Current self-supervised learning algorithms are often modality-specific and require large amounts of computational resources. To address these issues, we increase the training efficiency of data2vec, a learning objective that generalizes across several modalities. We do not encode masked tokens, use a fast convolutional decoder and amortize the effort to build teacher representations. data2vec 2.0 benefits from the rich contextualized target representations introduced in data2vec which enable a fast self-supervised learner. Experiments on ImageNet-1K image classification show that data2vec 2.0 matches the accuracy of Masked Autoencoders in 16.4x lower pre-training time, on Librispeech speech recognition it performs as well as wav2vec 2.0 in 10.6x less time, and on GLUE natural language understanding it matches a retrained RoBERTa model in half the time. Trading some speed for accuracy results in ImageNet-1K top-1 accuracy of 86.8\% with a ViT-L model trained for 150 epochs.

本文研究了基于图像的蒙版自动编码器（MAE）的简单扩展，以从音频谱图中学习自我监督的表示。在MAE中的变压器编码器编码器设计之后，我们的Audio-MAE首先编码具有较高遮罩比的音频谱图斑块，仅通过编码器层馈入非掩盖令牌。然后，解码器重新订购并解码编码的上下文，并用掩码令牌填充，以重建输入频谱图。我们发现将局部窗户注意力纳入解码器是有益的，因为音频谱图在当地时间和频带中高度相关。然后，我们在目标数据集上以较低的掩模比微调编码器。从经验上讲，音频MAE在六个音频和语音分类任务上设定了新的最先进的性能，超过了使用外部监督预训练的其他最新模型。代码和模型将在https://github.com/facebookresearch/audiomae上。

在过去的几年中，语音表征的自我监督学习（SSL）受到了很多关注，但大多数工作都集中在具有大量未标记数据的语言和域上。但是，对于许多语言，即使在未标记的数据中也存在短缺，这限制了SSL的有效性。在这项工作中，我们专注于通过利用WAV2VEC 2.0预处理的数据增强来将SSL应用于域具有有限数据的域的问题。此外，我们建议对模型的每个组件进行改进，从而与LibrisPeech测试清除 /其他的WAV2VEC 2.0相比，将相对单词错误率（WER）提高高达13％。

无监督的语音识别表现出了使每种语言都可以访问的自动语音识别（ASR）系统的巨大潜力。但是，现有方法仍然严重依赖手工制作的预处理。与端到端进行监督语音识别的趋势类似，我们介绍了WAV2VEC-U 2.0，它消除了所有音频端的预处理，并通过更好的体系结构提高了准确性。此外，我们引入了一个辅助自我监督的目标，该目标将模型的预测与输入联系起来。实验表明，WAV2VEC-U 2.0在概念上更简单的同时，可以改善不同语言的无监督识别结果。

本文介绍了基于Wav2VEC 2.0的跨语言语音表示学习的大规模模型。我们在128种语言中培训最多2B个公共讲话音频的近半小时的型号的模型，比公共数据的数量级比最大的已知事先工作。我们的评估涵盖了广泛的任务，域，数据制度和语言，都是高低资源。在Covost-2语音翻译基准测试中，我们将先前的最先进的状态平均为7.4 BLEU超过21个翻译方向进入英语。对于语音识别，XLS-R在Babel，MLS，CommonVoice以及Voxpopuli上的最佳已知工作中提高，降低了相对的误差率14-34％。 XLS-R还在Voxlingua107语言识别上设置了新的技术状态。此外，我们表明，具有足够的模型规模，交叉思维预先预测可以在将英语演讲翻译成其他语言时才能优于英语撇印，这是一个有利于单晶的预借预制的设置。我们希望XLS-R可以帮助改善世界上更多语言的语音处理任务。

We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler. wav2vec 2.0 masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned. Experiments using all labeled data of Librispeech achieve 1.8/3.3 WER on the clean/other test sets. When lowering the amount of labeled data to one hour, wav2vec 2.0 outperforms the previous state of the art on the 100 hour subset while using 100 times less labeled data. Using just ten minutes of labeled data and pre-training on 53k hours of unlabeled data still achieves 4.8/8.2 WER. This demonstrates the feasibility of speech recognition with limited amounts of labeled data. 1 1 Code and models are available at https://github.com/pytorch/fairseq Preprint. Under review.

FAIRSEQ is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and supports distributed training across multiple GPUs and machines. We also support fast mixed-precision training and inference on modern GPUs. A demo video can be found here: https://www.youtube. com/watch?v=OtgDdWtHvto.

In this paper, we perform an exhaustive evaluation of different representations to address the intent classification problem in a Spoken Language Understanding (SLU) setup. We benchmark three types of systems to perform the SLU intent detection task: 1) text-based, 2) lattice-based, and a novel 3) multimodal approach. Our work provides a comprehensive analysis of what could be the achievable performance of different state-of-the-art SLU systems under different circumstances, e.g., automatically- vs. manually-generated transcripts. We evaluate the systems on the publicly available SLURP spoken language resource corpus. Our results indicate that using richer forms of Automatic Speech Recognition (ASR) outputs allows SLU systems to improve in comparison to the 1-best setup (4% relative improvement). However, crossmodal approaches, i.e., learning from acoustic and text embeddings, obtains performance similar to the oracle setup, and a relative improvement of 18% over the 1-best configuration. Thus, crossmodal architectures represent a good alternative to overcome the limitations of working purely automatically generated textual data.

The access to activity of subcortical structures offers unique opportunity for building intention dependent brain-computer interfaces, renders abundant options for exploring a broad range of cognitive phenomena in the realm of affective neuroscience including complex decision making processes and the eternal free-will dilemma and facilitates diagnostics of a range of neurological deceases. So far this was possible only using bulky, expensive and immobile fMRI equipment. Here we present an interpretable domain grounded solution to recover the activity of several subcortical regions from the multichannel EEG data and demonstrate up to 60% correlation between the actual subcortical blood oxygenation level dependent sBOLD signal and its EEG-derived twin. Then, using the novel and theoretically justified weight interpretation methodology we recover individual spatial and time-frequency patterns of scalp EEG predictive of the hemodynamic signal in the subcortical nuclei. The described results not only pave the road towards wearable subcortical activity scanners but also showcase an automatic knowledge discovery process facilitated by deep learning technology in combination with an interpretable domain constrained architecture and the appropriate downstream task.

对比方法导致了最近的自我监督表示学习（SSL）的表现激增。诸如BYOL或SIMSIAM之类的最新方法据称将这些对比方法提炼为它们的本质，消除了钟声和哨子，包括负面示例，这些示例不影响下游性能。这些“非对比度”方法的工作非常出色，而无需使用负面因素，即使全球最低限度的崩溃都在淡化。我们通过经验分析了这些非对抗性方法，发现Simsiam对数据集和模型大小非常敏感。特别是，如果模型相对于数据集大小而言太小，则SIMSIAM表示会经历部分维度崩溃。我们提出了一个度量标准来测量这种崩溃的程度，并表明它可以用于预测下游任务性能，而无需任何微调或标签。我们进一步分析建筑设计选择及其对下游性能的影响。最后，我们证明，转移到持续的学习设置充当正规化器并防止崩溃，并且在Imagenet上使用Resnet-18，连续和多上述训练之间的混合物可以提高线性探针精度多达18个百分点。