We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.

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。

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.

最近的言语和语言技术的方法预先rain非常大型模型，用于特定任务。然而，这种大型模型的好处通常仅限于世界上少数资源丰富的语言。在这项工作中，我们对来自印度次大陆的低资源语言构建ASR系统进行多种贡献。首先，我们从各种领域策划40个印度语言的17,000小时的原始语音数据，包括教育，新闻，技术和金融。其次，使用这种原始语音数据，我们预先存在于40个印度语言的Wav2Vec样式模型的多个变体。第三，我们分析佩带的模型以查找关键特点：码本矢量的类似探测音素在语言中共享，跨层的表示是语言系列的判别，并且注意力头通常会在小型本地窗口中注意。第四，我们微调了9种语言的下游ASR模型，并在3个公共数据集上获得最先进的结果，包括非常低的资源语言，如Sinhala和Nepali。我们的工作建立了多语言预介质是建立ASR系统的有效策略，为印度次大陆的语言上不同的扬声器建立ASR系统。

自动语音识别和文本到语音系统主要以监督方式培训，需要高质量，准确标记的语音数据集。在这项工作中，我们研究语音数据的常见问题，并为语音数据集的构建和交互式错误分析引入工具箱。施工工具基于K \“urzinger等。工作，并且，尽我们所知，数据集探索工具是世界上第一个这类开源工具。我们演示了如何应用这些工具来创建一个俄语语音数据集并分析现有语音数据集（多语种LibrisPeech，Mozilla Common语音）。该工具是开放的，作为Nemo框架的一部分。

We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of speech. To evaluate the quality of this parallel speech, we train bilingual speech-to-speech translation models on mined data only and establish extensive baseline results on EuroParl-ST, VoxPopuli and FLEURS test sets. Enabled by the multilinguality of SpeechMatrix, we also explore multilingual speech-to-speech translation, a topic which was addressed by few other works. We also demonstrate that model pre-training and sparse scaling using Mixture-of-Experts bring large gains to translation performance. The mined data and models are freely available.

开发语音技术是对低资源语言的挑战，其中注释和原始语音数据稀疏。马耳他是一种这样的语言。近年来，对马耳他的计算处理有所增加，包括语音技术，但后者的资源仍然稀疏。在本文中，我们考虑提高这些语言的语音识别的数据增强技术，专注于马耳他作为测试用例。我们考虑三种不同类型的数据增强：无监督的培训，多语言培训和合成演讲的使用作为培训数据。目标是确定这些技术或它们的组合，是改善起始点是大约7小时转录语音的语言的语言的最有效。我们的结果表明，在这里研究了三种数据增强技术，导致我们在不使用语言模型的情况下实现15％的绝对增长。

Personal assistants, automatic speech recognizers and dialogue understanding systems are becoming more critical in our interconnected digital world. A clear example is air traffic control (ATC) communications. ATC aims at guiding aircraft and controlling the airspace in a safe and optimal manner. These voice-based dialogues are carried between an air traffic controller (ATCO) and pilots via very-high frequency radio channels. In order to incorporate these novel technologies into ATC (low-resource domain), large-scale annotated datasets are required to develop the data-driven AI systems. Two examples are automatic speech recognition (ASR) and natural language understanding (NLU). In this paper, we introduce the ATCO2 corpus, a dataset that aims at fostering research on the challenging ATC field, which has lagged behind due to lack of annotated data. The ATCO2 corpus covers 1) data collection and pre-processing, 2) pseudo-annotations of speech data, and 3) extraction of ATC-related named entities. The ATCO2 corpus is split into three subsets. 1) ATCO2-test-set corpus contains 4 hours of ATC speech with manual transcripts and a subset with gold annotations for named-entity recognition (callsign, command, value). 2) The ATCO2-PL-set corpus consists of 5281 hours of unlabeled ATC data enriched with automatic transcripts from an in-domain speech recognizer, contextual information, speaker turn information, signal-to-noise ratio estimate and English language detection score per sample. Both available for purchase through ELDA at http://catalog.elra.info/en-us/repository/browse/ELRA-S0484. 3) The ATCO2-test-set-1h corpus is a one-hour subset from the original test set corpus, that we are offering for free at https://www.atco2.org/data. We expect the ATCO2 corpus will foster research on robust ASR and NLU not only in the field of ATC communications but also in the general research community.

Modern speech recognition systems exhibits rapid performance degradation under domain shift. This issue is especially prevalent in data-scarce settings, such as low-resource languages, where diversity of training data is limited. In this work we propose M2DS2, a simple and sample-efficient finetuning strategy for large pretrained speech models, based on mixed source and target domain self-supervision. We find that including source domain self-supervision stabilizes training and avoids mode collapse of the latent representations. For evaluation, we collect HParl, a $120$ hour speech corpus for Greek, consisting of plenary sessions in the Greek Parliament. We merge HParl with two popular Greek corpora to create GREC-MD, a test-bed for multi-domain evaluation of Greek ASR systems. In our experiments we find that, while other Unsupervised Domain Adaptation baselines fail in this resource-constrained environment, M2DS2 yields significant improvements for cross-domain adaptation, even when a only a few hours of in-domain audio are available. When we relax the problem in a weakly supervised setting, we find that independent adaptation for audio using M2DS2 and language using simple LM augmentation techniques is particularly effective, yielding word error rates comparable to the fully supervised baselines.

