Whisper: Courtside Edition Enhancing ASR Performance Through LLM-Driven Context Generation

TL;DR

Whisper: Courtside Edition employs a multi-agent LLM pipeline to improve domain-specific ASR accuracy by generating context-aware prompts, significantly reducing word error rates without retraining the base model.

Contribution

The paper introduces a novel LLM-driven prompt augmentation pipeline that enhances Whisper's ASR performance in specialized domains without retraining.

Findings

Achieved a 17.0% relative reduction in WER on NBA commentary data.

Outperformed direct transcript post-editing in 40.1% of segments.

Degradation occurred in only 7.1% of segments.

Abstract

Domain-specific speech remains a persistent challenge for automatic speech recognition (ASR), even for state-of-the-art systems like OpenAI's Whisper. We introduce Whisper: Courtside Edition, a novel multi-agent large language model (LLM) pipeline that enhances Whisper transcriptions without retraining. The pipeline intercepts Whisper's initial transcript, applies specialized LLM agents for domain context identification, named entity recognition, and jargon detection, and generates compact prompts that guide Whisper's decoder. Evaluated on 421 NBA basketball commentary segments (a domain characterized by dense proper nouns and technical terminology) our best pipeline achieves a statistically significant 17.0% relative reduction in word error rate (WER; from 0.217 to 0.180, p<0.001). Improvements are observed in 40.1% of segments with degradation in only 7.1%, substantially outperforming direct transcript post-editing. These results demonstrate that prompt-based augmentation can deliver scalable domain adaptation for ASR, offering a practical alternative to costly model fine-tuning.