Zejun Ma
Artificial Intelligence · with Wang · 2019–2023
A researcher in the Science corpus: 6 papers; trusts 19 researchers and is trusted by 0 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 116 citations into it
- Signal Processing — 68 citations into it
- Computer Vision and Pattern Recognition — 20 citations into it
- Evaluation & Benchmarks — 9 citations into it
Whom Zejun Ma trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
Papers from Zejun Ma's perspective
Ordered by how strongly the researchers Zejun Ma trusts endorse each paper. Same corpus, a different order for every researcher.
- Attention is All you Need (Neural Information Processing Systems)
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- ImageNet classification with deep convolutional neural networks
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Long Short-Term Memory
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Distributed Representations of Words and Phrases and their Compositionality (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
Their papers
- HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection (2022) — 442 citations
- Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias (2023) — 101 citations
- PolyVoice: Language Models for Speech to Speech Translation (2023) — 35 citations
- A Chapter-Wise Understanding System for Text-To-Speech in Chinese Novels (2021) — 15 citations
- A Hybrid Text Normalization System Using Multi-Head Self-Attention For Mandarin (2019) — 17 citations
- A Unified Sequence-to-Sequence Front-End Model for Mandarin Text-to-Speech Synthesis (2019) — 28 citations