Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Shangkun Huang, Huan Shen, Wei Zou, Yunzhang Chen• 2026

Related benchmarks

TaskDatasetResultRank
Contextual Automatic Speech RecognitionAISHELL-1-NE (test)
CER0.92
4
Hotword RetrievalAISHELL-1-NE (test)
F1 Score97.03
3
Showing 2 of 2 rows

Other info

Follow for update