Reference-free and Confidence-independent Binary Quality Estimation for Automatic Speech Recognition
Fiche du document
11 novembre 2016
- doi: 10.4000/books.aaccademia.1562
- eisbn: 9788899200008
https://creativecommons.org/licenses/by-nc-nd/4.0/ , info:eu-repo/semantics/openAccess
Mots-clés
research Linguistics Computational Linguistics Fondazione Bruno Kessler language linguistica linguistica computazionale Fondazione Bruno Kessler linguaggio ricerca linguistique linguistique computationelle Fondazione Bruno Kessler langage recherche Multidisciplinary Linguistics LAN025000 GLSujets proches
Linguistic science Science of languageCiter ce document
Hamed Zamani et al., « Reference-free and Confidence-independent Binary Quality Estimation for Automatic Speech Recognition », Accademia University Press, ID : 10.4000/books.aaccademia.1562
Métriques
Partage / Export
Résumé
We address the problem of assigning binary quality labels to automatically transcribed utterances when neither reference transcripts nor information about the decoding process are accessible. Our quality estimation models are evaluated in a large vocabulary continuous speech recognition setting (the transcription of English TED talks). In this setting, we apply different learning algorithms and strategies and measure performance in two testing conditions characterized by different distributions of “good” and “bad” instances. The positive results of our experiments pave the way towards the use of binary estimators of ASR output quality in a number of application scenarios.