Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Nikolaos Ellinas"'
Autor:
Konstantinos Klapsas, Nikolaos Ellinas, Karolos Nikitaras, Georgios Vamvoukakis, Panagiotis Kakoulidis, Konstantinos Markopoulos, Spyros Raptis, June Sig Sung, Gunu Jho, Aimilios Chalamandaris, Pirros Tsiakoulis
Publikováno v:
Interspeech 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4bf5393cfdae9a92c669692863b0575b
https://doi.org/10.21437/interspeech.2022-10856
https://doi.org/10.21437/interspeech.2022-10856
Autor:
Georgia Maniati, Alexandra Vioni, Nikolaos Ellinas, Karolos Nikitaras, Konstantinos Klapsas, June Sig Sung, Gunu Jho, Aimilios Chalamandaris, Pirros Tsiakoulis
In this work, we present the SOMOS dataset, the first large-scale mean opinion scores (MOS) dataset consisting of solely neural text-to-speech (TTS) samples. It can be employed to train automatic MOS prediction systems focused on the assessment of mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cc651faeaa04115356a3dc709682b63a
http://arxiv.org/abs/2204.03040
http://arxiv.org/abs/2204.03040
Autor:
Nikolaos Ellinas, Georgios Vamvoukakis, Tae-Hoon Kim, Aimilios Chalamandaris, Panos Kakoulidis, Hyoungmin Park, Myrsini Christidou, Alexandra Vioni, June Sig Sung, Pirros Tsiakoulis
Publikováno v:
ICASSP
This paper presents a method for controlling the prosody at the phoneme level in an autoregressive attention-based text-to-speech system. Instead of learning latent prosodic features with a variational framework as is commonly done, we directly extra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::17c8aee70c6bacd61d322c38a73e80b8
http://arxiv.org/abs/2111.10177
http://arxiv.org/abs/2111.10177
Autor:
Aimilios Chalamandaris, Georgios Vamvoukakis, Nikolaos Ellinas, Konstantinos Markopoulos, Pirros Tsiakoulis, June Sig Sung, Hyoungmin Park, Georgia Maniati
The idea of using phonological features instead of phonemes as input to sequence-to-sequence TTS has been recently proposed for zero-shot multilingual speech synthesis. This approach is useful for code-switching, as it facilitates the seamless utteri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a24fc2c09faa4d72db9308dddd537a4
http://arxiv.org/abs/2111.09075
http://arxiv.org/abs/2111.09075
Autor:
Konstantinos Markopoulos, Myrsini Christidou, June Sig Sung, Aimilios Chalamandaris, Pirros Tsiakoulis, Georgios Vamvoukakis, Alexandra Vioni, Panos Kakoulidis, Hyoungmin Park, Nikolaos Ellinas, Georgia Maniati
In this paper, a text-to-rapping/singing system is introduced, which can be adapted to any speaker's voice. It utilizes a Tacotron-based multispeaker acoustic model trained on read-only speech data and which provides prosody control at the phoneme le
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16fb08b35ac399ca9b1c19767b2451d6
http://arxiv.org/abs/2111.09146
http://arxiv.org/abs/2111.09146
Publikováno v:
Speech and Computer ISBN: 9783030878016
This paper presents an expressive speech synthesis architecture for modeling and controlling the speaking style at a word level. It attempts to learn word-level stylistic and prosodic representations of the speech data, with the aid of two encoders.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::45db24cd3ea30df1691209cfd13f7a66
https://doi.org/10.1007/978-3-030-87802-3_31
https://doi.org/10.1007/978-3-030-87802-3_31
Autor:
Pirros Tsiakoulis, Panos Kakoulidis, June Sig Sung, Konstantinos Markopoulos, Myrsini Christidou, Nikolaos Ellinas, Alexandra Vioni, Georgios Vamvoukakis, Aimilios Chalamandaris, Hyoungmin Park
Publikováno v:
Speech and Computer ISBN: 9783030878016
This paper presents a method for phoneme-level prosody control of F0 and duration on a multispeaker text-to-speech setup, which is based on prosodic clustering. An autoregressive attention-based model is used, incorporating multispeaker architecture
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cdaf2cb1601bb31210d84862c313de8d
https://doi.org/10.1007/978-3-030-87802-3_11
https://doi.org/10.1007/978-3-030-87802-3_11
Autor:
June Sig Sung, Spyros Raptis, Pirros Tsiakoulis, Nikolaos Ellinas, Aimilios Chalamandaris, Hyoungmin Park, Georgia Maniati, Georgios Vamvoukakis, Panos Kakoulidis, Konstantinos Markopoulos
Publikováno v:
INTERSPEECH
This paper presents an end-to-end text-to-speech system with low latency on a CPU, suitable for real-time applications. The system is composed of an autoregressive attention-based sequence-to-sequence acoustic model and the LPCNet vocoder for wavefor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::13c056ca9a78a01703950c53571922b5
https://doi.org/10.21437/interspeech.2020-2464
https://doi.org/10.21437/interspeech.2020-2464
Autor:
Alexandros Potamianos, Georgios Paraskevopoulos, Christos Baziotis, Athanasia Kolovou, Nikolaos Ellinas, Pinelopi Papalampidi, Athanasiou Nikolaos
Publikováno v:
SemEval@NAACL-HLT
In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3 "Irony detection in English tweets". We design and ensemble two independent models, based on recurrent neural networks (Bi-LSTM), which operate at the word and ch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aab7d17530539bed28172bd717fb319a
http://arxiv.org/abs/1804.06659
http://arxiv.org/abs/1804.06659
Autor:
Alexandros Potamianos, Christos Baziotis, Georgios Paraskevopoulos, Athanasia Kolovou, Athanasiou Nikolaos, Nikolaos Ellinas
Publikováno v:
SemEval@NAACL-HLT
In this paper we present a deep-learning model that competed at SemEval-2018 Task 2 "Multilingual Emoji Prediction". We participated in subtask A, in which we are called to predict the most likely associated emoji in English tweets. The proposed arch
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8863444f9d01988230c196af8c081c7b