Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-31932
Title: | Cross-Domain Adaptation of Spoken Language Identification for Related Languages: The Curious Case of Slavic Languages |
Author(s): | Abdullah, Badr M. Avgustinova, Tania Möbius, Bernd Klakow, Dietrich |
Language: | English |
Title: | Cognitive intelligence for speech processing : 21st Annual Conference of the International Speech Communication Association (INTERSPEECH 2020) : held online due to Covid-19 : Shanghai, China, 25-29 October 2020 |
Startpage: | 477 |
Endpage: | 481 |
Publisher/Platform: | Curran Associates, Inc. |
Year of Publication: | 2020 |
Place of publication: | Red Hook, NY |
Title of the Conference: | Interspeech 2020 |
Place of the conference: | Shanghai, China |
Publikation type: | Conference Paper |
Abstract: | State-of-the-art spoken language identification (LID) systems, which are based on end-to-end deep neural networks, have shown remarkable success not only in discriminating between distant languages but also between closely-related languages or even different spoken varieties of the same language. However, it is still unclear to what extent neural LID models generalize to speech samples with different acoustic conditions due to domain shift. In this paper, we present a set of experiments to investigate the impact of domain mismatch on the performance of neural LID systems for a subset of six Slavic languages across two domains (read speech and radio broadcast) and examine two low-level signal descriptors (spectral and cepstral features) for this task. Our experiments show that (1) out-of-domain speech samples severely hinder the performance of neural LID models, and (2) while both spectral and cepstral features show comparable performance within-domain, spectral features show more robustness under domain mismatch. Moreover, we apply unsupervised domain adaptation to minimize the discrepancy between the two domains in our study. We achieve relative accuracy improvements that range from 9% to 77% depending on the diversity of acoustic conditions in the source domain. |
DOI of the first publication: | 10.21437/Interspeech.2020-2930 |
URL of the first publication: | https://www.isca-speech.org/archive/Interspeech_2020/abstracts/2930.html |
Link to this record: | hdl:20.500.11880/30651 http://dx.doi.org/10.22028/D291-31932 |
ISBN: | 978-1-7138-2069-7 |
Date of registration: | 17-Feb-2021 |
Notes: | Volume 1 |
Faculty: | P - Philosophische Fakultät |
Department: | P - Sprachwissenschaft und Sprachtechnologie |
Professorship: | P - Prof. Dr. Bernd Möbius |
Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
There are no files associated with this item.
Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.