ToDo: @shunk031さんの運用方法が良さそうなのでそちらの方法に移行する。
- Deep Voice: Real-time Neural Text-to-Speech https://arxiv.org/abs/1702.07825
- Deep Voice 2: Multi-Speaker Neural Text-to-Speech http://research.baidu.com/wp-content/uploads/2017/05/Deep-Voice-2-Complete-Arxiv.pdf
- Fast Wavenet Generation Algorithm https://arxiv.org/abs/1611.09482
- WaveNet: A Generative Model for Raw Audio https://arxiv.org/abs/1609.03499
- Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders https://arxiv.org/abs/1704.01279
- SampleRNN: An Unconditional End-to-End Neural Audio Generation Model https://arxiv.org/abs/1612.07837
- Char2Wav: End-to-End Speech Synthesis http://www.josesotelo.com/speechsynthesis
- Generating Sequences With Recurrent Neural Networks https://arxiv.org/abs/1308.0850
- Tacotron: Towards End-to-End Speech Synthesis https://arxiv.org/abs/1703.10135
- Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks http://www.cs.toronto.edu/~graves/icml_2006.pdf
- Voice Conversion from Unaligned Corpora using Variational Autoencoding Wasserstein Generative Adversarial Networks https://arxiv.org/abs/1704.00849
- Robust speaker-adaptive hmm-based text-to-speech synthesis https://pdfs.semanticscholar.org/8434/758e69ca9674866663bf4fb4a4569e93aaed.pdf
- Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior Probabilities https://arxiv.org/abs/1704.02360
- Sampling-based speech parameter generation using moment-matching networks https://arxiv.org/abs/1704.03626
- Multi-Language Multi-Speaker Acoustic Modeling for LSTM-RNN based Statistical Parametric Speech Synthesis https://research.google.com/pubs/pub45400.html
- Deep Neural Network-Based Speaker Embeddings for End-To-End Speaker Verification http://danielpovey.com/files/2016_slt_xvector.pdf
- End-to-end text-dependent speaker verification https://research.google.com/pubs/pub44681.html
- Exploring Neural Transducers for End-to-End Speech Recognition https://arxiv.org/abs/1707.07413
- Neural Nets for Generating Music https://medium.com/artists-and-machine-intelligence/neural-nets-for-generating-music-f46dffac21c0
- 日本語テキスト音声合成用記号 http://www.jeita.or.jp/cgi-bin/standard/pdf.cgi?jk_n=1408&jk_pdf_file=20110307080703_8FnXHkG4Y0.pdf
- Deep Learning for Siri’s Voice: On-device Deep Mixture Density Networks for Hybrid Unit Selection Synthesis https://machinelearning.apple.com/2017/08/06/siri-voices.html
- Probabilistic acoustic tube: a probabilistic generative model of speech for speech analysis/synthesis http://proceedings.mlr.press/v22/ou12.html
- Investigating the shortcomings of HMM synthesis http://www.cstr.ed.ac.uk/downloads/publications/2013/ssw8_PS2-4_Merritt.pdf
- Generative Adversarial Network-based Postfilter for STFT Spectrograms http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/ganp_stft/index.html
- Deep Learning Techniques for Music Generation - A Survey https://arxiv.org/abs/1709.01620
- Transfer Learning for Speech and Language Processing https://arxiv.org/abs/1511.06066
- Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework https://arxiv.org/abs/1707.01670
- Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks https://arxiv.org/abs/1709.08041
- Statistical Voice Conversion with WaveNet-Based Waveform Generation http://www.isca-speech.org/archive/Interspeech_2017/abstracts/0986.html
- A neural parametric singing synthesizer https://arxiv.org/abs/1704.03809
- Lip Reading Sentences in the Wild https://arxiv.org/abs/1611.05358
- Sequence-to-Sequence Neural Net Models for Grapheme-to-Phoneme Conversion https://arxiv.org/abs/1506.00196
- Listening while Speaking: Speech Chain by Deep Learning https://arxiv.org/abs/1707.04879v1
- Deep Speaker: an End-to-End Neural Speaker Embedding System https://arxiv.org/abs/1705.02304
- EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding https://arxiv.org/abs/1507.08240
- Speech Enhancement Using Bayesian Wavenet http://www.isca-speech.org/archive/Interspeech_2017/abstracts/1672.html
- Pixel Recurrent Neural Networks https://arxiv.org/abs/1601.06759
- PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications https://arxiv.org/abs/1701.05517
