# Explanations for Automatic Speech Recognition Source: [Explanations for Automatic Speech Recognition]() Collection index: [llms.txt]() Data updated: 2026-06-24T05:00:04.549Z Authors: Xiaoliang Wu, Peter Bell, Ajitha Rajan Published: 2023-02-27T11:09:19.000Z ## Abstract We address quality assessment for neural network based ASR by providing explanations that help increase our understanding of the system and ultimately help build trust in the system. Compared to simple classification labels, explaining transcriptions is more challenging as judging their correctness is not straightforward and transcriptions as a variable-length sequence is not handled by existing interpretable machine learning models. We provide an explanation for an ASR transcription as a subset of audio frames that is both a minimal and sufficient cause of the transcription. To do this, we adapt existing explainable AI (XAI) techniques from image classification-Statistical Fault Localisation(SFL) and Causal. Additionally, we use an adapted version of Local Interpretable Model-Agnostic Explanations (LIME) for ASR as a baseline in our experiments. We evaluate the quality of the explanations generated by the proposed techniques over three different ASR ,Google API, the baseline model of Sphinx, Deepspeech and 100 audio samples from the Commonvoice dataset. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [ASR Explanation Generation on Commonvoice (100 audio samples)](): ASR Explanation Generation; Commonvoice (100 audio samples); Consistency: 98. ## Original sources and implementation [Original paper]() [PDF]()