Releasing a toolkit and comparing the performance of language embeddings across various spoken language identification datasets
Loading...
Access rights
openAccess
publishedVersion
URL
Journal Title
Journal ISSN
Volume Title
A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Date
2020
Major/Subject
Mcode
Degree programme
Language
en
Pages
5
Series
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Volume 2020-October, pp. 467-471, Interspeech
Abstract
In this paper, we propose a software toolkit for easier end-to-end training of deep learning based spoken language identification models across several speech datasets. We apply our toolkit to implement three baseline models, one speaker recognition model, and three x-vector architecture variations, which are trained on three datasets previously used in spoken language identification experiments. All models are trained separately on each dataset (closed task) and on a combination of all datasets (open task), after which we compare if the open task training yields better language embeddings. We begin by training all models end-to-end as discriminative classifiers of spectral features, labeled by language. Then, we extract language embedding vectors from the trained end-to-end models, train separate Gaussian Naive Bayes classifiers on the vectors, and compare which model provides best language embeddings for the back-end classifier. Our experiments show that the open task condition leads to improved language identification performance on only one of the datasets. In addition, we discovered that increasing x-vector model robustness with random frequency channel dropout significantly reduces its end-to-end classification performance on the test set, while not affecting back-end classification performance of its embeddings. Finally, we note that two baseline models consistently outperformed all other models.Description
| openaire: EC/H2020/780069/EU//MeMAD
Keywords
Deep learning, Language embedding, Spoken language identification, TensorFlow, X-vector
Other note
Citation
Lindgren, M, Jauhiainen, T & Kurimo, M 2020, Releasing a toolkit and comparing the performance of language embeddings across various spoken language identification datasets . in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH . vol. 2020-October, Interspeech, International Speech Communication Association (ISCA), pp. 467-471, Interspeech, Shanghai, China, 25/10/2020 . https://doi.org/10.21437/Interspeech.2020-2706