可以通过组合自动语音识别（ASR）和文本摘要（TS）来实现来自语音的文本摘要的语音摘要。通过这种级联方法，我们可以利用最先进的模型和大型训练数据集，用于两个子任务，即变压器和TS的ASR和双向编码器表示的变压器。但是，ASR错误直接影响级联方法的输出概要的质量。我们提出了一个级联语音摘要模型，它对ASR错误具有强大，并且利用ASR生成的多个假设来衰减摘要摘要的效果。我们调查了几个方案来组合ASR假设。首先，我们建议使用由ASR系统提供的其后部值作为基于BERT的TS系统的输入来加权的子字嵌入向量的总和。然后，我们介绍了一种更一般的方案，它使用添加到预先训练的BERT模块的关注的融合模块来对齐并组合几个ASR假设。最后，我们在How2 DataSet上执行语音摘要实验和我们将使用本文发布的新组合的基于TED的数据集。这些实验表明，通过这些方案再培训基于伯特的TS系统可以改善总结性能，并且基于注意的熔融模块特别有效。

Spoken language understanding (SLU) tasks have been studied for many decades in the speech research community, but have not received as much attention as lower-level tasks like speech and speaker recognition. In particular, there are not nearly as many SLU task benchmarks, and many of the existing ones use data that is not freely available to all researchers. Recent work has begun to introduce such benchmark datasets for several tasks. In this work, we introduce several new annotated SLU benchmark tasks based on freely available speech data, which complement existing benchmarks and address gaps in the SLU evaluation landscape. We contribute four tasks: question answering and summarization involve inference over longer speech sequences; named entity localization addresses the speech-specific task of locating the targeted content in the signal; dialog act classification identifies the function of a given speech utterance. We follow the blueprint of the Spoken Language Understanding Evaluation (SLUE) benchmark suite. In order to facilitate the development of SLU models that leverage the success of pre-trained speech representations, we will be publishing for each task (i) annotations for a relatively small fine-tuning set, (ii) annotated development and test sets, and (iii) baseline models for easy reproducibility and comparisons. In this work, we present the details of data collection and annotation and the performance of the baseline models. We also perform sensitivity analysis of pipeline models' performance (speech recognizer + text model) to the speech recognition accuracy, using more than 20 state-of-the-art speech recognition models.

Bidirectional Encoder Representations from Transformers (BERT; Devlin et al. 2019) represents the latest incarnation of pretrained language models which have recently advanced a wide range of natural language processing tasks. In this paper, we showcase how BERT can be usefully applied in text summarization and propose a general framework for both extractive and abstractive models. We introduce a novel document-level encoder based on BERT which is able to express the semantics of a document and obtain representations for its sentences. Our extractive model is built on top of this encoder by stacking several intersentence Transformer layers. For abstractive summarization, we propose a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two (the former is pretrained while the latter is not). We also demonstrate that a two-staged fine-tuning approach can further boost the quality of the generated summaries. Experiments on three datasets show that our model achieves stateof-the-art results across the board in both extractive and abstractive settings. 1

会话言论通常在话语水平上以松散的句法结构体现，但同时表现出连续话语的局部相干关系。事先工作已经表明，使用经常性神经网络或长短期存储器语言模型（LM）捕获较长的上下文信息可能遭受最近的偏置，而不是在远程上下文中。为了捕获词语和跨越话语之间的长期语义互动，我们提出了对话语音的自动语音识别（ASR）中语言建模的不同谈话历史融合方法。此外，引入了一种新的函数融合机制，该机制被引入熔断器并利用当前话语的声学嵌入和其相应的对话历史的语义含量以协作方式。为了塑造我们的想法，我们将ASR N-Best假设救援人员框架作为预测问题，利用BERT，一个标志性的预训练LM，作为成分车辆，以便于从给定的N最佳假设列表中选择Oracle假设。在AMI基准数据集上进行的实证实验似乎展示了我们对某些目前的线上的方法相关的可行性和功效。

在本文中，我们提出了一种新颖的架构，用于直接提取语音到语音摘要Essumm，它是一个无监督的模型，而无需依赖中间转录的文本。与以前的文本演示方法不同，我们旨在直接从语音中生成摘要，而无需转录。首先，根据语音信号的声学特征提取一组较小的语音段。对于每个候选语音段，为潜在的语音表示度度量设计了基于距离的汇总置信度评分。具体来说，我们利用现成的自我监督卷积神经网络来提取RAW Audio的深层语音功能。我们的方法会自动预测具有目标摘要长度的关键信息的最佳语音段序列。两个著名的会议数据集（AMI和ICSI语料库）的广泛结果表明，我们基于语音的直接方法通过未转录的数据提高汇总质量的有效性。我们还观察到，我们的无监督语音方法甚至在需要额外的语音识别的情况下以近期基于成绩单的摘要方法进行表现。

