no code implementations • 24 May 2023 • Rongjie Huang, Huadai Liu, Xize Cheng, Yi Ren, Linjun Li, Zhenhui Ye, Jinzheng He, Lichao Zhang, Jinglin Liu, Xiang Yin, Zhou Zhao
Direct speech-to-speech translation (S2ST) aims to convert speech from one language into another, and has demonstrated significant progress to date.
no code implementations • 22 May 2023 • Huadai Liu, Rongjie Huang, Xuan Lin, Wenqiang Xu, Maozong Zheng, Hong Chen, Jinzheng He, Zhou Zhao
To mitigate the data scarcity in learning visual acoustic information, we 1) introduce a self-supervised learning framework to enhance both the visual-text encoder and denoiser decoder; 2) leverage the diffusion transformer scalable in terms of parameters and capacity to learn visual scene information.
no code implementations • 21 May 2023 • Huadai Liu, Rongjie Huang, Jinzheng He, Gang Sun, Ran Shen, Xize Cheng, Zhou Zhao
Speech-to-SQL (S2SQL) aims to convert spoken questions into SQL queries given relational databases, which has been traditionally implemented in a cascaded manner while facing the following challenges: 1) model training is faced with the major issue of data scarcity, where limited parallel data is available; and 2) the systems should be robust enough to handle diverse out-of-domain speech samples that differ from the source data.
no code implementations • 18 May 2023 • Jinzheng He, Jinglin Liu, Zhenhui Ye, Rongjie Huang, Chenye Cui, Huadai Liu, Zhou Zhao
To tackle these challenges, we propose RMSSinger, the first RMS-SVS method, which takes realistic music scores as input, eliminating most of the tedious manual annotation and avoiding the aforementioned inconvenience.
3 code implementations • 13 Jul 2022 • Rongjie Huang, Zhou Zhao, Huadai Liu, Jinglin Liu, Chenye Cui, Yi Ren
Through the preliminary study on diffusion model parameterization, we find that previous gradient-based TTS models require hundreds or thousands of iterations to guarantee high sample quality, which poses a challenge for accelerating sampling.
1 code implementation • 25 May 2022 • Rongjie Huang, Jinglin Liu, Huadai Liu, Yi Ren, Lichao Zhang, Jinzheng He, Zhou Zhao
Specifically, a sequence of discrete representations derived in a self-supervised manner are predicted from the model and passed to a vocoder for speech reconstruction, while still facing the following challenges: 1) Acoustic multimodality: the discrete units derived from speech with same content could be indeterministic due to the acoustic property (e. g., rhythm, pitch, and energy), which causes deterioration of translation accuracy; 2) high latency: current S2ST systems utilize autoregressive models which predict each unit conditioned on the sequence previously generated, failing to take full advantage of parallelism.