- Fast Generation for Convolutional Autoregressive Models https://arxiv.org/abs/1704.06001
- Parallel Multiscale Autoregressive Density Estimation https://arxiv.org/abs/1703.03664
- Qualitatively characterizing neural network optimization problems https://arxiv.org/abs/1412.6544
- Deep Residual Learning for Image Recognition https://arxiv.org/abs/1512.03385
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift https://arxiv.org/abs/1502.03167
- Quasi-Recurrent Neural Networks https://arxiv.org/abs/1611.01576
- Human-level control through deep reinforcement learning http://www.davidqiu.com:8888/research/nature14236.pdf
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation https://arxiv.org/abs/1406.1078
- Neural Machine Translation by Jointly Learning to Align and Translate https://arxiv.org/abs/1409.0473
- A Neural Transducer https://arxiv.org/abs/1511.04868
- Visualizing Data using t-SNE https://lvdmaaten.github.io/publications/papers/JMLR_2008.pdf https://lvdmaaten.github.io/tsne/
- Attention Is All You Need https://arxiv.org/abs/1706.03762
- Attention and Augmented Recurrent Neural Networks http://distill.pub/2016/augmented-rnns
- Universal Intelligence: A Definition of Machine Intelligence https://arxiv.org/abs/0712.3329
- Convolutional Sequence to Sequence Learning https://arxiv.org/abs/1705.03122
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks https://arxiv.org/abs/1511.06434
- Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space https://arxiv.org/abs/1612.00005
- Wasserstein GAN https://arxiv.org/abs/1701.07875
- One Model To Learn Them All https://arxiv.org/abs/1706.05137
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation https://arxiv.org/abs/1609.08144
- A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning https://ronan.collobert.com/pub/matos/2008_nlp_icml.pdf
- Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems https://arxiv.org/abs/1508.01745
- Methods for Interpreting and Understanding Deep Neural Networks https://arxiv.org/abs/1706.07979
- End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results https://arxiv.org/abs/1412.1602
- Attention-Based Models for Speech Recognition https://arxiv.org/abs/1506.07503
- Listen, Attend and Spell https://arxiv.org/abs/1508.01211
- Multi-task Sequence to Sequence Learning https://arxiv.org/abs/1511.06114
- Multi-way, multilingual neural machine translation with a shared attention mechanism https://arxiv.org/abs/1601.01073
- Multilingual Language Processing From Bytes https://arxiv.org/abs/1512.00103
- Character-Aware Neural Language Models https://arxiv.org/abs/1508.06615
- Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation https://arxiv.org/abs/1508.02096
- Meta-Learning with Temporal Convolutions https://arxiv.org/abs/1707.03141
- Dual Learning for Machine Translation https://arxiv.org/abs/1611.00179
- FaceNet: A Unified Embedding for Face Recognition and Clustering https://arxiv.org/abs/1503.03832
- Adam: A Method for Stochastic Optimization https://arxiv.org/abs/1412.6980
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling https://arxiv.org/abs/1412.3555
- Grammar as a Foreign Language https://arxiv.org/abs/1412.7449
- Uncertainty in Deep Learning http://mlg.eng.cam.ac.uk/yarin/blog_2248.html
- Understanding Black-box Predictions via Influence Functions https://arxiv.org/abs/1703.04730
- Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses https://arxiv.org/abs/1708.07149
- Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning https://arxiv.org/abs/1702.03274
- Building Machines That Learn and Think Like People https://arxiv.org/abs/1604.00289
- Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models https://arxiv.org/abs/1706.06689
- A Deep Reinforcement Learning Chatbot https://arxiv.org/abs/1709.02349
- Squeeze-and-Excitation Networks https://arxiv.org/abs/1709.01507
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models https://arxiv.org/abs/1401.4082
- Auto-Encoding Variational Bayes https://arxiv.org/abs/1312.6114
