传统上，自动语音识别的研究重点是对音频表示的本地首选编码，以预测话语中的语音。不幸的是，依靠此类超本地信息的方法往往容易受到本地级腐败（例如音频框架掉落或大声的噪音）和全球级别的噪音（例如环境噪音或背景噪音）在训练期间看到。在这项工作中，我们介绍了一种新颖的方法，该方法利用了基于掩盖语言建模的自我监督的学习技术来计算对话语发生的环境的全球多模式编码。然后，我们使用一个新的深融合框架将这种全局上下文集成到传统的ASR方法中，并证明所得的方法可以在LibrisPeech上胜过高达7％的基线方法；内部数据集的收益范围从6％（较大型号）到45％（在较小的型号上）。

深度神经网络在很大程度上证明了他们通过从输入音频帧中提取有意义的功能来执行自动语音识别（ASR）的能力。但是，此类功能不仅包括有关口语内容的信息，而且还可能包含有关不必要上下文的信息，例如背景噪声和声音或说话者身份，口音或受保护的属性。这样的信息可以通过引入口头词与说出此类词的上下文之间的虚假相关性来直接损害概括性能。在这项工作中，我们介绍了一种无监督的，编码的方法，用于将语音编码器描述为明确的内容编码表示和虚假的上下文编码表示形式。通过这样做，我们证明了标准ASR基准的性能提高，并在现实世界和人为嘈杂的ASR方案中的性能提高。

语音的视频录制包含相关的音频和视觉信息，为语音表示从扬声器的唇部运动和产生的声音提供了强大的信号。我们介绍了视听隐藏单元BERT（AV-HUBERT），是视听语音的自我监督的代表学习框架，这些屏幕屏蔽了多流视频输入并预测自动发现和迭代地精制多模式隐藏单元。 AV-HUBERT学习强大的视听语音表示，这些语音表示受益于唇读和自动语音识别。在最大的公众唇读基准LRS3（433小时）中，AV-Hubert达到32.5％WER，只有30个小时的标签数据，优于前一种最先进的方法（33.6％）培训，达到了一千次转录的视频数据（31k小时）。当使用来自LRS3的所有433小时的标记数据并结合自培训时，唇读WER进一步降低至26.9％。使用我们在相同的基准测试中使用您的视听表示，用于音频语音识别的相对效率为40％，而最先进的性能（1.3％Vs 2.3％）。我们的代码和模型可在https://github.com/facebookResearch/av_hubert获得

We present RAVEn, a self-supervised multi-modal approach to jointly learn visual and auditory speech representations. Our pre-training objective involves encoding masked inputs, and then predicting contextualised targets generated by slowly-evolving momentum encoders. Driven by the inherent differences between video and audio, our design is asymmetric w.r.t. the two modalities' pretext tasks: Whereas the auditory stream predicts both the visual and auditory targets, the visual one predicts only the auditory targets. We observe strong results in low- and high-resource labelled data settings when fine-tuning the visual and auditory encoders resulting from a single pre-training stage, in which the encoders are jointly trained. Notably, RAVEn surpasses all self-supervised methods on visual speech recognition (VSR) on LRS3, and combining RAVEn with self-training using only 30 hours of labelled data even outperforms a recent semi-supervised method trained on 90,000 hours of non-public data. At the same time, we achieve state-of-the-art results in the LRS3 low-resource setting for auditory speech recognition (as well as for VSR). Our findings point to the viability of learning powerful speech representations entirely from raw video and audio, i.e., without relying on handcrafted features. Code and models will be made public.

We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) intra- and inter-modal contrastive learning with masking, and (3) self-training by reconstructing joint audio-video contextualized features learned from the first two objectives. Pre-training with MAViL not only enables the model to perform well in audio-visual classification and retrieval tasks but also improves representations of each modality in isolation, without using information from the other modality for fine-tuning or inference. Empirically, MAViL sets a new state-of-the-art on AudioSet (53.1 mAP) and VGGSound (67.1% accuracy). For the first time, a self-supervised audio-visual model outperforms ones that use external supervision on these benchmarks. Code will be available soon.

