Zobrazeno 1 - 10
of 20
pro vyhledávání: '"ZAINKÓ, CSABA"'
Neural network-based Text-to-Speech has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron2, FastSpeech, FastPitch) usually generate Mel-spectrogram from text and then synthesize speech using vocoder (e.g., Wa
Externí odkaz:
http://arxiv.org/abs/2208.07122
Autor:
Gyires-Tóth, Bálint, Zainkó, Csaba
MOS (Mean Opinion Score) is a subjective method used for the evaluation of a system's quality. Telecommunications (for voice and video), and speech synthesis systems (for generated speech) are a few of the many applications of the method. While MOS t
Externí odkaz:
http://arxiv.org/abs/2204.11030
Autor:
Zainkó, Csaba, Tóth, László, Shandiz, Amin Honarmandi, Gosztolya, Gábor, Markó, Alexandra, Németh, Géza, Csapó, Tamás Gábor
For articulatory-to-acoustic mapping, typically only limited parallel training data is available, making it impossible to apply fully end-to-end solutions like Tacotron2. In this paper, we experimented with transfer learning and adaptation of a Tacot
Externí odkaz:
http://arxiv.org/abs/2107.12051
To date, various speech technology systems have adopted the vocoder approach, a method for synthesizing speech waveform that shows a major role in the performance of statistical parametric speech synthesis. WaveNet one of the best models that nearly
Externí odkaz:
http://arxiv.org/abs/2106.06863
For articulatory-to-acoustic mapping using deep neural networks, typically spectral and excitation parameters of vocoders have been used as the training targets. However, vocoding often results in buzzy and muffled final speech quality. Therefore, in
Externí odkaz:
http://arxiv.org/abs/2008.03152
Autor:
Teixeira, António, Hämäläinen, Annika, Avelar, Jairo, Almeida, Nuno, Németh, Géza, Fegyó, Tibor, Zainkó, Csaba, Csapó, Tamás, Tóth, Bálint, Oliveira, André, Dias, Miguel Sales
Publikováno v:
In Procedia Computer Science 2014 27:389-397
Autor:
Németh, Géza, Zainkó, Csaba
Publikováno v:
Acta Linguistica Hungarica (Since 2017 Acta Linguistica Academica). 49(3-4):385-405
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=626072
The WaveNet architecture is suitable to generate high quality speech, it was demonstrated for English by Google DeepMind. In this paper we de- scribe our experiments of using WaveNet for Hungarian speech generation. We investigated the effects of dif
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::abd40739bf9cad1321f4bc0f60d53ca0
Publikováno v:
Text, Speech & Dialogue (9783642157592); 2010, p455-463, 9p
Autor:
Gardner-Bonneau, Daryle, Blanchard, Harry E., Németh, Géza, Kiss, Géza, Zainkó, Csaba, Olaszy, Gábor, Tóth, Bálint
Publikováno v:
Human Factors & Voice Interactive Systems; 2008, p163-191, 29p