# CLAR: CIF-Localized Alignment for Retrieval-Augmented Speech LLM-Based Contextual ASR

arXiv: https://arxiv.org/abs/2603.25460 · HTML: https://mlsanity.com/paper/2603.25460/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- Placed in Speech recognition models and training, one of 11 directions in Speech and audio language models.
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Placed in

- Speech and audio language models / [Speech recognition models and training](https://mlsanity.com/speech/speech-recognition-models-and-training/)

## Builds on (most cited first, 25 of 25)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition](https://mlsanity.com/paper/2206.08317/) (2022)
- [AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale](https://mlsanity.com/paper/1808.10583/) (2018)
- [Qwen3-ASR Technical Report](https://mlsanity.com/paper/2601.21337/) (2026)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion](https://mlsanity.com/paper/2104.02194/) (2021)
- [CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition](https://mlsanity.com/paper/1905.11235/) (2019)
- [Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition](https://mlsanity.com/paper/2407.04675/) (2024)
- [Natural Language Supervision for General-Purpose Audio Representations](https://mlsanity.com/paper/2309.05767/) (2023)
- [FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration](https://mlsanity.com/paper/2501.14350/) (2025)
- [Fun-ASR Technical Report](https://mlsanity.com/paper/2509.12508/) (2025)
- [CTC-Assisted LLM-Based Contextual ASR](https://mlsanity.com/paper/2411.06437/) (2024)
- [SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability](https://mlsanity.com/paper/2308.03266/) (2023)
- [Efficient Streaming LLM for Speech Recognition](https://mlsanity.com/paper/2410.03752/) (2024)
- [BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLM](https://mlsanity.com/paper/2505.19179/) (2025)
- [Retrieval Augmented Correction of Named Entity Speech Recognition Errors](https://mlsanity.com/paper/2409.06062/) (2024)
- [Contextualization of ASR with LLM using phonetic retrieval-based augmentation](https://mlsanity.com/paper/2409.15353/) (2024)
- [Contextual Biasing of Named-Entities with Large Language Models](https://mlsanity.com/paper/2309.00723/) (2023)
- [PAC: Pronunciation-Aware Contextualized Large Language Model-based Automatic Speech Recognition](https://mlsanity.com/paper/2509.12647/) (2025)
- [Leveraging LLM for Stuttering Speech: A Unified Architecture Bridging Recognition and Event Detection](https://mlsanity.com/paper/2505.22005/) (2025)
- [Retrieval Augmented Generation based context discovery for ASR](https://mlsanity.com/paper/2509.19567/) (2025)
- [Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context](https://mlsanity.com/paper/2506.10779/) (2025)
- [Generative Annotation for ASR Named Entity Correction](https://mlsanity.com/paper/2508.20700/) (2025)
- [Retrieval-Augmented Self-Taught Reasoning Model with Adaptive Chain-of-Thought for ASR Named Entity Correction](https://mlsanity.com/paper/2602.12287/) (2026)

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

- [Training-Free Contextual ASR via SpeechLLM-Based Error-Aware Selective Retrieval](https://mlsanity.com/paper/2609.30694/) (2026)

## Abstract (arXiv)

Speech LLM-based ASR often struggles with named entities and long-tail words due to strong internal language-model priors. Retrieval-augmented biasing can help, but its effectiveness depends on accurate hotword localization in full-utterance speech under weak supervision. We propose CLAR, a dual-encoder speech-text retriever that uses Continuous Integrate-and-Fire (CIF) to learn monotonic token-level alignments without timestamps. With length-aware localized matching, CLAR anchors short-entity acoustic cues and reduces representation dilution and attention drift. The retriever is trained with a multi-granularity objective combining global and local segment-level contrastive losses and a CIF quantity constraint. At inference, top-ranked hotwords are injected as contextual prompts for the Speech LLM, improving recognition without shallow fusion. Experiments show that CLAR significantly improves hotword retrieval and reduces both CER and B-WER against strong contextual ASR baselines.