Diffusion models have achieved state-of-the-art synthesis quality on visual and audio tasks, and recent works adapt them to textual data by diffusing on the embedding space. But the difference between the continuous data space and the embedding space raises challenges to the diffusion model, which have not been carefully explored. In this paper, we conduct systematic studies and analyze the challenges threefold. Firstly, the data distribution is learnable for embeddings, which may lead to the collapse of the loss function. Secondly, as the norm of embedding varies between popular and rare words, adding the same noise scale will lead to sub-optimal results. In addition, we find that noises sampled from a standard Gaussian distribution may distract the diffusion process. To solve the above challenges, we propose Difformer, a denoising diffusion probabilistic model based on Transformer, which consists of three techniques including utilizing an anchor loss function, a layer normalization module for embeddings, and a norm factor to the Gaussian noise. All techniques are complementary to each other and critical to boosting the model performance together. Experiments are conducted on benchmark datasets over two seminal text generation tasks including machine translation and text summarization. The results show that Difformer significantly outperforms the embedding diffusion baselines, while achieving competitive results with strong autoregressive baselines.

Diffusion model, a new generative modelling paradigm, has achieved great success in image, audio, and video generation. However, considering the discrete categorical nature of text, it is not trivial to extend continuous diffusion models to natural language, and text diffusion models are less studied. Sequence-to-sequence text generation is one of the essential natural language processing topics. In this work, we apply diffusion models to approach sequence-to-sequence text generation, and explore whether the superiority generation performance of diffusion model can transfer to natural language domain. We propose SeqDiffuSeq, a text diffusion model for sequence-to-sequence generation. SeqDiffuSeq uses an encoder-decoder Transformers architecture to model denoising function. In order to improve generation quality, SeqDiffuSeq combines the self-conditioning technique and a newly proposed adaptive noise schedule technique. The adaptive noise schedule has the difficulty of denoising evenly distributed across time steps, and considers exclusive noise schedules for tokens at different positional order. Experiment results illustrate the good performance on sequence-to-sequence generation in terms of text quality and inference time.

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the two powerful models and enjoy the best of both worlds. On the one hand, diffusion models offer a promising training strategy that helps improve the generation quality. On the other hand, pre-trained denoising language models (e.g., BERT) can be used as a good initialization that accelerates convergence. We explore training BERT to learn the reverse process of a discrete diffusion process with an absorbing state and elucidate several designs to improve it. First, we propose a new noise schedule for the forward diffusion process that controls the degree of noise added at each step based on the information of each token. Second, we investigate several designs of incorporating the time step into BERT. Experiments on unconditional text generation demonstrate that DiffusionBERT achieves significant improvement over existing diffusion models for text (e.g., D3PM and Diffusion-LM) and previous generative masked language models in terms of perplexity and BLEU score.

Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges on the fact that the underlying physical phenomena are continuous. For inherently discrete and categorical data such as language, various diffusion-inspired alternatives have been proposed. However, the continuous nature of diffusion models conveys many benefits, and in this work we endeavour to preserve it. We propose CDCD, a framework for modelling categorical data with diffusion models that are continuous both in time and input space. We demonstrate its efficacy on several language modelling tasks.

For sequence generation, both autoregressive models and non-autoregressive models have been developed in recent years. Autoregressive models can achieve high generation quality, but the sequential decoding scheme causes slow decoding speed. Non-autoregressive models accelerate the inference speed with parallel decoding, while their generation quality still needs to be improved due to the difficulty of modeling multi-modalities in data. To address the multi-modality issue, we propose Diff-Glat, a non-autoregressive model featured with a modality diffusion process and residual glancing training. The modality diffusion process decomposes the modalities and reduces the modalities to learn for each transition. And the residual glancing sampling further smooths the modality learning procedures. Experiments demonstrate that, without using knowledge distillation data, Diff-Glat can achieve superior performance in both decoding efficiency and accuracy compared with the autoregressive Transformer.

In this paper, we propose a large-scale language pre-training for text GENeration using dIffusion modEl, which is named GENIE. GENIE is a pre-training sequence-to-sequence text generation model which combines Transformer and diffusion. The diffusion model accepts the latent information from the encoder, which is used to guide the denoising of the current time step. After multiple such denoise iterations, the diffusion model can restore the Gaussian noise to the diverse output text which is controlled by the input text. Moreover, such architecture design also allows us to adopt large scale pre-training on the GENIE. We propose a novel pre-training method named continuous paragraph denoise based on the characteristics of the diffusion model. Extensive experiments on the XSum, CNN/DailyMail, and Gigaword benchmarks shows that GENIE can achieves comparable performance with various strong baselines, especially after pre-training, the generation quality of GENIE is greatly improved. We have also conduct a lot of experiments on the generation diversity and parameter impact of GENIE. The code for GENIE will be made publicly available.

Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to language have presented diffusion as an alternative to autoregressive language generation. We instead view diffusion as a complementary method that can augment the generative capabilities of existing pre-trained language models. We demonstrate that continuous diffusion models can be learned in the latent space of a pre-trained encoder-decoder model, enabling us to sample continuous latent representations that can be decoded into natural language with the pre-trained decoder. We show that our latent diffusion models are more effective at sampling novel text from data distributions than a strong autoregressive baseline and also enable controllable generation.

Can continuous diffusion models bring the same performance breakthrough on natural language they did for image generation? To circumvent the discrete nature of text data, we can simply project tokens in a continuous space of embeddings, as is standard in language modeling. We propose Self-conditioned Embedding Diffusion, a continuous diffusion mechanism that operates on token embeddings and allows to learn flexible and scalable diffusion models for both conditional and unconditional text generation. Through qualitative and quantitative evaluation, we show that our text diffusion models generate samples comparable with those produced by standard autoregressive language models - while being in theory more efficient on accelerator hardware at inference time. Our work paves the way for scaling up diffusion models for text, similarly to autoregressive models, and for improving performance with recent refinements to continuous diffusion.

在本文中，我们提出了一种新的生成模型，逐步逐步的去噪AutoEncoder（Sundae），不依赖于自回归模型。类似地与去噪扩散技术，在从随机输入开始并从随机输入开始并每次直到收敛改善它们时，日出施加Sundae。我们提出了一个简单的新改进运算符，它比扩散方法更少迭代，同时在定性地在自然语言数据集上产生更好的样本。Sundae在WMT'14英语到德语翻译任务上实现最先进的结果（非自回归方法），在巨大清洁的常见爬网数据集和Python代码的数据集上对无条件语言建模的良好定性结果来自GitHub。通过在模板中填充任意空白模式，Sundae的非自动增加性质开辟了超出左右提示的可能性。

The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one. We present a diffusion-based captioning model, dubbed the name DDCap, to allow more decoding flexibility. Unlike image generation, where the output is continuous and redundant with a fixed length, texts in image captions are categorical and short with varied lengths. Therefore, naively applying the discrete diffusion model to text decoding does not work well, as shown in our experiments. To address the performance gap, we propose several key techniques including best-first inference, concentrated attention mask, text length prediction, and image-free training. On COCO without additional caption pre-training, it achieves a CIDEr score of 117.8, which is +5.0 higher than the auto-regressive baseline with the same architecture in the controlled setting. It also performs +26.8 higher CIDEr score than the auto-regressive baseline (230.3 v.s.203.5) on a caption infilling task. With 4M vision-language pre-training images and the base-sized model, we reach a CIDEr score of 125.1 on COCO, which is competitive to the best well-developed auto-regressive frameworks. The code is available at https://github.com/buxiangzhiren/DDCap.

Binaural audio plays a significant role in constructing immersive augmented and virtual realities. As it is expensive to record binaural audio from the real world, synthesizing them from mono audio has attracted increasing attention. This synthesis process involves not only the basic physical warping of the mono audio, but also room reverberations and head/ear related filtrations, which, however, are difficult to accurately simulate in traditional digital signal processing. In this paper, we formulate the synthesis process from a different perspective by decomposing the binaural audio into a common part that shared by the left and right channels as well as a specific part that differs in each channel. Accordingly, we propose BinauralGrad, a novel two-stage framework equipped with diffusion models to synthesize them respectively. Specifically, in the first stage, the common information of the binaural audio is generated with a single-channel diffusion model conditioned on the mono audio, based on which the binaural audio is generated by a two-channel diffusion model in the second stage. Combining this novel perspective of two-stage synthesis with advanced generative models (i.e., the diffusion models),the proposed BinauralGrad is able to generate accurate and high-fidelity binaural audio samples. Experiment results show that on a benchmark dataset, BinauralGrad outperforms the existing baselines by a large margin in terms of both object and subject evaluation metrics (Wave L2: 0.128 vs. 0.157, MOS: 3.80 vs. 3.61). The generated audio samples (https://speechresearch.github.io/binauralgrad) and code (https://github.com/microsoft/NeuralSpeech/tree/master/BinauralGrad) are available online.

