Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Jonas Rohnke"'
We present a Split Vector Quantized Variational Autoencoder (SVQ-VAE) architecture using a split vector quantizer for NTTS, as an enhancement to the well-known Variational Autoencoder (VAE) and Vector Quantized Variational Autoencoder (VQ-VAE) archit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2b8d1684f946b52c1dbeb86efdd84e2
http://arxiv.org/abs/2110.12539
http://arxiv.org/abs/2110.12539
Publikováno v:
INTERSPEECH
We present a neural text-to-speech system for fine-grained prosody transfer from one speaker to another. Conventional approaches for end-to-end prosody transfer typically use either fixed-dimensional or variable-length prosody embedding via a seconda
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::23a5de24ec69a253e40e2df5e8da1abe
Publikováno v:
INTERSPEECH
Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-human capabilities when considering isolated sentences. But something which is still lacking in order to achieve human-like communication is the dynamic variations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1305c02f1a3ae42200009ee4c8c19f6e
Autor:
G. Poole, Jonas Rohnke
Publikováno v:
78th EAGE Conference and Exhibition 2016.
Summary Simultaneous shooting increases acquisition efficiency by activating more than one source at the same time. This introduces blending noise that typically needs to be removed before data processing. We present a new deblending algorithm based
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b0c2cc913697d3aa0999077e76235f5
https://doi.org/10.3997/2214-4609.201600953
https://doi.org/10.3997/2214-4609.201600953
