Search results
Creating Personalized Synthetic Voices from Articulation Impaired Speech Using Augmented Reconstruction Loss. Y Tian, J Li, T Lee. ICASSP 2024, 2024. 2024. Articles 1–8. PhD in Electronic...
Aug 30, 2024 · User-Driven Voice Generation and Editing through Latent Space Navigation. no code implementations • 30 Aug 2024 • Yusheng Tian, Junbin Liu, Tan Lee. This paper presents a user-driven approach for synthesizing highly specific target voices based on user feedback, which is particularly beneficial for speech-impaired individuals who wish to ...
Experience: iFLYTEK Co., Ltd. · Location: New Territories · 45 connections on LinkedIn. View Yusheng 钰笙 Tian 田’s profile on LinkedIn, a professional community of 1 billion members.
- Hefei, Anhui, China
- iFLYTEK Co., Ltd.
- 40
- 49
May 18, 2023 · View a PDF of the paper titled Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data, by Yusheng Tian and 2 other authors. Creating synthetic voices with found data is challenging, as real-world recordings often contain various types of audio degradation.
- arXiv:2305.10891 [eess.AS]
- Audio and Speech Processing (eess.AS)
- Accepted to ASRU 2023
Sep 10, 2019 · The film, directed by Tian Yusheng, is a Chinese adaptation from the South Korean buddy comedy "The Last Ride" by Nam Dae-joong. The story is about an 18-year-old youth Gao Yuan (played by Peng Yuchang) with a terminal disease who hopes to lose his virginity before he dies.
Yusheng Tian, Wei Liu, Tan Lee. Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR. ABSTRACT. etic voices with found data is challeng-ing, as real-world recordings often contain various types of audio degradation. One way to address this problem is to .
ABSTRACT. networks (CNNs) have been applied to extracting speaker embeddings with significant success in spe. ker verification. Incorporating the attention mechanism has shown to be effective in improving the m. del performance. This paper presents an efficient two-dimensional convolution-based attention module, namely C2D-Att. The interaction bet