尽管视听模型与仅限音频模型相比可以产生卓越的性能和鲁棒性，但由于缺乏标记和未标记的视听数据以及每种方式部署一个模型的成本，它们的开发和采用受到阻碍。在本文中，我们提出了U-Hubert，这是一个自制的预训练框架，可以通过统一的蒙版群集预测目标来利用多模式和单峰语音。通过在预训练期间利用模态辍学，我们证明了一个微调模型可以在PAR上取得比较的性能或比最先进的模态特异性模型更好。此外，我们仅在音频上进行微调的模型可以通过视听和视觉语音输入来表现良好，从而实现了零击的模态概括，以实现语音识别和扬声器验证。特别是，我们的单个模型在带有音频/视听/视觉输入的LRS3上产生1.2％/1.4％/27.2％的语音识别单词错误率。

我们提出了一种简单有效的自我监督学习方法，以供语音识别。该方法以随机预测量化器生成的离散标签的形式学习了一个模型，以预测蒙版的语音信号。尤其是量化器的语音输入带有随机初始化的矩阵，并在随机限制的代码簿中进行最近的邻居查找。在自我监督的学习过程中，矩阵和密码簿均未更新。由于未对随机预测量化器进行训练，并与语音识别模型分开，因此该设计使该方法具有灵活性，并且与通用语音识别体系结构兼容。在LibrisPeech上，我们的方法与以前的工作相比，使用非流式模型获得了与以前的工作相似的单词率，并且比WAV2VEC 2.0和WAP2VEC 2.0和w2v-bert提供了较低的单词率率和延迟。在多语言任务上，该方法还提供了与WAV2VEC 2.0和W2V-bert的显着改进。

基于音频的自动语音识别（ASR）在嘈杂的环境中显着降低，并且特别容易受到干扰语音的影响，因为模型无法确定要转录的扬声器。视听语音识别（AVSR）系统通过将音频流与不变噪声不变的可视信息补充，帮助模型对所需扬声器的视觉信息来提高鲁棒性。但是，以前的AVSR工作仅关注监督学习设置;因此，通过可用的标记数据量阻碍了进度。在这项工作中，我们提出了一个自我监督的AVSR框架，建立在视听休伯特（AV-HUBERT），是最先进的视听语音表示学习模型。在最大可用的AVSR基准数据集LRS3中，我们的方法在存在的情况下使用少于10％的标签数据（433HR与30HR）之前的最先进（28.0％与14.1％）优于〜50％（28.0％vs.14.1％）禁止噪声，平均减少了基于音频模型的WER以上超过75％（25.8％与5.8％）。

Self-supervised approaches for speech representation learning are challenged by three unique problems: (1) there are multiple sound units in each input utterance, (2) there is no lexicon of input sound units during the pre-training phase, and (3) sound units have variable lengths with no explicit segmentation. To deal with these three problems, we propose the Hidden-Unit BERT (HuBERT) approach for self-supervised speech representation learning, which utilizes an offline clustering step to provide aligned target labels for a BERT-like prediction loss. A key ingredient of our approach is applying the prediction loss over the masked regions only, which forces the model to learn a combined acoustic and language model over the continuous inputs. HuBERT relies primarily on the consistency of the unsupervised clustering step rather than the intrinsic quality of the assigned cluster labels. Starting with a simple k-means teacher of 100 clusters, and using two iterations of clustering, the HuBERT model either matches or improves upon the state-ofthe-art wav2vec 2.0 performance on the Librispeech (960h) and Libri-light (60,000h) benchmarks with 10min, 1h, 10h, 100h, and 960h fine-tuning subsets. Using a 1B parameter model, HuBERT shows up to 19% and 13% relative WER reduction on the more challenging dev-other and test-other evaluation subsets. 1

