Zobrazeno 1 - 10
of 79
pro vyhledávání: '"Gao, Jiameng"'
Autor:
Gao, Jiameng
In this paper we describe our entry for the VoiceMOS Challenge 2022 for both the main and out-of-domain (OOD) track of the competition. Our system is based on finetuning pre-trained self-supervised waveform prediction models, while improving its gene
Externí odkaz:
http://arxiv.org/abs/2204.03967
Autor:
Zhang, Nan, Zhang, Qingqing, Zhang, Zhiyuan, Yu, Jing, Fu, Yu, Gao, Jiameng, Jiang, Xuemei, Jiang, Ping, Wen, Zongmei
Publikováno v:
In International Immunopharmacology 30 September 2024 139
Publikováno v:
In Journal of Environmental Management September 2024 368
Publikováno v:
Clinical & Translational Discovery. Aug2024, Vol. 4 Issue 4, p1-10. 10p.
Autor:
Yu, Jing, Fu, Yu, Gao, Jiameng, Zhang, Qingqing, Zhang, Nan, Zhang, Zhiyuan, Jiang, Xuemei, Chen, Chang, Wen, Zongmei
Publikováno v:
In Redox Biology August 2024 74
Autor:
Mohan, Devang S Ram, Hu, Vivian, Teh, Tian Huey, Torresquintero, Alexandra, Wallis, Christopher G. R., Staib, Marlene, Foglianti, Lorenzo, Gao, Jiameng, King, Simon
Text does not fully specify the spoken form, so text-to-speech models must be able to learn from speech data that vary in ways not explained by the corresponding text. One way to reduce the amount of unexplained variation in training data is to provi
Externí odkaz:
http://arxiv.org/abs/2106.08352
Autor:
Torresquintero, Alexandra, Teh, Tian Huey, Wallis, Christopher G. R., Staib, Marlene, Mohan, Devang S Ram, Hu, Vivian, Foglianti, Lorenzo, Gao, Jiameng, King, Simon
Text-to-speech is now able to achieve near-human naturalness and research focus has shifted to increasing expressivity. One popular method is to transfer the prosody from a reference speech sample. There have been considerable advances in using proso
Externí odkaz:
http://arxiv.org/abs/2106.08321
Publikováno v:
In Asian Journal of Surgery January 2024 47(1):380-388
Autor:
Mohan, Devang S Ram, Lenain, Raphael, Foglianti, Lorenzo, Teh, Tian Huey, Staib, Marlene, Torresquintero, Alexandra, Gao, Jiameng
Modern approaches to text to speech require the entire input character sequence to be processed before any audio is synthesised. This latency limits the suitability of such models for time-sensitive tasks like simultaneous interpretation. Interleavin
Externí odkaz:
http://arxiv.org/abs/2008.03096
Autor:
Staib, Marlene, Teh, Tian Huey, Torresquintero, Alexandra, Mohan, Devang S Ram, Foglianti, Lorenzo, Lenain, Raphael, Gao, Jiameng
Code-switching---the intra-utterance use of multiple languages---is prevalent across the world. Within text-to-speech (TTS), multilingual models have been found to enable code-switching. By modifying the linguistic input to sequence-to-sequence TTS,
Externí odkaz:
http://arxiv.org/abs/2008.04107