在这项工作中，我们展示了一种新的神经机翻译方法（NMT），使用去噪扩散概率模型（DDPM），调整了文本数据，在该领域的最近进步之后。我们表明，可以使用在源句子上的扩散模型来无自动增加句子。我们还表明，我们的模型能够在培训期间无奈的语言成对（零拍摄学习）之间翻译。

降级扩散概率模型（DDPM）最近在许多生成任务中都取得了领先的性能。但是，继承的迭代采样过程成本阻碍了他们的应用程序到文本到语音部署。通过有关扩散模型参数化的初步研究，我们发现以前基于梯度的TTS模型需要数百或数千个迭代以保证高样本质量，这对加速采样带来了挑战。在这项工作中，我们提出了Prodiff的建议，以用于高质量文本到语音的渐进快速扩散模型。与以前的估计数据密度梯度的工作不同，Prodiff通过直接预测清洁数据来避免在加速采样时避免明显的质量降解来参数化denoising模型。为了通过减少扩散迭代来应对模型收敛挑战，Prodiff通过知识蒸馏减少目标位点的数据差异。具体而言，Denoising模型使用N-Step DDIM教师的生成的MEL光谱图作为训练目标，并将行为提炼成具有N/2步的新模型。因此，它允许TTS模型做出尖锐的预测，并通过数量级进一步减少采样时间。我们的评估表明，Prodiff仅需要两次迭代即可合成高保真性MEL光谱图，同时使用数百个步骤保持样本质量和多样性与最先进的模型竞争。 Prodiff在单个NVIDIA 2080TI GPU上的采样速度比实时快24倍，这使得扩散模型实际上是第一次适用于文本到语音综合部署。我们广泛的消融研究表明，Prodiff中的每种设计都是有效的，我们进一步表明，Prodiff可以轻松扩展到多扬声器设置。音频样本可在\ url {https://prodiff.github.io/。}上找到

手语制作（SLP）旨在将口语语言自动转化为符号序列。 SLP的核心过程是将符号光泽序列转换为其相应的标志姿势序列（G2P）。大多数现有的G2P模型通常以自回归方式执行这种条件的远程生成，这不可避免地导致错误的积累。为了解决这个问题，我们提出了一种量化量子序列序列的生成的矢量量化扩散方法，称为poseVQ扩散，这是一种迭代性非自动入学方法。具体而言，我们首先引入量化量化变量自动编码器（姿势VQVAE）模型，以表示姿势序列作为一系列潜在代码。然后，我们通过最近开发的扩散体系结构的扩展来对潜在离散空间进行建模。为了更好地利用时空信息，我们介绍了一种新颖的体系结构，即CodeUnet，以在离散空间中生成更高质量的姿势序列。此外，利用学习的代码，我们开发了一种新型的顺序k-nearest-neighbours方法，以预测相应的光泽序列的姿势序列的可变长度。因此，与自回旋G2P模型相比，我们的模型具有更快的采样速度，并产生明显更好的结果。与以前的非自动入学G2P方法相比，PoseVQ扩散通过迭代改进改善了预测的结果，从而在SLP评估基准上获得了最新的结果。

产生人类想要的声音效果是一个重要的话题。但是，在这一领域，很少有研究声音发电。在这项研究中，我们调查了以文本提示为条件的声音，并提出了一个新型的文本对生成框架，该框架由文本编码器组成，矢量量化了变异自动编码器（VQ-VAE），解码器和歌手。该框架首先使用解码器将从文本编码器提取的文本特征传递到借助VQ-VAE的MEL光谱图中，然后使用Vocoder将生成的MEL光谱图转换为波形。我们发现，解码器显着影响发电性能。因此，我们专注于在这项研究中设计一个好的解码器。我们从传统的自动回解码器开始，该解码器已被证明是以前的Sound Generation Works中的最先进方法。但是，AR解码器始终按顺序预测MEL-SPECTROGIN图令牌，这引入了单向偏见和错误问题的积累。此外，使用AR解码器，声音生成时间随着声音持续时间线性增加。为了克服AR解码器引入的缺点，我们提出了一个基于离散扩散模型的非自动回形解码器，称为DiffSound。具体而言，DIFFSOUND可以在一个步骤中预测所有MEL光谱图令牌，然后在下一步中完善预测的令牌，因此可以在几个步骤后获得最优于预测的结果。我们的实验表明，与AR解码器相比，我们提出的差异不仅产生更好的文本到单一生成结果，而且还具有更快的生成速度，例如MOS：3.56 \ textit {v.s} 2.786，并且生成速度为五个比AR解码器快的时间。

