Songxiang Liu
Artificial Intelligence · 2019–2023
A researcher in the Science corpus: 8 papers; trusts 178 researchers and is trusted by 5 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 215 citations into it; #20,617 of 35,345 by trust here, #11,072 by citations
- Signal Processing — 163 citations into it; #4,758 of 7,572 by trust here, #1,820 by citations
- Speech & Audio — 137 citations into it
- Generative Models — 83 citations into it
- Computer Vision and Pattern Recognition — 75 citations into it
- Model Architectures — 24 citations into it
- Representation & Self-Supervised Learning — 17 citations into it
- Evaluation & Benchmarks — 14 citations into it
Whom Songxiang Liu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Alex Graves
- Yoshua Bengio
- Aäron van den Oord
- Alex Krizhevsky
- Ilya Sutskever
- Yann LeCun
- Jimmy Ba
- Kaiming He
Who trusts Songxiang Liu overall
- Rongjie Huang
- Dongchao Yang
- Cong Han
- Yuma Koizumi
- Vadim Popov
- Zhou Zhao
- Vinay S. Raghavan
- Kohei Yatabe
- Zeqian Ju
- Chunlei Zhang
Papers from Songxiang Liu's perspective
Ordered by how strongly the researchers Songxiang Liu trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- ImageNet classification with deep convolutional neural networks
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec (2023) — 231 citations
- InstructTTS: Modelling Expressive TTS in Discrete Latent Space With Natural Language Style Prompt (2023) — 174 citations
- DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs (2022) — 82 citations
- UniAudio: An Audio Foundation Model Toward Universal Audio Generation (2023) — 215 citations
- VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention (2021) — 24 citations
- Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling (2020) — 125 citations
- Code-Switched Speech Synthesis Using Bilingual Phonetic Posteriorgram with Only Monolingual Corpora (2020) — 22 citations
- End-to-end Code-switched TTS with Mix of Monolingual Recordings (2019) — 36 citations