自我监督学习（SSL）在语音识别方面取得了巨大的成功，而有限的探索已尝试完成其他语音处理任务。由于语音信号包含多方面的信息，包括说话者身份，副语言学，口语内容等，学习所有语音任务的通用表示都具有挑战性。为了解决该问题，我们提出了一个新的预培训模型WAVLM，以解决全堆栈的下游语音任务。 Wavlm共同学习了蒙面的语音预测和预训练。通过这种方式，WAVLM不仅可以通过掩盖的语音预测来保持语音内容建模能力，而且还可以通过语音denoing来提高非ASR任务的潜力。此外，WAVLM还采用封闭式的变压器结构的封闭相对位置偏置，以更好地捕获输入语音的序列排序。我们还将培训数据集从60k小时扩展到94K小时。 WAVLM大型在精湛的基准上实现了最先进的性能，并在其代表性基准上为各种语音处理任务带来了重大改进。代码和预培训模型可在https://aka.ms/wavlm上找到。

在本文中，我们介绍了从包含超过80,000个小时的未标记的语音的大型数据集预处理捷克单语音频变压器方面的进展，随后使用内域数据组合对自动语音识别任务进行微调，并对模型进行微调。6000小时的跨域转录语音。我们在两个公共数据集（CommunVoice和Voxpopuli）和Malach Project中的一个非常具有挑战性的数据集中评估了各种微调设置的大量实验调色板。我们的结果表明，单语WAV2VEC 2.0模型是强大的ASR系统，它可以利用大型标记和未标记的数据集并成功与最先进的LVCSR系统竞争。此外，当没有用于目标ASR任务的培训数据时，WAV2VEC模型被证明是很好的零射门学习者。

450万小时的英语演讲从10个不同的10个不同来源，跨越高达10亿参数的不同来源，我们探索了自动语音识别的规模前沿。我们提出了数据选择技术，以有效地缩放培训数据，以找到大规模数据集中最有价值的样本。为了有效地进行模型尺寸，我们利用各种优化，例如稀疏传感器丢失和模型分片。通过培训1-10B参数通用英语ASR模型，我们将语音识别性能的限制推动在许多域中。此外，我们的模型学习强大的语音表示，在新域名和言语方面具有零和少量功能，超出了多个内部和公共基准的先前结果。对于由于脑损伤而具有障碍的扬声器，我们最好的零射击和少量射频分别在Aphasiabank测试集中实现了22％和60％，同时在公共社交媒体视频中实现了最佳性能。此外，相同的通用模型在SPGISPeech Financial-Domain数据集上达到了500倍的域内数据等效性能。

在本文中，我们分享了我们努力建立能够翻译一千多种语言的实用机器翻译（MT）系统的发现。我们在三个研究领域中描述了结果：（i）通过利用半监督预训练的语言识别和开发数据驱动的过滤技术来构建1500多种语言的清洁，网挖数据集； （ii）通过利用大规模的多语言模型来开发用于服务不足的语言的实用MT模型，该模型训练了有监督的并行数据，以使用100多种高资源语言和单语言数据集，以增加1000多种语言； （iii）研究这些语言的评估指标的局限性，并对我们MT模型的输出进行定性分析，突出显示了这些类型模型的几种频繁误差模式。我们希望我们的工作为旨在为当前研究的语言构建MT系统的从业者提供有用的见解，并突出显示可以补充Data-Sparse设置中大量多语言模型的弱点的研究方向。

Transfer learning, where a model is first pre-trained on a data-rich task before being finetuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new "Colossal Clean Crawled Corpus", we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.

We demonstrate that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even becoming competitive with prior state-ofthe-art fine-tuning approaches. Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous nonsparse language model, and test its performance in the few-shot setting. For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks and few-shot demonstrations specified purely via text interaction with the model. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks. We also identify some datasets where GPT-3's few-shot learning still struggles, as well as some datasets where GPT-3 faces methodological issues related to training on large web corpora.

