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.

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks including machine translation, handwriting synthesis [1, 2] and image caption generation [3]. We extend the attention-mechanism with features needed for speech recognition. We show that while an adaptation of the model used for machine translation in [2] reaches a competitive 18.7% phoneme error rate (PER) on the TIMIT phoneme recognition task, it can only be applied to utterances which are roughly as long as the ones it was trained on. We offer a qualitative explanation of this failure and propose a novel and generic method of adding location-awareness to the attention mechanism to alleviate this issue. The new method yields a model that is robust to long inputs and achieves 18% PER in single utterances and 20% in 10-times longer (repeated) utterances. Finally, we propose a change to the attention mechanism that prevents it from concentrating too much on single frames, which further reduces PER to 17.6% level.

In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU). We evaluate these recurrent units on the tasks of polyphonic music modeling and speech signal modeling. Our experiments revealed that these advanced recurrent units are indeed better than more traditional recurrent units such as tanh units. Also, we found GRU to be comparable to LSTM.

Recurrent Neural Networks can be trained to produce sequences of tokens given some input, as exemplified by recent results in machine translation and image captioning. The current approach to training them consists of maximizing the likelihood of each token in the sequence given the current (recurrent) state and the previous token. At inference, the unknown previous token is then replaced by a token generated by the model itself. This discrepancy between training and inference can yield errors that can accumulate quickly along the generated sequence. We propose a curriculum learning strategy to gently change the training process from a fully guided scheme using the true previous token, towards a less guided scheme which mostly uses the generated token instead. Experiments on several sequence prediction tasks show that this approach yields significant improvements. Moreover, it was used successfully in our winning entry to the MSCOCO image captioning challenge, 2015.

Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational components of typical LSTM variants. In this paper, we present the first large-scale analysis of eight LSTM variants on three representative tasks: speech recognition, handwriting recognition, and polyphonic music modeling. The hyperparameters of all LSTM variants for each task were optimized separately using random search, and their importance was assessed using the powerful fANOVA framework. In total, we summarize the results of 5400 experimental runs (≈ 15 years of CPU time), which makes our study the largest of its kind on LSTM networks. Our results show that none of the variants can improve upon the standard LSTM architecture significantly, and demonstrate the forget gate and the output activation function to be its most critical components. We further observe that the studied hyperparameters are virtually independent and derive guidelines for their efficient adjustment.

本文介绍了阿拉伯语多方面自动语音识别的设计与开发。深度神经网络正在成为解决顺序数据问题的有效工具，特别是采用系统的端到端培训。阿拉伯语语音识别是一个复杂的任务，因为存在多种方言，非可用性的大型语言和遗失的声音。因此，这项工作的第一种贡献是开发具有完全或至少部分发声转录的大型多方面语料库。此外，开源语料库已从多个源收集，通过定义公共字符集来对转录中的非标准阿拉伯字母表进行标准化。第二款贡献是开发框架，用于培训实现最先进的性能的声学模型。网络架构包括卷积和复发层的组合。音频数据的频谱图特征在频率VS时域中提取并在网络中馈送。通过复发模型产生的输出帧进一步训练以使音频特征与其相应的转录序列对齐。使用具有Tetra-Gram语言模型的波束搜索解码器来执行序列对准。所提出的系统实现了14％的错误率，以前优于以前的系统。

Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT'14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous best result on this task. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

长期记忆（LSTM）经常性网络经常用于涉及时间序列数据（例如语音识别）的任务。与以前的LSTM加速器相比，它可以利用空间重量稀疏性或时间激活稀疏性，本文提出了一种称为“ Spartus”的新加速器，该加速器可利用时空的稀疏性来实现超低潜伏期推断。空间稀疏性是使用新的圆柱平衡的靶向辍学（CBTD）结构化修剪法诱导的，从而生成平衡工作负载的结构化稀疏重量矩阵。在Spartus硬件上运行的修剪网络可实现高达96％和94％的重量稀疏度，而Timit和LibrisPeech数据集的准确性损失微不足道。为了在LSTM中诱导时间稀疏性，我们将先前的Deltagru方法扩展到Deltalstm方法。将时空的稀疏与CBTD和Deltalstm相结合，可以节省重量存储器访问和相关的算术操作。 Spartus体系结构是可扩展的，并且在大小FPGA上实现时支持实时在线语音识别。 1024个神经元的单个deltalstm层的Spartus每样本延迟平均1 US。使用TIMIT数据集利用我们的测试LSTM网络上的时空稀疏性导致Spartus在其理论硬件性能上达到46倍的加速，以实现9.4 TOP/S有效批次1吞吐量和1.1 TOP/S/W PARTIC效率。