- Learning deep architectures for ai https://www.iro.umontreal.ca/~lisa/pointeurs/TR1312.pdf
- From neural PCA to deep unsupervised learning https://arxiv.org/abs/1411.7783
- Deconstructing the Ladder Network Architecture https://arxiv.org/abs/1511.06430
- Neural Optimizer Search with Reinforcement Learning https://arxiv.org/abs/1709.07417
- Deep Predictive Learning: A Comprehensive Model of Three Visual Streams https://arxiv.org/abs/1709.04654
- Poincaré Embeddings for Learning Hierarchical Representations https://arxiv.org/abs/1705.08039
- Conditional Image Generation with PixelCNN Decoders https://arxiv.org/abs/1606.05328
- Generative Adversarial Networks https://arxiv.org/abs/1406.2661
- Sequence to sequence learning with neural networks https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf
- Highway Networks https://arxiv.org/abs/1505.00387
- Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation https://arxiv.org/abs/1611.04558
- Multi-Source Neural Translation https://arxiv.org/abs/1601.00710
- Fully Character-Level Neural Machine Translation without Explicit Segmentation https://arxiv.org/abs/1610.03017
- Polyglot Neural Language Models: A Case Study in Cross-Lingual Phonetic Representation Learning https://arxiv.org/abs/1605.03832
- Effective Approaches to Attention-based Neural Machine Translation https://arxiv.org/abs/1508.04025
- Long Short-Term Memory http://web.eecs.utk.edu/~itamar/courses/ECE-692/Bobby_paper1.pdf
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches https://arxiv.org/abs/1409.1259
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks https://arxiv.org/abs/1506.03099
- Twin Networks: Using the Future as a Regularizer https://arxiv.org/abs/1708.06742
- Learning Hierarchical Features from Generative Models https://arxiv.org/abs/1702.08396
- Improving neural networks by preventing co-adaptation of feature detectors https://arxiv.org/abs/1207.0580
- Visualizing and Understanding Neural Machine Translation http://aclanthology.coli.uni-saarland.de/pdf/P/P17/P17-1106.pdf
- Weighted Finite-State Transducers in Speech Recognition http://www.openfst.org/twiki/pub/FST/FstBackground/csl01.pdf
- SPEECH RECOGNITION WITH WEIGHTED FINITE-STATE TRANSDUCERS http://www.openfst.org/twiki/pub/FST/FstBackground/hbka.pdf
- Weighted Automata Algorithms http://www.cs.nyu.edu/~mohri/pub/hwa.pdf
- OpenFst: A General and Efficient Weighted Finite-State Transducer Library http://www.openfst.org/twiki/pub/FST/FstBackground/ciaa.pdf
- Natural Language Processing (almost) from Scratch http://www.jmlr.org/papers/volume12/collobert11a/collobert11a.pdf
- Probabilistic Typology: Deep Generative Models of Vowel Inventories https://arxiv.org/abs/1705.01684
- The Google File System https://research.google.com/archive/gfs.html
- Dynamo: Amazon’s Highly Available Key-value Store http://www.allthingsdistributed.com/2007/10/amazons_dynamo.html
- Bigtable: A Distributed Storage System for Structured Data https://research.google.com/archive/bigtable.html
- Simple Testing Can Prevent Most Critical Failures- An Analysis of Production Failures in Distributed Data-Intensive Systems https://www.usenix.org/system/files/conference/osdi14/osdi14-paper-yuan.pdf
- A comprehensive study of Convergent and Commutative Replicated Data Types https://hal.inria.fr/file/index/docid/555588/filename/techreport.pdf
- MapReduce: Simplified Data Processing on Large Clusters https://research.google.com/archive/mapreduce.html
- HAT, not CAP: Towards Highly Available Transactions https://www.usenix.org/system/files/conference/hotos13/hotos13-final80.pdf
- Highly Available Transactions: Virtues and Limitations https://arxiv.org/abs/1302.0309
- Use of Formal Methods at Amazon Web Services http://lamport.azurewebsites.net/tla/amazon.html
- Eventually Consistent - Revisited http://www.allthingsdistributed.com/2008/12/eventually_consistent.html
- Borg, Omega, and Kubernetes https://research.google.com/pubs/pub44843.html
- Design patterns for container-based distributed systems https://research.google.com/pubs/pub45406.html