Unsupervised Word Segmentation from Speech with Attention
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU136058" target="_blank" >RIV/00216305:26230/18:PU136058 - isvavai.cz</a>
Result on the web
<a href="https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1308.pdf" target="_blank" >https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1308.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21437/Interspeech.2018-1308" target="_blank" >10.21437/Interspeech.2018-1308</a>
Alternative languages
Result language
angličtina
Original language name
Unsupervised Word Segmentation from Speech with Attention
Original language description
We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing between recordings in the UL with translations in a well-resourced language. It uses Acoustic Unit Discovery (AUD) to convert speech into a sequence of pseudo-phones that is segmented using neural soft-alignments produced by a neural machine translation model. Evaluation uses an actual Bantu UL, Mboshi; comparisons to monolingual and bilingual baselines illustrate the potential of attentional word segmentation for language documentation.
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
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceeding of Interspeech 2018
ISBN
—
ISSN
1990-9772
e-ISSN
—
Number of pages
5
Pages from-to
2678-2682
Publisher name
International Speech Communication Association
Place of publication
Hyderabad
Event location
Hyderabad, India
Event date
Sep 2, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000465363900561