自动语音识别（ASR）是一种能力，使程序能够将人类演讲进入书面形式。人工智能（AI）的最新发展导致基于深神经网络的高精度ASR系统，例如经常性神经网络传感器（RNN-T）。然而，这些方法的核心组件和所执行的操作从强大的生物对应，即人脑中脱离。另一方面，基于尖刺神经网络（SNNS）的生物启发模型中的当前发展，落后于准确性并主要关注小规模应用。在这项工作中，我们通过从大脑中发现的多样性神经和突触动态吸引灵感来重新审视生物学上可合理的模型并大大提高他们的能力。特别是，我们介绍了模拟轴体和轴突突触的神经连接概念。基于此，我们提出了具有丰富神经突触动态的新型深度学习单元，并将它们集成到RNN-T架构中。我们首次展示，与现有的深度学习模型相比，大规模ASR模型的生物学现实实际实施可以产生竞争性能水平。具体地，我们表明这种实现具有若干优点，例如降低的计算成本和更低的延迟，这对于语音识别应用至关重要。

Human actions can be represented by the trajectories of skeleton joints. Traditional methods generally model the spatial structure and temporal dynamics of human skeleton with hand-crafted features and recognize human actions by well-designed classifiers. In this paper, considering that recurrent neural network (RNN) can model the long-term contextual information of temporal sequences well, we propose an end-to-end hierarchical RNN for skeleton based action recognition. Instead of taking the whole skeleton as the input, we divide the human skeleton into five parts according to human physical structure, and then separately feed them to five subnets. As the number of layers increases, the representations extracted by the subnets are hierarchically fused to be the inputs of higher layers. The final representations of the skeleton sequences are fed into a single-layer perceptron, and the temporally accumulated output of the perceptron is the final decision. We compare with five other deep RNN architectures derived from our model to verify the effectiveness of the proposed network, and also compare with several other methods on three publicly available datasets. Experimental results demonstrate that our model achieves the state-of-the-art performance with high computational efficiency.

In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixedlength vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of the proposed model are jointly trained to maximize the conditional probability of a target sequence given a source sequence. The performance of a statistical machine translation system is empirically found to improve by using the conditional probabilities of phrase pairs computed by the RNN Encoder-Decoder as an additional feature in the existing log-linear model. Qualitatively, we show that the proposed model learns a semantically and syntactically meaningful representation of linguistic phrases.

最近，基于注意的编码器 - 解码器（AED）模型对多个任务的端到端自动语音识别（ASR）显示了高性能。在此类模型中解决了过度控制，本文介绍了轻松关注的概念，这是一种简单地逐渐注入对训练期间对编码器 - 解码器注意重量的统一分配，其易于用两行代码实现。我们调查轻松关注跨不同AED模型架构和两个突出的ASR任务，华尔街日志（WSJ）和LibRisPeech的影响。我们发现，在用外部语言模型解码时，随着宽松的注意力训练的变压器始终如一地始终如一地遵循标准基线模型。在WSJ中，我们为基于变压器的端到端语音识别设置了一个新的基准，以3.65％的单词错误率，最优于13.1％的相对状态，同时仅引入单个HyperParameter。

梁搜索是端到端模型的主要ASR解码算法，生成树结构化假设。但是，最近的研究表明，通过假设合并进行解码可以通过可比或更好的性能实现更有效的搜索。但是，复发网络中的完整上下文与假设合并不兼容。我们建议在RNN传感器的预测网络中使用矢量定量的长期记忆单元（VQ-LSTM）。通过与ASR网络共同培训离散表示形式，可以积极合并假设以生成晶格。我们在总机语料库上进行的实验表明，提出的VQ RNN传感器改善了具有常规预测网络的换能器的ASR性能，同时还产生了具有相同光束尺寸的Oracle Word错误率（WER）的密集晶格。其他语言模型撤退实验还证明了拟议的晶格生成方案的有效性。

经常性的神经网络传感器（RNN-T）目标在建立当今最好的自动语音识别（ASR）系统中发挥着重要作用。与连接员时间分类（CTC）目标类似，RNN-T损失使用特定规则来定义生成一组对准以形成用于全汇训练的格子。但是，如果这些规则是最佳的，则在很大程度上未知，并且会导致最佳ASR结果。在这项工作中，我们介绍了一种新的传感器目标函数，它概括了RNN-T丢失来接受标签的图形表示，从而提供灵活和有效的框架来操纵训练格子，例如用于限制对齐或研究不同的转换规则。我们证明，与标准RNN-T相比，具有CTC样格子的基于传感器的ASR实现了更好的结果，同时确保了严格的单调对齐，这将允许更好地优化解码过程。例如，所提出的CTC样换能器系统对于测试 - LibrisPeech的其他条件，实现了5.9％的字误差率，相对于基于等效的RNN-T系统的提高，对应于4.8％。

