The massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art audio SSL models still employ reconstruction loss for pre-training. Compared with reconstruction loss, semantic-rich discrete label prediction encourages the SSL model to abstract the high-level audio semantics and discard the redundant details as in human perception. However, a semantic-rich acoustic tokenizer for general audio pre-training is usually not straightforward to obtain, due to the continuous property of audio and unavailable phoneme sequences like speech. To tackle this challenge, we propose BEATs, an iterative audio pre-training framework to learn Bidirectional Encoder representation from Audio Transformers, where an acoustic tokenizer and an audio SSL model are optimized by iterations. In the first iteration, we use random projection as the acoustic tokenizer to train an audio SSL model in a mask and label prediction manner. Then, we train an acoustic tokenizer for the next iteration by distilling the semantic knowledge from the pre-trained or fine-tuned audio SSL model. The iteration is repeated with the hope of mutual promotion of the acoustic tokenizer and audio SSL model. The experimental results demonstrate our acoustic tokenizers can generate discrete labels with rich audio semantics and our audio SSL models achieve state-of-the-art results across various audio classification benchmarks, even outperforming previous models that use more training data and model parameters significantly. Specifically, we set a new state-of-the-art mAP 50.6% on AudioSet-2M for audio-only models without using any external data, and 98.1% accuracy on ESC-50. The code and pre-trained models are available at https://aka.ms/beats.

This paper targets unsupervised skeleton-based action representation learning and proposes a new Hierarchical Contrast (HiCo) framework. Different from the existing contrastive-based solutions that typically represent an input skeleton sequence into instance-level features and perform contrast holistically, our proposed HiCo represents the input into multiple-level features and performs contrast in a hierarchical manner. Specifically, given a human skeleton sequence, we represent it into multiple feature vectors of different granularities from both temporal and spatial domains via sequence-to-sequence (S2S) encoders and unified downsampling modules. Besides, the hierarchical contrast is conducted in terms of four levels: instance level, domain level, clip level, and part level. Moreover, HiCo is orthogonal to the S2S encoder, which allows us to flexibly embrace state-of-the-art S2S encoders. Extensive experiments on four datasets, i.e., NTU-60, NTU-120, PKU-MMD I and II, show that HiCo achieves a new state-of-the-art for unsupervised skeleton-based action representation learning in two downstream tasks including action recognition and retrieval, and its learned action representation is of good transferability. Besides, we also show that our framework is effective for semi-supervised skeleton-based action recognition. Our code is available at https://github.com/HuiGuanLab/HiCo.

End-to-end formulation of automatic speech recognition (ASR) and speech translation (ST) makes it easy to use a single model for both multilingual ASR and many-to-many ST. In this paper, we propose streaming language-agnostic multilingual speech recognition and translation using neural transducers (LAMASSU). To enable multilingual text generation in LAMASSU, we conduct a systematic comparison between specified and unified prediction and joint networks. We leverage a language-agnostic multilingual encoder that substantially outperforms shared encoders. To enhance LAMASSU, we propose to feed target LID to encoders. We also apply connectionist temporal classification regularization to transducer training. Experimental results show that LAMASSU not only drastically reduces the model size but also outperforms monolingual ASR and bilingual ST models.

混合动力和端到端（E2E）自动语音识别（ASR）系统之间的基本建模差异在其中创造了巨大的多样性和互补性。本文研究了混合TDNN和构型E2E ASR系统的基于多通的逆转和交叉适应系统组合方法。在多通恢复中，最先进的混合动力LF-MMI训练有素的CNN-TDNN系统具有速度扰动，规格和贝叶斯学习隐藏单元供款（LHUC）扬声器的适应器，以在被恢复之前产生初始的N-tesk输出由扬声器适应构象异构体系统，使用2向跨系统得分插值。在交叉适应中，混合CNN-TDNN系统适用于构象异构体系统的1好的输出，反之亦然。在300小时的总机语料库上进行的实验表明，使用两种系统组合方法中的任何一个得出的组合系统都超过了单个系统。在NIST HUB5'00，RT03和RT03和RT02评估数据。

最近，蒙面的预测预训练在自我监督的学习（SSL）方面取得了显着的进展，以进行语音识别。它通常需要以无监督的方式获得的代码簿，从而使其准确和难以解释。我们提出了两种监督指导的代码书生成方法，以提高自动语音识别（ASR）的性能以及预训练效率，要么通过使用混合ASR系统来解码以生成音素级别对准（命名为PBERT），要么通过在上进行集群进行聚类。从端到端CTC模型（命名CTC聚类）提取的监督语音功能。混合动力和CTC模型均经过与微调相同的少量标记语音训练。实验表明，我们的方法对各种SSL和自我训练基准的优势具有显着优势，相对减少了17.0％。我们的预训练模型在非ASR语音任务中还显示出良好的可传递性。

