Show simple item record

dc.contributor.authorLi, Qiujiaen
dc.contributor.authorNess, Prebenen
dc.contributor.authorRagni, Antonen
dc.contributor.authorGales, Marken
dc.date.accessioned2019-02-16T00:30:41Z
dc.date.available2019-02-16T00:30:41Z
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/289495
dc.description.abstractThe standard approach to mitigate errors made by an automatic speech recognition system is to use confidence scores associated with each predicted word. In the simplest case, these scores are word posterior probabilities whilst more complex schemes utilise bi-directional recurrent neural network (BiRNN) models. A number of upstream and downstream applications, however, rely on confidence scores assigned not only to 1-best hypotheses but to all words found in confusion networks or lattices. These include but are not limited to speaker adaptation, semi-supervised training and information retrieval. Although word posteriors could be used in those applications as confidence scores, they are known to have reliability issues. To make improved confidence scores more generally available, this paper shows how BiRNNs can be extended from 1-best sequences to confusion network and lattice structures. Experiments are conducted using one of the Cambridge University submissions to the IARPA OpenKWS 2016 competition. The results show that confusion network and lattice-based BiRNNs can provide a significant improvement in confidence estimation.
dc.description.sponsorshipIARPA MATERIAL, ALTA Institute
dc.titleBI-DIRECTIONAL LATTICE RECURRENT NEURAL NETWORKS FOR CONFIDENCE ESTIMATIONen
dc.typeConference Object
dc.identifier.doi10.17863/CAM.36745
dcterms.dateAccepted2019-02-01en
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2019-02-01en
dc.contributor.orcidGales, Mark [0000-0002-5311-8219]
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.funder-project-idCambridge Assessment (unknown)
pubs.conference-name2019 IEEE International Conference on Acoustics, Speech, and Signal Processingen
pubs.conference-start-date2019-05-12en
cam.orpheus.counter14*
rioxxterms.freetoread.startdate2022-02-15


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record