Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the type or extent of information encoded in the pre-trained representations themselves. Developing such insights can help understand the capabilities and limits of these models and enable the research community to more efficiently develop their usage for downstream applications. In this work, we begin to fill this gap by examining one recent and successful pre-trained model (wav2vec 2.0), via its intermediate representation vectors, using a suite of analysis tools. We use the metrics of canonical correlation, mutual information, and performance on simple downstream tasks with non-parametric probes, in order to (i) query for acoustic and linguistic information content, (ii) characterize the evolution of information across model layers, and (iii) understand how fine-tuning the model for automatic speech recognition (ASR) affects these observations. Our findings motivate modifying the fine-tuning protocol for ASR, which produces improved word error rates in a low-resource setting.

Many self-supervised speech models, varying in their pre-training objective, input modality, and pre-training data, have been proposed in the last few years. Despite impressive empirical successes on downstream tasks, we still have a limited understanding of the properties encoded by the models and the differences across models. In this work, we examine the intermediate representations for a variety of recent models. Specifically, we measure acoustic, phonetic, and word-level properties encoded in individual layers, using a lightweight analysis tool based on canonical correlation analysis (CCA). We find that these properties evolve across layers differently depending on the model, and the variations relate to the choice of pre-training objective. We further investigate the utility of our analyses for downstream tasks by comparing the property trends with performance on speech recognition and spoken language understanding tasks. We discover that CCA trends provide reliable guidance to choose layers of interest for downstream tasks and that single-layer performance often matches or improves upon using all layers, suggesting implications for more efficient use of pre-trained models.

Self-supervised speech models have grown fast during the past few years and have proven feasible for use in various downstream tasks. Some recent work has started to look at the characteristics of these models, yet many concerns have not been fully addressed. In this work, we conduct a study on emotional corpora to explore a popular self-supervised model -- wav2vec 2.0. Via a set of quantitative analysis, we mainly demonstrate that: 1) wav2vec 2.0 appears to discard paralinguistic information that is less useful for word recognition purposes; 2) for emotion recognition, representations from the middle layer alone perform as well as those derived from layer averaging, while the final layer results in the worst performance in some cases; 3) current self-supervised models may not be the optimal solution for downstream tasks that make use of non-lexical features. Our work provides novel findings that will aid future research in this area and theoretical basis for the use of existing models.

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

最近，先驱工作发现，演讲预训练模型可以解决全堆栈语音处理任务，因为该模型利用底层学习扬声器相关信息和顶层以编码与内容相关的信息。由于网络容量有限，我们认为如果模型专用于音频内容信息学习，则可以进一步提高语音识别性能。为此，我们向自我监督学习（ILS-SSL）提出中间层监督，这将模型通过在中间层上添加额外的SSL丢失来尽可能地专注于内容信息。 LibrisPeech测试 - 其他集合的实验表明，我们的方法显着优于Hubert，这实现了基数/大型模型的W / O语言模型设置的相对字错误率降低了23.5％/ 11.6％。详细分析显示我们模型的底层与拼音单元具有更好的相关性，这与我们的直觉一致，并解释了我们对ASR的方法的成功。

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。

由自我发项层组成的大型，预训练的神经网络（变形金刚）最近在几种语音情绪识别（SER）数据集上取得了最新的结果。这些模型通常以自我监督的方式进行预训练，以提高自动语音识别性能，从而了解语言信息。在这项工作中，我们研究了在Ser微调过程中利用此信息的程度。使用基于开源工具的可重现方法，我们在改变文本的情感时综合了韵律中性的语音话语。变压器模型的价预测对正面和负面情绪含量以及否定性非常反应，但对增强剂或还原器不反应，而这些语言特征都没有影响唤醒或优势。这些发现表明，变形金刚可以成功利用语言信息来改善其价预测，并且应将语言分析包括在其测试中。

已经证明，基于自我监督的学习（SSL）模型可以生成强大的表示，可用于改善下游语音任务的性能。可以使用几种最先进的SSL模型，并且这些模型中的每一个都优化了不同的损失，这会导致其功能互补的可能性。本文提出了使用此类SSL表示和模型的集合，该集合利用了各种预审预周化模型提取的特征的互补性质。我们假设这导致了更丰富的特征表示，并显示了ASR下游任务的结果。为此，我们使用了三个SSL模型，这些模型在ASR任务上显示出了出色的结果，即Hubert，Wav2Vec2.0和小波。我们使用从预训练的模型获得下游ASR任务的嵌入方式来探索用于ASR任务的模型集合和功能集合。我们使用LiblisPeech（100H）和WSJ数据集的单个模型和预训练的功能获得了改进的性能，用于下游任务。