作为生成部件作为自回归模型的向量量化变形式自动化器（VQ-VAE）的集成在图像生成上产生了高质量的结果。但是，自回归模型将严格遵循采样阶段的逐步扫描顺序。这导致现有的VQ系列模型几乎不会逃避缺乏全球信息的陷阱。连续域中的去噪扩散概率模型（DDPM）显示了捕获全局背景的能力，同时产生高质量图像。在离散状态空间中，一些作品已经证明了执行文本生成和低分辨率图像生成的可能性。我们认为，在VQ-VAE的富含内容的离散视觉码本的帮助下，离散扩散模型还可以利用全局上下文产生高保真图像，这补偿了沿像素空间的经典自回归模型的缺陷。同时，离散VAE与扩散模型的集成解决了传统的自回归模型的缺点是超大的，以及在生成图像时需要在采样过程中的过度时间的扩散模型。结果发现所生成的图像的质量严重依赖于离散的视觉码本。广泛的实验表明，所提出的矢量量化离散扩散模型（VQ-DDM）能够实现与低复杂性的顶层方法的相当性能。它还展示了在没有额外培训的图像修复任务方面与自回归模型量化的其他矢量突出的优势。

低频词预测仍然是现代神经电机翻译（NMT）系统的挑战。最近的自适应培训方法通过强调整体培训目标的重量来促进不频繁词语的产出。尽管召回了低频词的召回，但它们的预测精度意外地受到自适应目标的阻碍。灵感来自观察到低频词形成更紧凑的嵌入空间，我们从代表学习角度解决这一挑战。具体地，我们提出了一种频率感知的令牌级对比度学习方法，其中每个解码步骤的隐藏状态以基于相应的字频率的柔和对比方式从其他目标单词的对应物推开。我们对广泛使用的NIST汉语 - 英语和WMT14英语 - 德语翻译任务进行实验。经验结果表明，我们的提出方法不仅可以显着提高翻译质量，还可以提高词汇分集和优化词表示空间。进一步调查揭示了，与相关的自适应培训策略相比，我们对低频词预测方法的优势在于在不牺牲精度的情况下在不同频率上的令牌级召回的鲁棒性。

扩散模型是一类深入生成模型，在具有密集理论建立的各种任务上显示出令人印象深刻的结果。尽管与其他最先进的模型相比，扩散模型的样本合成质量和多样性令人印象深刻，但它们仍然遭受了昂贵的抽样程序和次优可能的估计。最近的研究表明，对提高扩散模型的性能的热情非常热情。在本文中，我们对扩散模型的现有变体进行了首次全面综述。具体而言，我们提供了扩散模型的第一个分类法，并将它们分类为三种类型，即采样加速增强，可能性最大化的增强和数据将来增强。我们还详细介绍了其他五个生成模型（即变异自动编码器，生成对抗网络，正常流量，自动回归模型和基于能量的模型），并阐明扩散模型与这些生成模型之间的连接。然后，我们对扩散模型的应用进行彻底研究，包括计算机视觉，自然语言处理，波形信号处理，多模式建模，分子图生成，时间序列建模和对抗性纯化。此外，我们提出了与这种生成模型的发展有关的新观点。

通常使用自回归生成模型，尤其是对于涉及顺序数据的那些任务。然而，由于链式有条件建模的内在特征（例如，暴露偏见或缺乏远距离连贯性），由于许多固有的缺陷而困扰着它们，严重限制了它们正确模型分布的能力。在本文中，我们提出了一种独特的方法，该方法称为训练自回旋生成模型，以利用精心设计的基于能量的学习目标。通过利用SoftMax操作的额外自由度，我们被允许使自回归模型本身成为基于能量的模型，用于衡量输入的可能性，而无需引入任何额外的参数。此外，我们表明可以有效地训练电子臂，并能够减轻暴露偏置问题并增加自回归生成模型的时间连贯性。广泛的经验结果涵盖了语言建模，神经机器翻译和图像产生等基准，证明了拟议方法的有效性。

我们介绍了文本到图像生成的矢量量化扩散（VQ-扩散）模型。该方法基于矢量量化变分性AutoEncoder（VQ-VAE），其潜像通过最近开发的去噪扩散概率（DDPM）的条件变体为基础。我们发现这种潜在空间方法非常适合于图像到图像生成任务，因为它不仅消除了具有现有方法的单向偏差，还允许我们结合掩模和更换的扩散策略，以避免积累错误，这是现有方法的严重问题。我们的实验表明，与具有类似数量的参数数量的传统自回归（AR）模型相比，VQ扩散产生明显更好的文本到图像生成结果。与以前的基于GAN的文本到图像方法相比，我们的VQ扩散可以通过大边缘处理更复杂的场景并提高合成的图像质量。最后，我们表明我们的方法中的图像生成计算可以通过Reparameter化进行高效。利用传统的AR方法，文本到图像生成时间随输出图像分辨率线性增加，因此即使对于正常尺寸图像也是相当耗时的。 VQ-扩散使我们能够在质量和速度之间实现更好的权衡。我们的实验表明，具有Reparameterization的VQ扩散模型比传统的AR方法快15倍，同时实现更好的图像质量。