由长期记忆复发网络（LSTM-RNN）和变压器代表的最先进的神经网络语言模型（NNLMS）和变压器变得非常复杂。当获得有限的培训数据时，它们容易过度拟合和泛化。为此，本文提出了一个总体完整的贝叶斯学习框架，其中包含三种方法，以说明LSTM-RNN和Transformer LMS的潜在不确定性。分别使用贝叶斯，高斯过程和变异LSTM-RNN或变压器LMS对其模型参数，神经激活的选择和隐藏输出表示的不确定性。有效的推理方法被用来自动选择使用神经体系结构搜索的最佳网络内部组件作为贝叶斯学习。还使用了最少数量的蒙特卡洛参数样本。这些允许贝叶斯NNLM培训和评估中产生的计算成本最小化。实验是针对两项任务进行的：AMI符合转录和牛津-BBC唇读句子2（LRS2）使用最先进的LF-MMI培训的有效的TDNN系统重叠的语音识别，具有数据增强，扬声器的适应和多种音频，频道横梁成形以进行重叠的语音。基线LSTM-RNN和Transformer LMS具有估计的模型参数和辍学正则化的一致性改进，就困惑性和单词错误率（WER）获得了两项任务。特别是，在LRS2数据上，在基线LSTM-RNN和Transformer LMS中，在贝叶斯NNLMS及其各自的Baselines之间的模型组合后，在基线LSTM-RNN和Transferes LMS上分别获得了最高1.3％和1.2％的绝对降低（相对12.1％和11.3％）。 。

Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive field or simple temporal averaging for sequential processing, recurrent convolutional models are "doubly deep" in that they can be compositional in spatial and temporal "layers". Such models may have advantages when target concepts are complex and/or training data are limited. Learning long-term dependencies is possible when nonlinearities are incorporated into the network state updates. Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics; yet they can be optimized with backpropagation. Our recurrent long-term models are directly connected to modern visual convnet models and can be jointly trained to simultaneously learn temporal dynamics and convolutional perceptual representations. Our results show such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized.

Variational methods have been previously explored as a tractable approximation to Bayesian inference for neural networks. However the approaches proposed so far have only been applicable to a few simple network architectures. This paper introduces an easy-to-implement stochastic variational method (or equivalently, minimum description length loss function) that can be applied to most neural networks. Along the way it revisits several common regularisers from a variational perspective. It also provides a simple pruning heuristic that can both drastically reduce the number of network weights and lead to improved generalisation. Experimental results are provided for a hierarchical multidimensional recurrent neural network applied to the TIMIT speech corpus.

We use multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length representation. This representation is decoded using single or multiple decoder LSTMs to perform different tasks, such as reconstructing the input sequence, or predicting the future sequence. We experiment with two kinds of input sequences -patches of image pixels and high-level representations ("percepts") of video frames extracted using a pretrained convolutional net. We explore different design choices such as whether the decoder LSTMs should condition on the generated output. We analyze the outputs of the model qualitatively to see how well the model can extrapolate the learned video representation into the future and into the past. We try to visualize and interpret the learned features. We stress test the model by running it on longer time scales and on out-of-domain data. We further evaluate the representations by finetuning them for a supervised learning problemhuman action recognition on the UCF-101 and HMDB-51 datasets. We show that the representations help improve classification accuracy, especially when there are only a few training examples. Even models pretrained on unrelated datasets (300 hours of YouTube videos) can help action recognition performance.

本文介绍了在自动语音识别（ASR）的语境中的声学模型的新型深度学习架构，称为MixNet。除了在LSTM-HMM中的DNN-HMM和存储器单元中的完全连接层之外，该模型使用基于专家（MOE）的混合的两个附加层。在输入时操作的第一个Moe层基于预定义的广义语音类，并且在倒数第二层操作的第二层基于自动学习的声学类。在自然语音中，不同声学类的分布在分布中是不可避免的，这导致帧间错误分类。如果经过修改的传统架构，则预期ASR精度将改进，以使其更适合于占这种重叠。 MixNet正在开发牢记这一点。通过散点图进行的分析验证了MOE确实改善了转化为更好ASR精度的类之间的分离。实验在大型词汇ASR任务上进行，表明，与传统模型，即DNN和LSTM分别提供了13.6％和10.0％的单词误差速率，即使用SMBR标准训练。与用于电话分类的现有方法相比（由EIGEN等人），我们所提出的方法产生了显着的改善。