ASR Error Detection via Audio-Transcript entailment

Meripo, Nimshi Venkat; Konam, Sandeep

doi:10.21437/interspeech.2022-11177

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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: Related Workmentioning

confidence: 99%

“…The error correction techniques in speech recognition, such as [16–24], 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: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An enhanced method for dialect transcription via error‐correcting thesaurus

Ma,

Deng,

et al. 2023

IET Communications

View full text Add to dashboard Cite

Automatic speech recognition (ASR) has been widely used in the field of customer service, but the performance of general ASR in dialect transcription is not satisfactory, especially in Guangdong Province. Targeted training of ASR transcription engine will produce effect, but the training cost is high, and it is not suitable for small‐scale training with multiple dialects and frequencies. The complaint problems in the customer service field have obvious clustering and are suitable for few‐shot and multi‐frequency training. In view of this, in the actual engineering application, the method of ASR transcribed into the dialect error correction thesaurus is tried to be used to replace the wrong words, and have achieved good results. The optimization technology after automatic speech transcription proposed in this study can improve the recognition accuracy of general ASR by 13.75% for dialect words.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%