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

口语语言理解（SLU）任务涉及从语音音频信号映射到语义标签。鉴于此类任务的复杂性，可能预期良好的性能需要大量标记的数据集，这很难为每个新任务和域收集。但是，最近的自我监督讲话表现的进步使得考虑使用有限标记的数据学习SLU模型是可行的。在这项工作中，我们专注于低资源讨论（ner）并解决问题：超越自我监督的预培训，我们如何使用未为任务注释的外部语音和/或文本数据？我们借鉴了各种方法，包括自我训练，知识蒸馏和转移学习，并考虑其对端到端模型和管道（语音识别后跟文本型号）的适用性。我们发现，这些方法中的几种方法可以在资源受限的环境中提高绩效，超出了训练有素的表示的福利。与事先工作相比，我们发现改进的F1分数高达16％。虽然最好的基线模型是一种管道方法，但使用外部数据时最终通过端到端模型实现的最佳性能。我们提供了详细的比较和分析，例如，端到端模型能够专注于更加立列人的单词。

Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task. In audio/speech signal processing, a wide range of features where engineered through decades of research efforts. As it turns out, learning to predict such features (a.k.a pseudo-labels) has proven to be a particularly relevant pretext task, leading to useful self-supervised representations which prove to be effective for downstream tasks. However, methods and common practices for combining such pretext tasks for better performance on the downstream task have not been explored and understood properly. In fact, the process relies almost exclusively on a computationally heavy experimental procedure, which becomes intractable with the increase of the number of pretext tasks. This paper introduces a method to select a group of pretext tasks among a set of candidates. The method we propose estimates calibrated weights for the partial losses corresponding to the considered pretext tasks during the self-supervised training process. The experiments conducted on automatic speech recognition, speaker and emotion recognition validate our approach, as the groups selected and weighted with our method perform better than classic baselines, thus facilitating the selection and combination of relevant pseudo-labels for self-supervised representation learning.

口头语言建模的最新工作表明，可以从原始音频中学习语言的可能性，而无需任何文本标签。该方法首先依赖于将音频转换为一系列离散单元（或伪文本），然后直接在此类伪文本上训练语言模型。这是必要的离散瓶颈，在语音信号的编码中可能引入不可逆转的错误，还是我们可以完全没有离散单位学习语言模型？在这项工作中，我们研究了离散和连续表示在口语建模中的作用。我们表明，离散化对于口语建模的良好结果确实至关重要。我们表明，离散化可以从连续功能中消除语言上无关的信息，从而有助于提高语言建模表演。在这项研究的基础上，我们培训了Hubert功能离散单元的语言模型，达到新的最先进的结果，导致了零资源语音挑战的词汇，句法和语义指标2021（轨道1-仅讲话）。

学习高级语音表征的自学学习（SSL）一直是在低资源环境中构建自动语音识别（ASR）系统的一种流行方法。但是，文献中提出的共同假设是，可以使用可用于SSL预训练的相同域或语言的大量未标记数据，我们承认，在现实世界中，这是不可行的。在本文中，作为Interspeech Gram Vaani ASR挑战的一部分，我们尝试研究域，语言，数据集大小和上游训练SSL数据对最终性能下游ASR任务的效果。我们还建立在持续的训练范式的基础上，以研究使用SSL训练的模型所拥有的先验知识的效果。广泛的实验和研究表明，ASR系统的性能易受用于SSL预训练的数据。它们的性能随着相似性和预训练数据量的增加而提高。我们认为，我们的工作将有助于语音社区在低资源环境中建立更好的ASR系统，并引导研究改善基于SSL的语音系统预培训的概括。

End-to-end text-to-speech synthesis (TTS) can generate highly natural synthetic speech from raw text. However, rendering the correct pitch accents is still a challenging problem for end-to-end TTS. To tackle the challenge of rendering correct pitch accent in Japanese end-to-end TTS, we adopt PnG~BERT, a self-supervised pretrained model in the character and phoneme domain for TTS. We investigate the effects of features captured by PnG~BERT on Japanese TTS by modifying the fine-tuning condition to determine the conditions helpful inferring pitch accents. We manipulate content of PnG~BERT features from being text-oriented to speech-oriented by changing the number of fine-tuned layers during TTS. In addition, we teach PnG~BERT pitch accent information by fine-tuning with tone prediction as an additional downstream task. Our experimental results show that the features of PnG~BERT captured by pretraining contain information helpful inferring pitch accent, and PnG~BERT outperforms baseline Tacotron on accent correctness in a listening test.

