)
- [Named Entity Detection and Injection for Direct Speech Translation](https://mlsanity.com/paper/2210.11981/) (2022)
- [CTC-GMM: CTC guided modality matching for fast and accurate streaming speech translation](https://mlsanity.com/paper/2410.05146/) (2024)

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

- [LOGIC: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration](https://mlsanity.com/paper/2601.15397/) (2026)

## Abstract (arXiv)

Phrases are essential to understand the core concepts in conversations. However, due to their rare occurrence in training data, correct translation of phrases is challenging in speech translation tasks. In this paper, we propose a phrase dictionary biasing method to leverage pairs of phrases mapping from the source language to the target language. We apply the phrase dictionary biasing method to two types of widely adopted models, a transducer-based streaming speech translation model and a multimodal large language model. Experimental results show that the phrase dictionary biasing method outperforms phrase list biasing by 21% relatively for the streaming speech translation model. In addition, phrase dictionary biasing enables multimodal large language models to use external phrase information, achieving 85% relative improvement in phrase recall.