关节特征本质上是声信号失真的不变，并且已成功地纳入了为正常语音设计的自动语音识别（ASR）系统。它们在非典型任务领域（例如老年人和跨语言的言语无序）的实际应用通常受到从目标扬声器收集此类专家数据的困难。本文介绍了一种跨域和跨语性A2A反演方法，该方法利用了A2A模型中24小时TAL Corpus的平行音频，视觉和超声舌成像（UTI）数据，然后进行交叉训练和交叉训练。语言适用于两种语言的三个数据集：英语dementiabank pitt和antonese JCCOCC MOCA老年演讲Corpora;以及英语Torgo违反语音数据，以产生基于UTI的发音特征。 Experiments conducted on three tasks suggested incorporating the generated articulatory features consistently outperformed the baseline hybrid TDNN and Conformer based end-to-end systems constructed using acoustic features only by statistically significant word error rate or character error rate reductions up to 2.64%, 1.92% and数据增强和说话者适应后，绝对4.17％，7.89％和13.28％相对1.21％。

本文介绍了我们针对IWSLT 2022离线任务的端到端Yitrans语音翻译系统的提交，该任务从英语音频转换为德语，中文和日语。 Yitrans系统建立在大规模训练的编码器模型上。更具体地说，我们首先设计了多阶段的预训练策略，以建立具有大量标记和未标记数据的多模式模型。然后，我们为下游语音翻译任务微调模型的相应组件。此外，我们做出了各种努力，以提高性能，例如数据过滤，数据增强，语音细分，模型集合等。实验结果表明，我们的Yitrans系统比在三个翻译方向上的强基线取得了显着改进，并且比去年在TST2021英语 - 德国人中的最佳端到端系统方面的改进+5.2 BLEU改进。根据自动评估指标，我们的最终意见在英语 - 德国和英语端到端系统上排名第一。我们使代码和模型公开可用。

Twitter机器人检测已成为打击错误信息，促进社交媒体节制并保持在线话语的完整性的越来越重要的任务。最先进的机器人检测方法通常利用Twitter网络的图形结构，在面对传统方法无法检测到的新型Twitter机器人时，它们表现出令人鼓舞的性能。但是，现有的Twitter机器人检测数据集很少是基于图形的，即使这些基于图形的数据集也遭受有限的数据集量表，不完整的图形结构以及低注释质量。实际上，缺乏解决这些问题的大规模基于图的Twitter机器人检测基准，严重阻碍了基于图形的机器人检测方法的开发和评估。在本文中，我们提出了Twibot-22，这是一个综合基于图的Twitter机器人检测基准，它显示了迄今为止最大的数据集，在Twitter网络上提供了多元化的实体和关系，并且与现有数据集相比具有更好的注释质量。此外，我们重新实施35代表性的Twitter机器人检测基线，并在包括Twibot-22在内的9个数据集上进行评估，以促进对模型性能和对研究进度的整体了解的公平比较。为了促进进一步的研究，我们将所有实施的代码和数据集巩固到Twibot-22评估框架中，研究人员可以在其中始终如一地评估新的模型和数据集。 Twibot-22 Twitter机器人检测基准和评估框架可在https://twibot22.github.io/上公开获得。

尽管针对正常语音的自动语音识别（ASR）技术取得了迅速的进展，但迄今为止，准确认识违反障碍和老年语音仍然是高度挑战的任务。由于这些用户中经常发现的移动性问题，很难为ASR系统开发收集大量此类数据。为此，数据增强技术起着至关重要的作用。与现有的数据增强技术相反，仅修改光谱轮廓的说话速率或整体形状，使用一组新颖的扬声器依赖（SD）生成对抗网络（Gan ）本文基于数据增强方法。这些既可以灵活地允许：a）在可用的语音数据可用时修改时间或速度的正常语音光谱，并更接近受损说话者的扬声器； b）对于非平行数据，SVD分解了正常语音频谱基础特征，要转换为目标老年人说话者的特征，然后再与时间基础重组以生成最先进的TDNN的增强数据和构象体ASR系统培训。实验是针对四个任务进行的：英语Uapseech和Torgo违反语音语音Corpora；英国痴呆症皮特和广东话JCCOCC MOCA老年语音数据集。所提出的基于GAN的数据增强方法始终优于基线速度扰动方法，最多可在Torgo和Dementiabank数据上降低4.91％和3.0％的绝对速度（相对相对9.61％和6.4％）。应用基于LHUC的扬声器适应后，保留了一致的性能改进。

最近，即使预训练目标是为语音识别而设计的，自我监督学习（SSL）即使在说话者的识别方面表现出了很强的表现。在本文中，我们研究了哪些因素导致对与说话者相关的任务的自我监督学习成功，例如扬声器验证（SV）通过一系列精心设计的实验。我们对Voxceleb-1数据集的经验结果表明，SSL对SV任务的好处是来自蒙版语音预测丢失，数据量表和模型大小的组合，而SSL量化器具有较小的影响。我们进一步采用了综合梯度归因方法和损失景观可视化，以了解说话者识别性能的自我监督学习的有效性。