In this paper, we propose a novel multi-modal multi-task encoder-decoder pre-training framework (MMSpeech) for Mandarin automatic speech recognition (ASR), which employs both unlabeled speech and text data. The main difficulty in speech-text joint pre-training comes from the significant difference between speech and text modalities, especially for Mandarin speech and text. Unlike English and other languages with an alphabetic writing system, Mandarin uses an ideographic writing system where character and sound are not tightly mapped to one another. Therefore, we propose to introduce the phoneme modality into pre-training, which can help capture modality-invariant information between Mandarin speech and text. Specifically, we employ a multi-task learning framework including five self-supervised and supervised tasks with speech and text data. For end-to-end pre-training, we introduce self-supervised speech-to-pseudo-codes (S2C) and phoneme-to-text (P2T) tasks utilizing unlabeled speech and text data, where speech-pseudo-codes pairs and phoneme-text pairs are a supplement to the supervised speech-text pairs. To train the encoder to learn better speech representation, we introduce self-supervised masked speech prediction (MSP) and supervised phoneme prediction (PP) tasks to learn to map speech into phonemes. Besides, we directly add the downstream supervised speech-to-text (S2T) task into the pre-training process, which can further improve the pre-training performance and achieve better recognition results even without fine-tuning. Experiments on AISHELL-1 show that our proposed method achieves state-of-the-art performance, with a more than 40% relative improvement compared with other pre-training methods.

视听自动语音识别（AV-ASR）是ASR的扩展，它通常来自扬声器嘴的动作。与仅关注唇部运动的作品不同，我们研究了整个视觉框架（视觉动作，对象，背景等）的贡献。这对于不一定可见的说话者不一定可见的视频特别有用。为了解决这项任务，我们提出了一个新的序列到序列视听ASR变压器（Avatar），该序列是从频谱图和全帧RGB端到端训练的。为了防止音频流主导训练，我们提出了不同的单词掩盖策略，从而鼓励我们的模型注意视觉流。我们证明了视觉模态对2 AV-ASR基准测试的贡献，尤其是在模拟噪声的情况下，并表明我们的模型以很大的边距优于所有其他先前的工作。最后，我们还为AV-ASR创建了一个名为Visspeech的新的现实世界测试床，该床在挑战性的音频条件下展示了视觉模态的贡献。

大规模未标记数据集的预培训显示了计算机视觉和自然语言处理领域的令人印象深刻的性能改进。鉴于大规模教学视频数据集的出现，预训练视频编码器的常见策略是使用随附的语音作为弱监管。但是，由于演讲用于监督预培训，视频编码器从未见过，这不会学会处理该模态。我们解决了当前预训练方法的这种缺点，这未能利用口语语言中的丰富的线索。我们的提议是使用所有可用的视频模型作为监督，即外观，声音和转录语音预先列车。我们在输入中掩盖了整个模态并使用其他两个模态预测它。这鼓励每个码头与其他方式合作，我们的视频编码器学会处理外观和音频以及语音。我们展示了我们在How2R，YouScook2和浓缩电影数据集上视频检索的“模态屏蔽”预培训方法的卓越性能。

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.

本文调查了视听扬声器表示的自我监督的预训练，其中显示了视觉流，显示说话者的口腔区域与语音一起用作输入。我们的研究重点是视听隐藏单元BERT（AV-HUBERT）方法，该方法是最近开发的通用音频语音训练前训练框架。我们进行了广泛的实验，以探测预训练和视觉方式的有效性。实验结果表明，AV-Hubert可以很好地概括与说话者相关的下游任务，从而使标签效率提高了大约10倍的仅10倍，仅音频和视听扬声器验证。我们还表明，结合视觉信息，甚至仅仅是唇部区域，都大大提高了性能和噪声稳健性，在清洁条件下将EER降低了38％，在嘈杂的条件下将EER降低了75％。

Recognizing a word shortly after it is spoken is an important requirement for automatic speech recognition (ASR) systems in real-world scenarios. As a result, a large body of work on streaming audio-only ASR models has been presented in the literature. However, streaming audio-visual automatic speech recognition (AV-ASR) has received little attention in earlier works. In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer architecture, which is made streamable using chunk-wise self-attention (CSA) and causal convolution. Streaming recognition with a decoder neural network is realized by using the triggered attention technique, which performs time-synchronous decoding with joint CTC/attention scoring. For frame-level ASR criteria, such as CTC, a synchronized response from the audio and visual encoders is critical for a joint AV decision making process. In this work, we propose a novel alignment regularization technique that promotes synchronization of the audio and visual encoder, which in turn results in better word error rates (WERs) at all SNR levels for streaming and offline AV-ASR models. The proposed AV-ASR model achieves WERs of 2.0% and 2.6% on the Lip Reading Sentences 3 (LRS3) dataset in an offline and online setup, respectively, which both present state-of-the-art results when no external training data are used.

