语音带宽扩展的分层递归神经网络 论文代码： Ling Zhen-Hua Ling，Yang Ai，Yu Gu和Dai Li-Rong Dai，“使用分层递归神经网络进行语音带宽扩展的波形建模和生成”，关于音频，语音和语言处理的IEEE / ACM交易，第一卷。 26号5，第883-894页，2018年。 ./HRNN_HF是本文中HRNN系统的代码。 ./CHRNN_HF是本文中的CHRNN系统的代码。

TF-VAE-GAN-DRAW ，和TensorFlow实现。 跑 VAE / GAN： python main.py --working_directory /tmp/gan --model vae 画： python main-draw.py --working_directory /tmp/gan 深度卷积生成对抗网络在使用默认参数的10个星期后产生了不错的结果。 ＃＃＃去做： 更复杂的数据。 添加 用空间变压器层替换当前的注意力机制

PredRNN：时空预测学习的递归神经网络 时空序列的预测性学习旨在通过从历史情境中学习来生成未来的图像，其中视觉动态被认为具有可通过成分子系统学习的模块化结构。 NeurIPS 2017的第一个版本 此存储库首先包含PredRNN （2017）的PyTorch实现[ ]，这是一个循环网络，具有一对以几乎独立的过渡方式运行的存储单元，最后形成了复杂环境的统一表示。 具体而言，除了LSTM的原始存储单元外，该网络还具有锯齿形存储流，该存储流以自下而上和自上而下的方式在所有层中传播，从而使学习到的RNN级别的视觉动态能够进行通信。 PredRNN-V2（2021）的新功能 此回购还包括PredRNN-V2 （2021）的实现[]，它在以下两个方面改进了PredRNN。 1.内存解耦 我们发现PredRNN中的一对存储单元包含不良的冗余功能，因此会出现存储解耦损失，从而鼓励他们学习视觉动力学的

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output alignment is unknown. The combination of these methods with the Long Short-term Memory RNN architecture has proved particularly fruitful, delivering state-of-the-art results in cursive handwriting recognition. However RNN performance in speech recognition has so far been disappointing, with better results returned by deep feedforward networks. This paper investigates deep recurrent neural networks, which combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs. When trained end-to-end with suitable regularisation, we find that deep Long Short-term Memory RNNs achieve a test set error of 17.7% on the TIMIT phoneme recognition benchmark, which to our knowledge is the best recorded score.

循环神经网络在语音识别中的应用 LSTM 双向RNN 双向lstm

关于深度学习神经网络参数更新方法的文献

Recurrent Neural Networks for Prediction offers a new insight into the learning algorithms, architectures and stability of recurrent neural networks and, consequently, will have instant appeal. It provides an extensive background for researchers, academics and postgraduates enabling them to apply such networks in new applications.