我们介绍了CVSS，这是一种大规模的多语言对语音转换（S2ST）语料库，从21种语言覆盖了21种语言的句子级并行S2ST对。通过将Covost 2从Covost 2的翻译文本综合将翻译文本与最先进的TTS系统合成语音，源自公共语音语音语料库和COVOST 2语音到文本转换（ST）语料库。提供了两个版本的翻译演讲：1）CVSS-C：所有翻译演讲都是一种高质量的规范声音; 2）CVSS-T：翻译语音从相应的源语音传输。此外，CVSS提供标准化的翻译文本，它与翻译语音中的发音匹配。在每个版本的CVSS上，我们建立了基线多语言直接S2ST模型和Cascade S2ST模型，验证了语料库的有效性。为了构建强大的Cascade S2ST基准，我们在Covost 2上培训了St模型，这优于前一种最先进的培训，而无需额外的数据。尽管如此，直接S2ST模型的性能在从头开始训练时接近强级联基线，并且在匹配ST模型中初始化时，仅在ASR转换转换时的0.1或0.7bleu差异。

作为人类，我们通过我们所有的感官来驾驭世界，使用每个人从每个人纠正其他人。我们介绍了Merlot Reserve，一个模型，该模型是联合随着时间的推移而表示视频的模型 - 通过从音频，字幕和视频帧学习的新培训目标。给出了一个视频，我们用掩模令牌替换文本和音频的片段;该模型通过选择正确的蒙版片段来学习。我们的目标比替代方面更快地学习，并在规模上表现良好：我们预先逼近2000万YouTube视频。经验结果表明，Merlot Reserve学会通过所有组成模式的视频的强烈陈述。在FineTuned时，它在VCR和TVQA上为VCR和TVQA进行了新的最先进，优先于前勤工作分别为5％和7％。消融表明，两个任务都受益于音频预制 - 甚至录像机，围绕图像中心的QA任务（没有声音）。此外，我们的客观使开箱即用的预测，揭示了强大的多式联合致辞理解。在一个完全零拍摄的环境中，我们的模型在四个视频理解任务中获得竞争结果，甚至优于最近提出的定位推理（星）基准的监督方法。我们分析为什么包含音频导致更好的视觉语言表示，这表明未来研究的重要机会。我们通过讨论多式联运预测的道德和社会影响来得出结论。

GPT-3等大型自回归语言模型是几秒钟的学习者，可以在没有微调的情况下执行各种语言任务。虽然已知这些模型能够共同代表许多不同的语言，但他们的培训数据由英语主导，可能限制了它们的交叉概括。在这项工作中，我们在覆盖多种语言的平衡语料库上培训多语言自回归语言模型，并在广泛的任务中研究他们几乎没有零点的学习能力。我们最大的模型，具有75亿参数，在20多种代表语言中，在几种代表语言中，在几种代表性语言中，在几种代表性语言中，在多语言型号推理中表现出可比大小的GPT-3（在0次设置和0次拍摄设置中的绝对精度改善+ 7.4％ 4-拍摄设置中的9.4％）和自然语言推理（每次拍摄和4次设置中的每一个+ 5.4％）。在Flores-101机器翻译基准测试中，我们的模型优于GPT-3在182个翻译方向上有32个培训例子，同时超过45个方向的官方监督基线。我们介绍了模型成功和失败的位置的详细分析，特别是它尤其显示在某些任务中实现交叉语境的内容学习，而仍然存在改善表面的鲁棒性和适应没有a的任务的余地自然冻结形式。最后，我们评估我们在仇恨语音检测中以五种语言的仇恨语音检测的模型，并发现它具有与可比大小的GPT-3模型类似的限制。

We present Mu$^{2}$SLAM, a multilingual sequence-to-sequence model pre-trained jointly on unlabeled speech, unlabeled text and supervised data spanning Automatic Speech Recognition (ASR), Automatic Speech Translation (AST) and Machine Translation (MT), in over 100 languages. By leveraging a quantized representation of speech as a target, Mu$^{2}$SLAM trains the speech-text models with a sequence-to-sequence masked denoising objective similar to T5 on the decoder and a masked language modeling (MLM) objective on the encoder, for both unlabeled speech and text, while utilizing the supervised tasks to improve cross-lingual and cross-modal representation alignment within the model. On CoVoST AST, Mu$^{2}$SLAM establishes a new state-of-the-art for models trained on public datasets, improving on xx-en translation over the previous best by 1.9 BLEU points and on en-xx translation by 1.1 BLEU points. On Voxpopuli ASR, our model matches the performance of an mSLAM model fine-tuned with an RNN-T decoder, despite using a relatively weaker sequence-to-sequence architecture. On text understanding tasks, our model improves by more than 6\% over mSLAM on XNLI, getting closer to the performance of mT5 models of comparable capacity on XNLI and TydiQA, paving the way towards a single model for all speech and text understanding tasks.

人民的言论是自由下载的30,000小时，并在CC-BY-SA下进行学术和商业用途的许可的受监管的会话英语语音识别数据集（具有CC-by子集）。通过使用现有转录搜索适当许可的音频数据来通过搜索互联网来收集数据。我们描述了我们的数据收集方法，并在Apache 2.0许可证下发布了我们的数据收集系统。我们表明，在此数据集上培训的模型在Librispeech的测试清洁测试集上实现了9.98％的单词错误率。最后，我们讨论了围绕创建一个相当大量的机器学习的法律和道德问题，并计划继续维护项目的计划根据MLCommons的赞助。