Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Large vocabulary speech recognition"'
Deep convolutional neural networks-based features for Indonesian large vocabulary speech recognition
Publikováno v:
IAES International Journal of Artificial Intelligence (IJ-AI). 12:610
There are great interests in developing speech recognition using deep learning technologies due to their capability to model the complexity of pronunciations, syntax, and language rules of speech data better than the traditional hidden Markov model (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d8b4bbf294aeb861ae6ea42c0f5efe54
https://doi.org/10.11591/ijai.v12.i2.pp610-617
https://doi.org/10.11591/ijai.v12.i2.pp610-617
We describe a novel way to implement subword language models in speech recognition systems based on weighted finite state transducers, hidden Markov models, and deep neural networks. The acoustic models are built on graphemes in a way that no pronunc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1d8015504640452d651cf873dbb44a5d
https://aaltodoc.aalto.fi/handle/123456789/47346
https://aaltodoc.aalto.fi/handle/123456789/47346
Publikováno v:
LANGUAGE RESOURCES AND EVALUATION. 51(4):961-987
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=CSC_________::f25a0d64023c1d98d62de52e267e09c8
http://juuli.fi/Record/0274691916
http://juuli.fi/Record/0274691916
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Mikko Kurimo, Tanel Alumäe, Ottokar Tilk, Seppo Enarvi, Matti Varjokallio, André Mansikkaniemi
One particular problem in large vocabulary continuous speech recognition for low-resourced languages is finding relevant training data for the statistical language models. Large amount of data is required, because models should estimate the probabili
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75eb82f22f817637d26241336d426e25
https://aaltodoc.aalto.fi/handle/123456789/27395
https://aaltodoc.aalto.fi/handle/123456789/27395
Publikováno v:
Proceedings of the 4th International Workshop on Spoken Language Technologies for Underresourced Languages
4th International Workshop on Spoken Language Technologies for Underresourced Languages
4th International Workshop on Spoken Language Technologies for Underresourced Languages, May 2014, Saint-Petersbourg, Russia. pp.53-60
4th International Workshop on Spoken Language Technologies for Underresourced Languages
4th International Workshop on Spoken Language Technologies for Underresourced Languages, May 2014, Saint-Petersbourg, Russia. pp.53-60
International audience; Luxembourgish, embedded in a multilingual context on the divide between Romance and Germanic cultures, remains one of Europe’s under-described languages. In this paper, we propose to study acoustic similarities between Luxem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4d6b7ba784daaca4b7ee6255f383fd1e
https://hal.archives-ouvertes.fr/hal-01134824
https://hal.archives-ouvertes.fr/hal-01134824
Publikováno v:
Actes des XXXe Journées d'Études sur la Parole (JEP'14)
XXXe Journées d'Études sur la Parole (JEP'14)
XXXe Journées d'Études sur la Parole (JEP'14), Jun 2014, Le Mans, France. pp.284-292
XXXe Journées d'Études sur la Parole (JEP'14)
XXXe Journées d'Études sur la Parole (JEP'14), Jun 2014, Le Mans, France. pp.284-292
Luxembourgish, a Germanic-Franconian language, is embedded in a multilingual context on the divide between Romance and Germanic cultures and remains one of Europe’s under-described languages. This paper investigates the similarity between Luxembour
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::216ccc62f83ceca19bf07681010a04ee
https://hal.science/hal-01134888
https://hal.science/hal-01134888
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Mohit Agarwal, Lukas Burget, Martin Karafiat, Pinar Akyazi, Richard Rose, Ondrej Glembek, Petr Schwarz, Samuel Thomas, Nagendra Kumar Goel, Daniel Povey, Arnab Ghoshal, Kai Feng, Ariya Rastrow
Publikováno v:
ICASSP
Although research has previously been done on multilingual speech recognition, it has been found to be very difficult to improve over separately trained systems. The usual approach has been to use some kind of “universal phone set” that covers mu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::afd2f03438b95a84f412ba40c9ec8427
https://doi.org/10.1109/icassp.2010.5495646
https://doi.org/10.1109/icassp.2010.5495646