Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Diana Militaru"'
Autor:
Andreea Cătană, Enikő Kutasi, Zina Cuzmici‑Barabaș, Diana Militaru, Irina Iordănescu, Mariela Militaru
Publikováno v:
Experimental and Therapeutic Medicine. 23
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d512a0e40091384427824b42ed571f6
https://doi.org/10.3892/etm.2022.11294
https://doi.org/10.3892/etm.2022.11294
Autor:
Andreea Cătană, Ruxandra Simonescu‑Colan, Zina Cuzmici‑Barabaș, Diana Militaru, Irina Iordănescu, Mariela Militaru
Publikováno v:
Experimental and Therapeutic Medicine. 23
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::30cd20814a7860f5564028d20cc8f17e
https://doi.org/10.3892/etm.2022.11252
https://doi.org/10.3892/etm.2022.11252
Autor:
Inge Gavat, Diana Militaru
Publikováno v:
SpeD
This paper will discuss the progress made in Automatic Speech Recognition and Understanding (ASRU) by applying Deep Learning (DL) in the frame of acoustic modeling. After explaining the concept of DL, specific algorithms like Restricted Bolzmann Mach
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::63635d8efee0dc049db8e9124675d94b
https://doi.org/10.1109/sped.2015.7343074
https://doi.org/10.1109/sped.2015.7343074
Publikováno v:
SpeD
A very important step toward the goal of human-computer dialog using natural language is the identification of semantic relations between different constituents of texts or speech. The semantic relations that can be established between the words sens
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e7b9325fef5f2948a54c38917a17ef83
https://doi.org/10.1109/sped.2015.7343107
https://doi.org/10.1109/sped.2015.7343107
Autor:
Marilena Lazar, Diana Militaru
Publikováno v:
2015 7th International Conference on Electronics, Computers and Artificial Intelligence (ECAI).
The natural language processing became one of the most important fields of artificial intelligence because is related to the area of human-computer interaction using human languages (natural language generation, question answering, machine translatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::322ca896e06f9f1336f1b64cf234b970
https://doi.org/10.1109/ecai.2015.7301166
https://doi.org/10.1109/ecai.2015.7301166
Autor:
Oana G. Cula, Inge Gavat, Zica Valsan, Octavian Dumitru, Bogdan Sabac, Ovidiu Grigore, Diana Militaru
Publikováno v:
International Journal of Speech Technology. 5:259-268
The present paper describes the evolution of our work concerning the problem of speech recognition. Beginning with a classical hidden Markov model (HMM), we have investigated two ways to improve the performance of this basic structure. The first way
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8fda8e484171f4fe82b0c9068761ffe9
https://doi.org/10.1023/a:1020249008539
https://doi.org/10.1023/a:1020249008539
Autor:
Marilena Lazar, Diana Militaru
Publikováno v:
SpeD
Language modeling plays an important role in continuous speech recognition and understanding providing an improvement of their performances. But language modeling has been shown to be a difficult task due to the many sources of variability that are p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f163c1acc0bc84e029440ac1ea3e4c64
https://doi.org/10.1109/sped.2013.6682649
https://doi.org/10.1109/sped.2013.6682649
Autor:
Diana Militaru, Rastoceanu Florin
Publikováno v:
2010 8th International Conference on Communications.
In this paper, we describe an application of speaker verification using Romanian vowels as speaker's models in case of a small Romanian language database. Vowels models are obtained with continuous HMMs using re-training of the vowels models for ever
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6cbb08a9facfe5c3b5f046002e78bd7e
https://doi.org/10.1109/iccomm.2010.5509031
https://doi.org/10.1109/iccomm.2010.5509031
Publikováno v:
2009 Proceedings of the 5-th Conference on Speech Technology and Human-Computer Dialogue.
The ProtoLOGOS Romanian language automatic speech recognition and understanding system is based at the level of acoustical modeling on the statistical framework of hidden Markov models and at the linguistic level on a finite state grammar or a bigram
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::02ef85bb2f63da580bdd084966d0ad43
https://doi.org/10.1109/sped.2009.5156171
https://doi.org/10.1109/sped.2009.5156171
Publikováno v:
Speech Recognition
In sections 2 and 3 of this chapter we presented results obtained in continuous speech recognition and understanding experiments for Romanian language concerning the efficiency of: ? acoustical modeling based on monophones and triphones in continuous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::131157101b7f9c5a565d62f8fdc9113f
https://doi.org/10.5772/6360
https://doi.org/10.5772/6360
