Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Matt Shannon"'
Autor:
Daisy Stanton, Matt Shannon, Soroosh Mariooryad, RJ Skerry-Ryan, Eric Battenberg, Tom Bagby, David Kao
This work explores the task of synthesizing speech in nonexistent human-sounding voices. We call this task "speaker generation", and present TacoSpawn, a system that performs competitively at this task. TacoSpawn is a recurrent attention-based text-t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f6e83b22f13a9e01602b62b69bb268cc
http://arxiv.org/abs/2111.05095
http://arxiv.org/abs/2111.05095
Autor:
Eric Battenberg, David T. H. Kao, Tom Bagby, Soroosh Mariooryad, RJ Skerry-Ryan, Daisy Stanton, Matt Shannon
Publikováno v:
ICASSP
Despite the ability to produce human-level speech for in-domain text, attention-based end-to-end text-to-speech (TTS) systems suffer from text alignment failures that increase in frequency for out-of-domain text. We show that these failures can be ad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::44e108a9536d4f771709c9eb9d0e9391
Autor:
Kevin W. Wilson, Erik McDermott, Arun Narayanan, Olivier Siohan, Ananya Misra, Khe Chai Sim, Ehsan Variani, J. Caroselli, Izhak Shafran, Chanwoo Kim, Matt Shannon, Mitchel Weintraub, Ron Weiss, Michiel Bacchiani, Bo Li, Richard Rose, Golan Pundak, Hasim Sak, Tara N. Sainath, K. K. Chin
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c81b81dbb4343fdbb34ac3549f2b60d
https://doi.org/10.21437/interspeech.2017-234
https://doi.org/10.21437/interspeech.2017-234
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b461f2cb47538eff7e875479463fb7f5
https://doi.org/10.21437/interspeech.2017-1705
https://doi.org/10.21437/interspeech.2017-1705
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::945d1f524f232969fc17706d7f5b9bcf
https://doi.org/10.21437/interspeech.2017-496
https://doi.org/10.21437/interspeech.2017-496
Autor:
Matt Shannon
Publikováno v:
INTERSPEECH
State-level minimum Bayes risk (sMBR) training has become the de facto standard for sequence-level training of speech recognition acoustic models. It has an elegant formulation using the expectation semiring, and gives large improvements in word erro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2389930c2451cc3db1f14e70de78bdc3
Autor:
Minh Quang Tran, B. Meszaros, Fabio Cismondi, Sergio Ciattaglia, Matt Shannon, Angel Ibarra, M. Coleman, Louis Zani, M. Grattarola, Th. Franke, C. Bachmann, Michael Rieth, Lorenzo Virgilio Boccaccini, A. Loving, G. Federici, F. Maviglia, C. Morlock, E. Diegele, Wolfgang Biel, Ronald Wenninger, H Hurzlmeier, Ch. Day, N. Taylor, Jeong-Ha You
Publikováno v:
Fusion engineering and design 109-111(B), 1464-1474 (2016). doi:10.1016/j.fusengdes.2015.11.050
Fusion Engineering and Design
Fusion engineering and design, 109-111, 1464-1474
Fusion Engineering and Design
Fusion engineering and design, 109-111, 1464-1474
This paper describes the progress of the DEMO design and R&D activities in Europe. The focus is on a systems engineering and design integration approach, which is recognized to be essential from an early stage to identify and address the engineering
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9870cf2a6e75d710f1f9dbe7ef7245e0
https://hdl.handle.net/2128/13713
https://hdl.handle.net/2128/13713
Publikováno v:
INTERSPEECH
Henter, G E, Merritt, T, Shannon, M, Mayo, C & King, S 2014, Measuring the Perceptual Effects of Modelling Assumptions in Speech Synthesis Using Stimuli Constructed from Repeated Natural Speech . in INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association . pp. 1504-1508 . < http://www.isca-speech.org/archive/interspeech_2014/i14_1504.html >
Scopus-Elsevier
Henter, G E, Merritt, T, Shannon, M, Mayo, C & King, S 2014, Measuring the Perceptual Effects of Modelling Assumptions in Speech Synthesis Using Stimuli Constructed from Repeated Natural Speech . in INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association . pp. 1504-1508 . < http://www.isca-speech.org/archive/interspeech_2014/i14_1504.html >
Scopus-Elsevier
Acoustic models used for statistical parametric speech synthesis typically incorporate many modelling assumptions. It is an open question to what extent these assumptions limit the naturalness of synthesised speech. To investigate this question, we r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ed9bcafd62b4ecdd4a6eb42f96716b4
https://doi.org/10.21437/interspeech.2014-361
https://doi.org/10.21437/interspeech.2014-361
Publikováno v:
William Byrne
We propose using the autoregressive hidden Markov model (HMM) for speech synthesis. The autoregressive HMM uses the same model for parameter estimation and synthesis in a consistent way, in contrast to the standard approach to statistical parametric
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0fc0119b56a50f0065bb75d5aa440bea
http://www.dspace.cam.ac.uk/handle/1810/244407
http://www.dspace.cam.ac.uk/handle/1810/244407
Publikováno v:
Interspeech 2011.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::266f5bd3d0e3c632249b86db7a03c779
https://doi.org/10.21437/interspeech.2011-31
https://doi.org/10.21437/interspeech.2011-31