# Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning

arXiv: https://arxiv.org/abs/2603.06505 · HTML: https://mlsanity.com/paper/2603.06505/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Prompting Large Language Models with Speech Recognition Abilities](https://mlsanity.com/paper/2307.11795/) (2023)
- [Deep context: end-to-end contextual speech recognition](https://mlsanity.com/paper/1808.02480/) (2018)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation](https://mlsanity.com/paper/2310.09424/) (2023)
- [Context-Aware Transformer Transducer for Speech Recognition](https://mlsanity.com/paper/2111.03250/) (2021)
- [Class LM and word mapping for contextual biasing in End-to-End ASR](https://mlsanity.com/paper/2007.05609/) (2020)
- [SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation](https://mlsanity.com/paper/2205.08180/) (2022)
- [Contextualized End-to-End Speech Recognition with Contextual Phrase Prediction Network](https://mlsanity.com/paper/2305.12493/) (2023)
- [Pseudo-Labeling for Massively Multilingual Speech Recognition](https://mlsanity.com/paper/2111.00161/) (2021)
- [CTC-Assisted LLM-Based Contextual ASR](https://mlsanity.com/paper/2411.06437/) (2024)
- [Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition](https://mlsanity.com/paper/2305.05271/) (2023)
- [Phoneme-aware Encoding for Prefix-tree-based Contextual ASR](https://mlsanity.com/paper/2312.09582/) (2023)
- [AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM](https://mlsanity.com/paper/2412.01145/) (2024)
- [Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods](https://mlsanity.com/paper/2509.13785/) (2025)
- [How to Connect Speech Foundation Models and Large Language Models? What Matters and What Does Not](https://mlsanity.com/paper/2409.17044/) (2024)
- [The Eloquence team submission for task 1 of MLC-SLM challenge](https://mlsanity.com/paper/2507.19308/) (2025)
- [End-to-end Automatic Speech Recognition and Speech Translation: Integration of Speech Foundational Models and LLMs](https://mlsanity.com/paper/2510.10329/) (2025)
- [Multilingual Speech Recognition Using Discrete Tokens with a Two-step Training Strategy](https://mlsanity.com/paper/2509.01900/) (2025)

## Abstract (arXiv)

Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isolated utterances. While recent efforts in context-aware ASR show promise, two key challenges persist: limited multilingual support and the absence of principled alignment between speech and contextual representations. In this paper, we introduce a context-aware multilingual ASR framework that supports diverse languages and accents while preserving the modularity of pretrained models. Our approach combines a frozen speech encoder and a decoder-only language model via a lightweight projection module, allowing structured context prompts, including dialogue history and biasing words, to guide transcription. To improve interaction between speech and context, we employ a contrastive learning objective that aligns their representations in a shared embedding space. Evaluations on over 1,500 hours of real-world conversational speech across 11 languages and 5 English dialects show that contextual input consistently improves recognition quality. Contrastive alignment provides additional gains when applied to different context types, with an overall performance gain of over 5%. These results highlight the importance of both contextual modeling and cross-modal alignment in multilingual ASR.