Weakly Supervised Medication Regimen Extraction from Medical Conversations

Patel, Dhruvesh; Konam, Sandeep; Selvaraj, Sai P.

doi:10.48550/arxiv.2010.05317

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beyond dictation solutions, there has also been an uptick in adopting manual scribing solutions to reduce the documentation burden so that physicians can focus more on patient care. More recently, there has been a growing interest in leveraging the ASR transcripts and automating parts of the scribing workflows using spoken conversation understanding technologies such as utterance classification [5], information extraction [6,7,8], and conversation summarization [9]. Since speech recognition is upstream of all these dictation and scribing-centered documentation workflows, words mistranscribed by the ASR system [10] can be problematic, leading to users performing time-consuming and laborious corrections [11].…”

Section: Introductionmentioning

confidence: 99%

ASR Error Detection via Audio-Transcript entailment

Meripo¹,

Konam²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Despite improved performances of the latest Automatic Speech Recognition (ASR) systems, transcription errors are still unavoidable. These errors can have a considerable impact in critical domains such as healthcare, when used to help with clinical documentation. Therefore, detecting ASR errors is a critical first step in preventing further error propagation to downstream applications. To this end, we propose a novel end-to-end approach for ASR error detection using audio-transcript entailment. To the best of our knowledge, we are the first to frame this problem as an end-to-end entailment task between the audio segment and its corresponding transcript segment. Our intuition is that there should be a bidirectional entailment between audio and transcript when there is no recognition error and vice versa. The proposed model utilizes an acoustic encoder and a linguistic encoder to model the speech and transcript respectively. The encoded representations of both modalities are fused to predict the entailment. Since doctor-patient conversations are used in our experiments, a particular emphasis is placed on medical terms. Our proposed model achieves classification error rates (CER) of 26.2% on all transcription errors and 23% on medical errors specifically, leading to improvements upon a strong baseline by 12% and 15.4%, respectively.

show abstract