Skip to content

BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASR

Sep 2026 · 0 citations · 28 references
Computer Science

TL;DR

BaLEEN (Biasing with Latent Encoded Entities), a lightweight, hypernetwork-based framework for dynamic contextual adaptation without fine-tuning the underlying ASR model, is proposed.

Abstract

Transcribing domain-specific entities and rare proper nouns remains a major challenge in automatic speech recognition (ASR). In this paper, we propose BaLEEN (Biasing with Latent Encoded Entities), a lightweight, hypernetwork-based framework for dynamic contextual adaptation without fine-tuning the underlying ASR model. BaLEEN encodes variable-length contextual keywords using a pretrained language model, compresses them into a fixed sequence of latent vectors via a Perceiver bottleneck, and injects context-dependent bias vectors directly into the intermediate encoder representations of the ASR model. Because both the language model and the backbone ASR model remain entirely frozen during training, BaLEEN operates as a plug-and-play adapter that incurs zero computational overhead at inference time when context biases are precomputed. We evaluate our method on a CTC-based ASR model using a Wikipedia-derived corpus with annotated named entities and synthetic speech. Experimental results demonstrate that BaLEEN reduces keyword miss rate by 8.7% on the test set relative to the unbiased baseline while simultaneously improving overall word error rate by 21% and character error rate by 28%.

View source

Similar papers

#natural language process... Open access Sep 2026

SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ

This paper describes the system for Task~2 of the second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge, which adapt Qwen3-Omni-30B-A3B-Instruct with a segment-evidence-aware data and post-training pipeline and obtains 90.92% accuracy on the final official evaluation set.

H. Le, L. Nguyen, Minh Tri Dao · 1 citation
#artificial intelligence Preprint Sep 2026

Rules Amortize, Pairings Don't: Linguistic Structure Determines What Latent Task Representations Can Replace In-Context Learning

In-context learning (ICL) can be amortized into latent objects (task vectors, function vectors, context vectors) that recover few-shot behavior at zero-shot inference cost, but recent theory shows a static vector acts as a single synthetic demonstration and must fail on high-rank mappings such as word-level bijections....

Gunmay Jhingran · 0 citations
Conference Sep 2026

Enhancing Domain-Specific ASR via Dual-Stage RAG-Based Context Injection

Standard Automatic Speech Recognition (ASR) systems struggle to accurately transcribe dense, domain-specific terminology in academic lectures. This paper introduces a dual-stage context injection pipeline that enhances transcription quality through a multi-stage Retrieval-Augmented Generation (RAG) framework. Domain kn...

Andreas Lindner · 0 citations
#natural language process... Preprint Sep 2026

Reusing Latent Speech Representations for Query-Conditioned Topic Localization in Transcripts

To improve span localization, ASR encoder states are reuse ASR encoder states as sentence-level representations and fuse them with textual embeddings to let lightweight span locators exploit speech information without running a separate audio encoder.

Steffen Freisinger, Philipp Seeberger, Thomas Ranzenberger et al. · 0 citations
Open access 2026

A Dataset for Evaluating ASR on Specialized Vocabulary

A linguistically curated bilingual dataset comprising 13,846 utterances distributed across synthetic and literature-derived subsets, with OOV rates reaching up to 100%, and a diagnostic evaluation framework that partitions recognition performance into Biased Word Error Rate (B-WER), which targets domain-specific jargon...

Emily Haubert Klering, E. Cortes, Т. И. Черненко et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.