Please use this identifier to cite or link to this item:
https://doi.org/10.21437/Interspeech.2017-391
DC Field | Value | |
---|---|---|
dc.title | Exploiting untranscribed broadcast data for improved code-switching detection | |
dc.contributor.author | Yilmaz E. | |
dc.contributor.author | Henk van den Heuvel | |
dc.contributor.author | David van Leeuwen | |
dc.date.accessioned | 2018-08-02T04:58:55Z | |
dc.date.available | 2018-08-02T04:58:55Z | |
dc.date.issued | 2017-01-01 | |
dc.identifier.citation | Yilmaz E., Henk van den Heuvel, David van Leeuwen (2017-01-01). Exploiting untranscribed broadcast data for improved code-switching detection. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2017-August : 42-46. ScholarBank@NUS Repository. https://doi.org/10.21437/Interspeech.2017-391 | |
dc.identifier.issn | 2308457X | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/145521 | |
dc.description.abstract | We have recently presented an automatic speech recognition (ASR) system operating on Frisian-Dutch code-switched speech. This type of speech requires careful handling of unexpected language switches that may occur in a single utterance. In this paper, we extend this work by using some raw broadcast data to improve multilingually trained deep neural networks (DNN) that have been trained on 11.5 hours of manually annotated bilingual speech. For this purpose, we apply the initial ASR to the untranscribed broadcast data and automatically create transcriptions based on the recognizer output using different language models for rescoring. Then, we train new acoustic models on the combined data, i.e., the manually and automatically transcribed bilingual broadcast data, and investigate the automatic transcription quality based on the recognition accuracies on a separate set of development and test data. Finally, we report code-switching detection performance elaborating on the correlation between the ASR and the code-switching detection performance. | |
dc.language.iso | en | |
dc.publisher | ISCA | |
dc.subject | Bilingual ASR, Code-switching, Frisian language, Under-resourced languages | |
dc.type | Conference Paper | |
dc.contributor.department | ELECTRICAL & COMPUTER ENGINEERING | |
dc.description.doi | 10.21437/Interspeech.2017-391 | |
dc.description.sourcetitle | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | |
dc.description.volume | 2017-August | |
dc.description.page | 42-46 | |
dc.published.state | Published | |
dc.grant.id | NWO Project 314-99-119 (Frisian Audio Mining Enterprise) | |
dc.grant.fundingagency | Nederlandse Organisatie voor Wetenschappelijk Onderzoek | |
Appears in Collections: | Elements Staff Publications |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
Interspeech2017_1.pdf | 283.18 kB | Adobe PDF | OPEN | Post-print | View/Download |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.