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。

Self-supervised pre-trained transformers have improved the state of the art on a variety of speech tasks. Due to the quadratic time and space complexity of self-attention, they usually operate at the level of relatively short (e.g., utterance) segments. In this paper, we study the use of context, i.e., surrounding segments, during fine-tuning and propose a new approach called context-aware fine-tuning. We attach a context module on top of the last layer of a pre-trained model to encode the whole segment into a context embedding vector which is then used as an additional feature for the final prediction. During the fine-tuning stage, we introduce an auxiliary loss that encourages this context embedding vector to be similar to context vectors of surrounding segments. This allows the model to make predictions without access to these surrounding segments at inference time and requires only a tiny overhead compared to standard fine-tuned models. We evaluate the proposed approach using the SLUE and Librilight benchmarks for several downstream tasks: Automatic speech recognition (ASR), named entity recognition (NER), and sentiment analysis (SA). The results show that context-aware fine-tuning not only outperforms a standard fine-tuning baseline but also rivals a strong context injection baseline that uses neighboring speech segments during inference.

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。

Automatic Speech Recognition (ASR) systems frequently use a search-based decoding strategy aiming to find the best attainable transcript by considering multiple candidates. One prominent speech recognition decoding heuristic is beam search, which seeks the transcript with the greatest likelihood computed using the predicted distribution. While showing substantial performance gains in various tasks, beam search loses some of its effectiveness when the predicted probabilities are highly confident, i.e., the predicted distribution is massed for a single or very few classes. We show that recently proposed Self-Supervised Learning (SSL)-based ASR models tend to yield exceptionally confident predictions that may hamper beam search from truly considering a diverse set of candidates. We perform a layer analysis to reveal and visualize how predictions evolve, and propose a decoding procedure that improves the performance of fine-tuned ASR models. Our proposed approach does not require further training beyond the original fine-tuning, nor additional model parameters. In fact, we find that our proposed method requires significantly less inference computation than current approaches. We propose aggregating the top M layers, potentially leveraging useful information encoded in intermediate layers, and relaxing model confidence. We demonstrate the effectiveness of our approach by conducting an empirical study on varying amounts of labeled resources and different model sizes, showing consistent improvements in particular when applied to low-resource scenarios.

Collecting sufficient labeled data for spoken language understanding (SLU) is expensive and time-consuming. Recent studies achieved promising results by using pre-trained models in low-resource scenarios. Inspired by this, we aim to ask: which (if any) pre-training strategies can improve performance across SLU benchmarks? To answer this question, we employ four types of pre-trained models and their combinations for SLU. We leverage self-supervised speech and language models (LM) pre-trained on large quantities of unpaired data to extract strong speech and text representations. We also explore using supervised models pre-trained on larger external automatic speech recognition (ASR) or SLU corpora. We conduct extensive experiments on the SLU Evaluation (SLUE) benchmark and observe self-supervised pre-trained models to be more powerful, with pre-trained LM and speech models being most beneficial for the Sentiment Analysis and Named Entity Recognition task, respectively.

我们提出了一项对基于自我监督的语音表示（S3R）语音转换（VC）的大规模比较研究。在识别合成VC的背景下，S3RS由于其替代昂贵的监督表示的潜力，例如语音后验（PPG），因此很有吸引力，这些表示是由最先进的VC系统采用的。使用先前开发的开源VC软件S3PRL-VC，我们在三种VC设置下提供了一系列深入的目标和主观分析：内部/跨语义的任何一对一（A2O）和任何对象 - 使用语音转换挑战2020（VCC2020）数据集。我们在各个方面研究了基于S3R的VC，包括模型类型，多语言和监督。我们还研究了通过K-均值聚类的滴定过程的效果，并展示了其在A2A设置中的改进。最后，与最先进的VC系统的比较证明了基于S3R的VC的竞争力，并阐明了可能的改进方向。