Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Benjamin Milde"'
Autor:
Benjamin Milde, Chris Biemann
Publikováno v:
INTERSPEECH
The Sparsespeech model is an unsupervised acoustic model that can generate discrete pseudo-labels for untranscribed speech. We extend the Sparsespeech model to allow for sampling over a random discrete variable, yielding pseudo-posteriorgrams. The de
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3d237831e6992ec623ac4b65b748e64
https://doi.org/10.21437/interspeech.2020-2629
https://doi.org/10.21437/interspeech.2020-2629
Autor:
Benjamin Milde, Chris Biemann
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ebb09db6c0385a80c7b899b731deb089
https://doi.org/10.21437/interspeech.2019-2938
https://doi.org/10.21437/interspeech.2019-2938
Autor:
Chris Biemann, Benjamin Milde
Publikováno v:
INTERSPEECH
We introduce "Unspeech" embeddings, which are based on unsupervised learning of context feature representations for spoken language. The embeddings were trained on up to 9500 hours of crawled English speech data without transcriptions or speaker info
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2dc2104d73278f2d9e0471624d18519f
https://doi.org/10.21437/interspeech.2018-2194
https://doi.org/10.21437/interspeech.2018-2194
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e32880d298fd13ab074dcda19ad735b3
https://doi.org/10.21437/interspeech.2017-1436
https://doi.org/10.21437/interspeech.2017-1436
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783319455099
TSD
TSD
With the increasing popularity of deep learning approaches in the field of speech recognition and classification many of such problems are encountering a paradigm shift from classic approaches, such as hidden Markov models, to recurrent neural networ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::778a8a3f43ecbcbc33130976c8ac8dbb
https://doi.org/10.1007/978-3-319-45510-5_50
https://doi.org/10.1007/978-3-319-45510-5_50
Publikováno v:
PARS: Parallel-Algorithmen, -Rechnerstrukturen und -Systemsoftware. 28:28-37
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::371fadf06a59e94fb9aae2a3374b5b00
https://doi.org/10.1007/bf03341982
https://doi.org/10.1007/bf03341982
Autor:
Benjamin Milde, Chris Biemann
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::275ae8d446cad616bc9ee56558ef7689
https://doi.org/10.21437/interspeech.2015-192
https://doi.org/10.21437/interspeech.2015-192
Autor:
Stefan Radomski, Evandro B. Gouvêa, Benjamin Milde, Max Mühlhäuser, Arvid Lange, Stephan Radeck-Arneth, Chris Biemann
Publikováno v:
Text, Speech, and Dialogue ISBN: 9783319240329
TSD
TSD
We present a new freely available corpus for German distant speech recognition and report speaker-independent word error rate WER results for two open source speech recognizers trained on this corpus. The corpus has been recorded in a controlled envi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::794bd723988d9e708755a0292fb179fc
https://doi.org/10.1007/978-3-319-24033-6_54
https://doi.org/10.1007/978-3-319-24033-6_54
Publikováno v:
IFIP Advances in Information and Communication Technology ISBN: 9783642214233
SEC
SEC
CAPTCHAs are small puzzles which should be easily solvable by human beings but hard to solve for computers. They build a security cornerstone of the modern Internet service landscape, deployed in essentially any kind of login service, allowing to dis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::24253fd2e201b9ba0a580b9f77d5fb3d
https://doi.org/10.1007/978-3-642-21424-0_5
https://doi.org/10.1007/978-3-642-21424-0_5
Autor:
Michael Schneider, Benjamin Milde
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783642231773
PaCT
PaCT
The security of lattice based cryptography can be considered to be based on the hardness of the shortest vector problem (SVP) in lattices. Sieving algorithms can be used to solve this problem, at least in small dimensions. The most promising among th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e77822b3c6bb716104e8107d9801680e
https://doi.org/10.1007/978-3-642-23178-0_40
https://doi.org/10.1007/978-3-642-23178-0_40