A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU142915" target="_blank" >RIV/00216305:26230/21:PU142915 - isvavai.cz</a>
Result on the web
<a href="https://www.fit.vut.cz/research/publication/12523/" target="_blank" >https://www.fit.vut.cz/research/publication/12523/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP39728.2021.9414899" target="_blank" >10.1109/ICASSP39728.2021.9414899</a>
Alternative languages
Result language
angličtina
Original language name
A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery
Original language description
In this work, we propose a hierarchical subspace model for acoustic unit discovery. In this approach, we frame the task as one of learning embeddings on a low-dimensional phonetic subspace, and simultaneously specify the subspace itself as an embedding on a hyper- subspace. We train the hyper-subspace on a set of transcribed languages and transfer it to the target language. In the target language, we infer both the language and unit embeddings in an unsupervised manner, and in so doing, we simultaneously learn a subspace of units specific to that language and the units that dwell on it. We conduct experiments on TIMIT and two low-resource languages: Mboshi and Yoruba. Results show that our model outperforms major acoustic unit discovery techniques, both in terms of clustering quality and segmentation accuracy.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ISBN
978-1-7281-7605-5
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
3710-3714
Publisher name
IEEE Signal Processing Society
Place of publication
Toronto, Ontario
Event location
Toronto, Canada
Event date
Jun 6, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000704288403193