In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. First, we leverage global action information to catalyze mutual interactions between linguistic texts and local regional objects. It uncovers global and local visual clues from paired video sequences and text descriptions for detailed visual and text relation modeling. Second, we introduce a TaNgled Transformer block (TNT) to encode three sources of information, i.e., global actions, local regional objects, and linguistic descriptions. Global-local correspondences are discovered via judicious clues extraction from contextual information. It enforces the joint video-text representation to be aware of fine-grained objects as well as global human intention. We validate the generalization capability of ActBERT on downstream video-and-language tasks, i.e., text-video clip retrieval, video captioning, video question answering, action segmentation, and action step localization. ActBERT significantly outperforms the stateof-the-art, demonstrating its superiority in video-text representation learning.actbct * This work was done when Linchao Zhu visited Baidu Research. Yi Yang is the corresponding author.

最近，语音表示学习改善了许多与语音有关的任务，例如语音识别，语音分类和语音到文本翻译。但是，以上所有任务都朝着语音理解的方向发展，但是对于反向方向，言语综合，由于产生高质量语音的挑战性质，代表性学习的潜力尚未实现。为了解决这个问题，我们提出了我们的框架，对准的声音文本预处理（$^3 $ t），该框架在培训期间重建了带有文本输入和声学文本对齐的蒙面声信号。通过这种方式，预处理的模型可以生成高质量的重建频谱图，可以直接应用于语音编辑和看不见的扬声器tts。实验显示了$^3 $ t在语音编辑上的SOTA模型，并在没有外部说话者验证模型的情况下改善了多扬声器语音综合。

We present XKD, a novel self-supervised framework to learn meaningful representations from unlabelled video clips. XKD is trained with two pseudo tasks. First, masked data reconstruction is performed to learn modality-specific representations. Next, self-supervised cross-modal knowledge distillation is performed between the two modalities through teacher-student setups to learn complementary information. To identify the most effective information to transfer and also to tackle the domain gap between audio and visual modalities which could hinder knowledge transfer, we introduce a domain alignment strategy for effective cross-modal distillation. Lastly, to develop a general-purpose solution capable of handling both audio and visual streams, a modality-agnostic variant of our proposed framework is introduced, which uses the same backbone for both audio and visual modalities. Our proposed cross-modal knowledge distillation improves linear evaluation top-1 accuracy of video action classification by 8.4% on UCF101, 8.1% on HMDB51, 13.8% on Kinetics-Sound, and 14.2% on Kinetics400. Additionally, our modality-agnostic variant shows promising results in developing a general-purpose network capable of handling different data streams. The code is released on the project website.

Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respectively. We use VideoBERT in numerous tasks, including action classification and video captioning. We show that it can be applied directly to openvocabulary classification, and confirm that large amounts of training data and cross-modal information are critical to performance. Furthermore, we outperform the state-of-theart on video captioning, and quantitative results verify that the model learns high-level semantic features.

While the Turkish language is listed among low-resource languages, literature on Turkish automatic speech recognition (ASR) is relatively old. In this report, we present our findings on Turkish ASR with speech representation learning using HUBERT. We investigate pre-training HUBERT for Turkish with large-scale data curated from online resources. We pre-train our model using 6,500 hours of speech data from YouTube. The results show that the models are not ready for commercial use since they are not robust against disturbances that typically occur in real-world settings such as variations in accents, slang, background noise and interference. We analyze typical errors and the limitations of the models for use in commercial settings.