Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Sigurgeirsson, Atli Thor"'
Autor:
Sigurgeirsson, Atli Thor, King, Simon
Reference-based Text-to-Speech (TTS) models can generate multiple, prosodically-different renditions of the same target text. Such models jointly learn a latent acoustic space during training, which can be sampled from during inference. Controlling t
Externí odkaz:
http://arxiv.org/abs/2305.10321
Autor:
Sigurgeirsson, Atli Thor, King, Simon
Some recent models for Text-to-Speech synthesis aim to transfer the prosody of a reference utterance to the generated target synthetic speech. This is done by using a learned embedding of the reference utterance, which is used to condition speech gen
Externí odkaz:
http://arxiv.org/abs/2303.04289
Autor:
Sigurgeirsson, Atli Thor, King, Simon
Appropriate prosody is critical for successful spoken communication. Contextual word embeddings are proven to be helpful in predicting prosody but do not allow for choosing between plausible prosodic renditions. Reference-based TTS models attempt to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb41da4fc6f2a3f75ce66070c9902423