深度学习论文专栏

深度学习论文专栏

以下，建立论文阅读专栏，一是为提高论文阅读能力，二是为保证知识更新，三是为了记录和传播好的论文思想
以下仅做粗浅分类，方便查阅，持续更新…

arXiv论文怎么读？
arXiv.org主页：https://arxiv.org/
axXiv of Audio and Speech Processing: https://arxiv.org/list/eess.AS/recent
axXiv of Computer Science (since January 1993): https://arxiv.org/archive/cs

一、NLP
1、Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention 【https://arxiv.org/pdf/2006.16236.pdf】2020新作待读

二、语音
1、Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions 【https://arxiv.org/pdf/1712.05884.pdf】 tacotron2
2、FastSpeech: Fast, Robust and Controllable Text to Speech 【https://arxiv.org/abs/1905.09263】fastspeech
3、FastSpeech 2: Fast and High-Quality End-to-End Text to Speech 【https://arxiv.org/abs/2006.04558】fastspeech-2
4、Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided attention【https://arxiv.org/abs/1710.08969】guide attention
5、Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron (Google, ICML 2018)
6、Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis (Google, ICML 2018)
7、Prosody Transfer in Neural Text to Speech Using Global Pitch and Loudness Features (2019)
8、Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens (NVIDIA, ICASSP 2020)
9、Hierarchical Generative Modeling for Controllable Speech Synthesis (Google, ICLR 2019)
10、Using VAEs and Normalizing Flows for One-shot Text-To-Speech Synthesis of Expressive Speech (Amazon, ICASSP 2020)
11、Multi-reference Tacotron by Intercross Training for Style Disentangling, Transfer and Control in Speech Synthesis (Baidu, interspeech 2019)
12、Multi-Reference Neural TTS Stylization with Adversarial Cycle Consistency (Microsoft, 2019)
13、Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesis (Apple, ICASSP 2020)
14、Disentangling Correlated Speaker and Noise for Speech Synthesis via Data Augmentation and Adversarial Factorization (Google, NeurIPS 2018)

三、其他
1、