Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Malisz, Zofia"'
We introduce an end-to-end neural speech synthesis system that uses the source-filter model of speech production. Specifically, we apply differentiable resonant filters to a glottal waveform generated by a neural vocoder. The aim is to obtain a contr
Externí odkaz:
http://arxiv.org/abs/2409.14823
We present a speech database and a phoneme-level language model of Polish. The database and model are designed for the analysis of prosodic and discourse factors and their impact on acoustic parameters in interaction with predictability effects. The
Externí odkaz:
http://arxiv.org/abs/2404.10112
Autor:
Zarazaga, Pablo Pérez, Malisz, Zofia
Whispered speech is characterised by a noise-like excitation that results in the lack of fundamental frequency. Considering that prosodic phenomena such as intonation are perceived through f0 variation, the perception of whispered prosody is relative
Externí odkaz:
http://arxiv.org/abs/2307.03168
We describe speaker-independent speech synthesis driven by a small set of phonetically meaningful speech parameters such as formant frequencies. The intention is to leverage deep-learning advances to provide a highly realistic signal generator that i
Externí odkaz:
http://arxiv.org/abs/2306.01957
Whispering is a ubiquitous mode of communication that humans use daily. Despite this, whispered speech has been poorly served by existing speech technology due to a shortage of resources and processing methodology. To remedy this, this paper provides
Externí odkaz:
http://arxiv.org/abs/2303.07442
Deep learning has revolutionised synthetic speech quality. However, it has thus far delivered little value to the speech science community. The new methods do not meet the controllability demands that practitioners in this area require e.g.: in liste
Externí odkaz:
http://arxiv.org/abs/2202.10973
Autor:
Malisz, Zofia, Włodarczak, Marcin, Buschmeier, Hendrik, Skubisz, Joanna, Kopp, Stefan, Wagner, Petra
Publikováno v:
Language Resources and Evaluation, 2016 Apr 01. 50(2), 411-442.
Externí odkaz:
http://www.jstor.org/stable/44131471
Autor:
Wagner, Petra, Beskow, Jonas, Betz, Simon, Edlund, Jens, Gustafson, Joakim, Eje Henter, Gustav, Le Maguer, Sébastien, Malisz, Zofia, Székely, Èva, Tånnander, Christina, Voße, Jana
Publikováno v:
PUB-Publications at Bielefeld University
Speech synthesis applications have become an ubiquity, in navigation systems, digital assistants or as screen or audio book readers. Despite their impact on the acceptability of the systems in which they are embedded, and despite the fact that differ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::6e8b93fcda9b567b53bbfd30a02726a4
https://pub.uni-bielefeld.de/record/2936378
https://pub.uni-bielefeld.de/record/2936378
Autor:
Malisz, Zofia, Henter, Gustav Eje, Valentini-Botinhao, Cassia, Watts, Oliver, Beskow, Jonas, Gustafson, Joakim
We discuss the circumstances that have led to a disjoint advancement of speech synthesis and phonetics in recent dec- ades. The difficulties mainly rest on the pursuit of orthogonal goals by the two fields: realistic vs. controllable synthetic speech
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a79b697483af880638129738186c92a
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-283134
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-283134
This study presents a database of controlled speech material as well as spontaneous Swedish conversation produced in modal and whispered voice. The database includes facial expression and head movement features tracked by a non-invasive and unobtrusi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::02ad28995c3b44bda400ad191b144bc6
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-283135
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-283135