Real-time correction of closed-captions

Cardinal, Patrick; Comeau, Michel; Boisvert, Maryse

doi:10.3115/1557769.1557803

Cited by 2 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The resulting list is named List h SimInter . Then, for each word pair (h, r) in Sub T est we enrich their corresponding confusion bins with the nearest neighbors of the hypothesis word (h) from LA SimInter , to have a bin size equals to 6 (this size seems relevant to visualize alternative words in a graphical user interface in a computer-assisted transcription software [26]). The list of competing words in the confusion bin is named List CN , and the one in the enriched confusion bin is named List EnrichCN .…”

Section: Enrichment Of Confusion Networkmentioning

confidence: 99%

Enriching Confusion Networks for Post-processing

Ghannay

Estève

Camelin

2017

Statistical Language and Speech Processing

View full text Add to dashboard Cite

The paper proposes a new approach for a posteriori enrichment of automatic speech recognition (ASR) confusion networks (CNs). CNs are usually needed to decrease word error rate and to compute confidence measures, but they are also used in many ways in order to improve post-processing of ASR outputs. For instance, they can be helpfully used to propose alternative word hypotheses when ASR outputs are corrected by a human on post-edition. However, CNs bins do not have a fixed length, and sometimes contain only one or two word hypotheses: in this case the number of alternatives to correct a misrecognized word is very low, reducing the chance of helping the human annotator. Our approach for CN enrichment is based on a new similarity measure presented in this paper, computed from acoustic and linguistic word embeddings, that allows us to take into consideration both acoustic and linguistic similarities between two words. Experimental results show that our approach is relevant: enriched CNs (for a bin size equals to 6) increase the potential correction of erroneous words by 23% than initial CNs produced by an ASR system. In our experiments, a spoken language understanding task is also targeted.

show abstract

Section: Enrichment Of Confusion Networkmentioning

confidence: 99%