Zobrazeno 1 - 10
of 83
pro vyhledávání: '"Fabio Brugnara"'
Publikováno v:
Speech Communication. 51:499-509
In automatic speech recognition applications, due to significant differences in voice characteristics, adults and children are usually treated as two population groups, for which different acoustic models are trained. In this paper, age-independent a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b7d7773f920bc66e25c9cca4571ae137
https://doi.org/10.1016/j.specom.2009.01.006
https://doi.org/10.1016/j.specom.2009.01.006
Publikováno v:
Speech Communication. 49:847-860
This paper presents several acoustic analyses carried out on read speech collected from Italian children aged from 7 to 13 years and North American children aged from 5 to 17 years. These analyses aimed at achieving a better understanding of spectral
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65184ec6ad80e7002af883993b046c13
https://doi.org/10.1016/j.specom.2007.01.002
https://doi.org/10.1016/j.specom.2007.01.002
Publikováno v:
Computer Speech & Language. 20:107-123
In this paper, speaker adaptive acoustic modeling is investigated by using a novel method for speaker normalization and a well known vocal tract length normalization method. With the novel normalization method, acoustic observations of training and t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a2b253f8cadcd7ce48c0a8f586f93705
https://doi.org/10.1016/j.csl.2005.05.002
https://doi.org/10.1016/j.csl.2005.05.002
Publikováno v:
Speech Communication. 38:335-347
This paper reports on experiments of porting the ITC-irst Italian broadcast news recognition system to two spontaneous dialogue domains. Porting was investigated by applying state-of-the-art adaptation methods on acoustic and language models, and by
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bb0622eb2acded1cb10d649bdd469a1c
https://doi.org/10.1016/s0167-6393(01)00074-7
https://doi.org/10.1016/s0167-6393(01)00074-7
Autor:
Fabio Brugnara, Diego Giuliani
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a27d671789bc90ad6d18f952f9440c9c
https://doi.org/10.21437/interspeech.2013-732
https://doi.org/10.21437/interspeech.2013-732
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642358272
EVALITA
EVALITA
In this paper we describe design, setup and results of the speech recognition task in the framework of the Evalita campaign for the Italian language, giving details on the released corpora and tools used for the challenge. A general discussion about
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::85b2ac7994d7419d27ae04e55192ba00
https://doi.org/10.1007/978-3-642-35828-9_30
https://doi.org/10.1007/978-3-642-35828-9_30
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642358272
EVALITA
EVALITA
This report describes the system used in FBK for participating in the large vocabulary Automatic Speech Recognition tasks of the Evalita 2011 evaluation campaign. The paper provides some details on the techniques included in the transcription system.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::974950cf215e359a4da4332831398c09
https://doi.org/10.1007/978-3-642-35828-9_32
https://doi.org/10.1007/978-3-642-35828-9_32
Publikováno v:
Computer Speech & Language. 9:353-379
This paper considers the problems of estimating bigram language models and of efficiently representing them by a finite state network, which can be employed by a hidden Markov model based, beam-search, continuous speech recognizer. A review of the be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::614091f3d8c7456303e8b397243a5f7c
https://doi.org/10.1006/csla.1995.0017
https://doi.org/10.1006/csla.1995.0017
Publikováno v:
Computer Speech & Language. 9:107-121
A speaker-independent automatic speech recognition system is developed using hidden Markov models (HMMs). Simulated annealing and randomized search are used to optimize discrete features of the system, including topologies, parameter ties, context cl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::adb64774bae284e77c8e549da56f7037
https://doi.org/10.1006/csla.1995.0007
https://doi.org/10.1006/csla.1995.0007
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad495a9cd7b1cc32d711880f0e7800f0
https://doi.org/10.21437/interspeech.2012-399
https://doi.org/10.21437/interspeech.2012-399