Sequence Teacher-Student Training of Acoustic Models for Automatic Free Speaking Language Assessment
dc.contributor.author | Wang, Yu | |
dc.contributor.author | Wong, JHM | |
dc.contributor.author | Gales, Mark | |
dc.contributor.author | Knill, Katherine | |
dc.contributor.author | Ragni, Anton | |
dc.date.accessioned | 2019-01-12T00:30:24Z | |
dc.date.available | 2019-01-12T00:30:24Z | |
dc.date.issued | 2018 | |
dc.identifier.isbn | 9781538643341 | |
dc.identifier.issn | 2639-5479 | |
dc.identifier.uri | https://www.repository.cam.ac.uk/handle/1810/287878 | |
dc.description.abstract | A high performance automatic speech recognition (ASR) system is an important constituent component of an automatic language assessment system for free speaking language tests. The ASR system is required to be capable of recognising non-native spontaneous English speech and to be deployable under real-time conditions. The performance of ASR systems can often be significantly improved by leveraging upon multiple systems that are complementary, such as an ensemble. Ensemble methods, however, can be computationally expensive, often requiring multiple decoding runs, which makes them impractical for deployment. In this paper, a lattice-free implementation of sequence-level teacher-student training is used to reduce this computational cost, thereby allowing for real-time applications. This method allows a single student model to emulate the performance of an ensemble of teachers, but without the need for multiple decoding runs. Adaptations of the student model to speakers from different first languages (L1s) and grades are also explored. | |
dc.description.sponsorship | Cambridge Assessment English | |
dc.publisher | IEEE | |
dc.title | Sequence Teacher-Student Training of Acoustic Models for Automatic Free Speaking Language Assessment | |
dc.type | Conference Object | |
prism.endingPage | 1000 | |
prism.publicationDate | 2019 | |
prism.publicationName | 2018 IEEE Spoken Language Technology Workshop, SLT 2018 - Proceedings | |
prism.startingPage | 994 | |
dc.identifier.doi | 10.17863/CAM.35192 | |
dcterms.dateAccepted | 2018-09-03 | |
rioxxterms.versionofrecord | 10.1109/SLT.2018.8639557 | |
rioxxterms.version | AM | |
rioxxterms.licenseref.uri | http://www.rioxx.net/licenses/all-rights-reserved | |
rioxxterms.licenseref.startdate | 2019-02-11 | |
dc.contributor.orcid | Gales, Mark [0000-0002-5311-8219] | |
dc.contributor.orcid | Knill, Katherine [0000-0003-1292-2769] | |
rioxxterms.type | Conference Paper/Proceeding/Abstract | |
pubs.funder-project-id | Cambridge Assessment (unknown) | |
pubs.conference-name | 2018 IEEE Spoken Language Technology Workshop (SLT) | |
pubs.conference-start-date | 2018-12-18 | |
cam.orpheus.success | Thu Nov 05 11:53:18 GMT 2020 - Embargo updated | |
pubs.conference-finish-date | 2018-12-21 | |
rioxxterms.freetoread.startdate | 2020-02-11 |
Files in this item
This item appears in the following Collection(s)
-
Cambridge University Research Outputs
Research outputs of the University of Cambridge