Non-Intrusive Automatic Speech Recognition Refinement: A Survey

TL;DR

This survey reviews non-intrusive methods for refining automatic speech recognition systems, categorizing approaches, discussing evaluation metrics, and highlighting future research directions.

Contribution

It provides a comprehensive classification and analysis of non-intrusive ASR refinement techniques, along with evaluation standards and research gaps.

Findings

Five main classes of refinement methods identified: fusion, re-scoring, correction, distillation, training adjustment.

Evaluation datasets and metrics are reviewed to standardize comparison of methods.

Open research gaps and future directions are proposed for improving ASR refinement.

Abstract

Automatic Speech Recognition (ASR) is an integral component of modern technology, powering applications such as voice-activated assistants, transcription services, and accessibility tools. Yet ASR systems continue to struggle with the inherent variability of human speech, such as accents, dialects, and speaking styles, as well as environmental interference, including background noise. Moreover, domain-specific conversations often employ specialized terminology, which can exacerbate transcription errors. These shortcomings not only degrade raw ASR accuracy but also propagate mistakes through subsequent natural language processing pipelines. Because redesigning an ASR model is costly and time-consuming, non-intrusive refinement techniques that leave the model's architecture intact have become increasingly popular. In this survey, we review current non-intrusive refinement approaches and group them into five classes: fusion, re-scoring, correction, distillation, and training adjustment. For each class, we outline the main methods, advantages, drawbacks, and ideal application scenarios. Beyond method classification, this work surveys adaptation techniques aimed at refining ASR in domain-specific contexts, reviews commonly used evaluation datasets along with their construction processes, and proposes a standardized set of metrics to facilitate fair comparisons. Finally, we identify open research gaps and suggest promising directions for future work. By providing this structured overview, we aim to equip researchers and practitioners with a clear foundation for developing more robust, accurate ASR refinement pipelines.