2022
DOI: 10.48550/arxiv.2207.10849
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

ASR Error Detection via Audio-Transcript entailment

Abstract: 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 o… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 26 publications
0
2
0
Order By: Relevance
“…Nimshi et al used an acoustic encoder and a language encoder to model speech and text respectively, and fused the two coded representations to predict implications. When the ASR recognition results are completely correct, there should be a two-way implication between speech and text [18]. The above researches achieves automatic error detection of ASR recognition results, but manual correction work is still required.…”
Section: Research On Speech Recognition Error Correction Technologymentioning
confidence: 99%
See 1 more Smart Citation
“…Nimshi et al used an acoustic encoder and a language encoder to model speech and text respectively, and fused the two coded representations to predict implications. When the ASR recognition results are completely correct, there should be a two-way implication between speech and text [18]. The above researches achieves automatic error detection of ASR recognition results, but manual correction work is still required.…”
Section: Research On Speech Recognition Error Correction Technologymentioning
confidence: 99%
“…The error correction techniques in speech recognition, such as [16][17][18][19][20][21][22][23][24], can enhance the accuracy and reliability of speech recognition to a certain extent, reducing the need for manual intervention and correction. However, their limitations lie in their inability to effectively handle recognition errors in dialectal vocabulary and their inability to adapt to the speech recognition requirements of different industries.…”
Section: Research On Speech Recognition Error Correction Technologymentioning
confidence: 99%