Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Gemello, Roberto"'
In this paper, we propose a dual-encoder ASR architecture for joint modeling of close-talk (CT) and far-talk (FT) speech, in order to combine the advantages of CT and FT devices for better accuracy. The key idea is to add an encoder selection network
Externí odkaz:
http://arxiv.org/abs/2109.08744
In this paper, we apply Semi-Supervised Learning (SSL) along with Data Augmentation (DA) for improving the accuracy of End-to-End ASR. We focus on the consistency regularization principle, which has been successfully applied to image classification t
Externí odkaz:
http://arxiv.org/abs/2007.13876
Autor:
Albesano, Dario, Baggia, Paolo, Danieli, Morena, Gemello, Roberto, Gerbino, Elisabetta, Rullent, Claudio
This paper presents Dialogos, a real-time system for human-machine spoken dialogue on the telephone in task-oriented domains. The system has been tested in a large trial with inexperienced users and it has proved robust enough to allow spontaneous in
Externí odkaz:
http://arxiv.org/abs/cmp-lg/9612004
Publikováno v:
In Speech Communication 2007 49(10):827-835
Publikováno v:
In Computer Speech & Language 2006 20(1):2-21
Publikováno v:
In Information Sciences 2000 123(1):3-11
Autor:
Potamianos, Alexandros, Bouselmi, Ghazi, Dimitriadis, Dimitrios, Fohr, Dominique, Gemello, Roberto, Illina, Irina, Mana, Franco, Maragos, Petros, Matassoni, M., Pitsikalis, Vassilis, Ramirez, J., Sanchez-Soto, E., Segura, J., Svaizer, P.
Publikováno v:
SRIV'06 ITRW on Speech Recognition and Intrinsic Variation
SRIV'06 ITRW on Speech Recognition and Intrinsic Variation, May 2006, Toulouse, France
SRIV'06 ITRW on Speech Recognition and Intrinsic Variation, May 2006, Toulouse, France
In this paper, we present algorithms for dealing with variability and mismatch in speech recognition due to environmental conditions and non-native speaker populations. The proposed algorithms cover a broad spectrum of ideas including robust feature
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::26e5e4f5d4eef3788eb0dcad4d89954b
https://hal.science/hal-00110502/file/hiwire_sriv06.pdf
https://hal.science/hal-00110502/file/hiwire_sriv06.pdf
Publikováno v:
In Pattern Recognition Letters 2010 31(11):1302-1309
Publikováno v:
2006 14th European Signal Processing Conference; 2006, p1-4, 4p
Publikováno v:
IEEE Signal Processing Letters; Jan2006, Vol. 13 Issue 1, p56-59, 4p, 4 Charts, 2 Graphs