Æȷοì
JUNE SIG SUNG
JUNE SIG SUNG
Mobile eXperience business, Samsung Electronics
samsung.comÀÇ À̸ÞÀÏ È®ÀεÊ
Á¦¸ñ
Àοë
Àοë
¿¬µµ
High quality streaming speech synthesis with low, sentence-length-independent latency
N Ellinas, G Vamvoukakis, K Markopoulos, A Chalamandaris, G Maniati, ...
arXiv preprint arXiv:2111.09052, 2021
422021
SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis
G Maniati, A Vioni, N Ellinas, K Nikitaras, K Klapsas, JS Sung, G Jho, ...
arXiv preprint arXiv:2204.03040, 2022
302022
Excitation modeling based on waveform interpolation for HMM-based speech synthesis.
JS Sung, DH Hong, KH Oh, NS Kim
Interspeech, 813-816, 2010
222010
Factored MLLR adaptation
NS Kim, JS Sung, DH Hong
IEEE Signal Processing Letters 18 (2), 99-102, 2010
212010
Cross-lingual low resource speaker adaptation using phonological features
G Maniati, N Ellinas, K Markopoulos, G Vamvoukakis, JS Sung, H Park, ...
arXiv preprint arXiv:2111.09075, 2021
152021
Vibrato learning in multi-singer singing voice synthesis
R Liu, X Wen, C Lu, L Song, JS Sung
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU ¡¦, 2021
102021
Speech reinforcement based on partial specific loudness.
JW Shin, W Lim, JS Sung, NS Kim
INTERSPEECH, 978-981, 2007
102007
Bunched LPCNet2: Efficient neural vocoders covering devices from cloud to edge
S Park, K Choo, J Lee, AV Porov, K Osipov, JS Sung
arXiv preprint arXiv:2203.14416, 2022
92022
Prosodic clustering for phoneme-level prosody control in end-to-end speech synthesis
A Vioni, M Christidou, N Ellinas, G Vamvoukakis, P Kakoulidis, T Kim, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and ¡¦, 2021
92021
Statistical approaches to excitation modeling in HMM-based speech synthesis
JS Sung, DH Hong, HW Koo, NS Kim
IEICE Transactions on Information and Systems 96 (2), 379-382, 2013
82013
Word-level style control for expressive, non-attentive speech synthesis
K Klapsas, N Ellinas, JS Sung, H Park, S Raptis
Speech and Computer: 23rd International Conference, SPECOM 2021, St ¡¦, 2021
72021
Factored MLLR adaptation for singing voice generation
JS Sung, DH Hong, SJ Kang, NS Kim
Twelfth Annual Conference of the International Speech Communication Association, 2011
72011
Investigating content-aware neural text-to-speech mos prediction using prosodic and linguistic features
A Vioni, G Maniati, N Ellinas, JS Sung, I Hwang, A Chalamandaris, ...
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and ¡¦, 2023
62023
Controllable speech synthesis by learning discrete phoneme-level prosodic representations
N Ellinas, M Christidou, A Vioni, JS Sung, A Chalamandaris, P Tsiakoulis, ...
Speech Communication 146, 22-31, 2023
52023
Fine-grained noise control for multispeaker speech synthesis
K Nikitaras, G Vamvoukakis, N Ellinas, K Klapsas, K Markopoulos, ...
arXiv preprint arXiv:2204.05070, 2022
52022
Factored maximum penalized likelihood kernel regression for HMM-based style-adaptive speech synthesis
JS Sung, DH Hong, NS Kim
IEEE Journal of Selected Topics in Signal Processing 8 (2), 251-261, 2014
52014
Factored MLLR adaptation algorithm for HMM-based expressive TTS
JS Sung, DH Hong, HW Koo, NS Kim
Proc. Interspeech 2012, 975-978, 2012
52012
A Novel Audio Fingerprinting Scheme based on Subband Envelop Hashing
Y Liu, HS Yun, JS Sung, NS Kim
Proceedings: APSIPA ASC 2009: Asia-Pacific Signal and Information Processing ¡¦, 2009
52009
Self-supervised learning for robust voice cloning
K Klapsas, N Ellinas, K Nikitaras, G Vamvoukakis, P Kakoulidis, ...
arXiv preprint arXiv:2204.03421, 2022
42022
Factored maximum likelihood kernelized regression for HMM-based singing voice synthesis.
JS Sung, DH Hong, HW Koo, NS Kim
Interspeech, 359-363, 2013
42013
ÇöÀç ½Ã½ºÅÛÀÌ ÀÛµ¿µÇÁö ¾Ê½À´Ï´Ù. ³ªÁß¿¡ ´Ù½Ã ½ÃµµÇØ ÁÖ¼¼¿ä.
ÇмúÀÚ·á 1–20