与单案摘要相比，抽象性多文件摘要（MDS）对其冗长和链接的来源的表示和覆盖范围提出了挑战。这项研究开发了一个平行的层次变压器（PHT），具有MDS的注意对齐。通过合并单词和段落级的多头注意，PHT的层次结构可以更好地处理令牌和文档级别的依赖项。为了指导解码到更好的源文档覆盖范围，然后将注意力调整机制引入以校准光束搜索，并预测的最佳注意力分布。根据Wikisum数据，进行了全面的评估，以测试拟议的体系结构对MD的改进。通过更好地处理内部和跨文档的信息，结果胭脂和人类评估都表明，我们的分层模型以相对较低的计算成本生成较高质量的摘要。

上下文化的单词嵌入会导致自然语言理解中最新的表演。最近，诸如BERT之类的预先训练的深层上下文化的文本编码器显示了其在改善包括抽象性摘要在内的自然语言任务方面的潜力。对话摘要中的现有方法着重于将大型语言模型纳入摘要任务，该任务是在大规模语料库中培训的，这些任务由新闻文章组成，而不是多个演讲者的对话。在本文中，我们介绍了自我监督的方法，以补偿培训对话摘要模型的缺点。我们的原则是使用借口对话文本检测不一致的信息流，以增强伯特对对话文本表示形式的上下文能力。我们使用增强的BERT在共享的编码器架构上构建并微调一个抽象的对话摘要模型。我们通过Samsum语料库（Samsum copus）进行了验证评估我们的抽象对话摘要，这是一个最近介绍的带有抽象性对话摘要的数据集。我们所有的方法都为在胭脂分数中测得的抽象摘要做出了改进。通过一项广泛的消融研究，我们还向关键模型超参数，切换话语和掩盖对话者的概率提出了灵敏度分析。

上下文ASR将偏见项列表与音频一起列出，随着ASR使用变得更加普遍，最近引起了最新的兴趣。我们正在发布上下文偏见列表，以伴随Enation21数据集，为此任务创建公共基准。我们使用WENET工具包中预处理的端到端ASR模型在此基准测试上介绍了基线结果。我们显示了应用于两种不同解码算法的浅融合上下文偏置的结果。我们的基线结果证实了观察到的观察，即端到端模型尤其是在训练过程中很少见或从未见过的单词，并且现有的浅融合技术不能充分解决这个问题。我们提出了一个替代拼写预测模型，与没有其他拼写的上下文偏见相比，相对相对，将稀有单词相对34.7％，而访问量的单词相对97.2％。该模型在概念上与先前工作中使用的模型相似，但是更容易实现，因为它不依赖发音字典或现有的文本对语音系统。

In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling key-words, capturing the hierarchy of sentence-toword structure, and emitting words that are rare or unseen at training time. Our work shows that many of our proposed models contribute to further improvement in performance. We also propose a new dataset consisting of multi-sentence summaries, and establish performance benchmarks for further research.

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.

Connectionist时间分类（CTC）的模型很有吸引力，因为它们在自动语音识别（ASR）中的快速推断。语言模型（LM）集成方法（例如浅融合和重新恢复）可以通过利用文本语料库的知识来提高基于CTC的ASR的识别准确性。但是，它们大大减慢了CTC的推论。在这项研究中，我们建议提炼基于CTC的ASR的BERT知识，从而扩展了我们先前针对基于注意的ASR的研究。基于CTC的ASR在训练过程中学习了BERT的知识，并且在测试过程中不使用BERT，从而维持CTC的快速推断。与基于注意力的模型不同，基于CTC的模型做出了框架级预测，因此它们需要与BERT的令牌级预测进行蒸馏。我们建议通过计算最合理的CTC路径来获得比对。对自发日语（CSJ）和TED-LIUM2语料库的实验评估表明，我们的方法改善了基于CTC的ASR的性能，而无需推理速度成本。

扬声器日流是一个标签音频或视频录制的任务，与扬声器身份或短暂的任务标记对应于扬声器标识的类，以识别“谁谈到何时发表讲话”。在早期，对MultiSpeaker录音的语音识别开发了扬声器日益衰退算法，以使扬声器自适应处理能够实现扬声器自适应处理。这些算法还将自己的价值作为独立应用程序随着时间的推移，为诸如音频检索等下游任务提供特定于扬声器的核算。最近，随着深度学习技术的出现，这在讲话应用领域的研究和实践中引起了革命性的变化，对扬声器日益改善已经进行了快速进步。在本文中，我们不仅审查了扬声器日益改善技术的历史发展，而且还审查了神经扬声器日益改善方法的最新进步。此外，我们讨论了扬声器日复速度系统如何与语音识别应用相结合，以及最近深度学习的激增是如何引领联合建模这两个组件互相互补的方式。通过考虑这种令人兴奋的技术趋势，我们认为本文对社区提供了有价值的贡献，以通过巩固具有神经方法的最新发展，从而促进更有效的扬声器日益改善进一步进展。

常规的自动语音识别系统不会产生标点符号，这对于语音识别结果的可读性很重要。随后的自然语言处理任务（例如机器翻译）也需要它们。标点符号预测模型上有许多作品将标点符号插入语音识别结果中作为后处理。但是，这些研究并未利用声学信息进行标点符号预测，并且直接受语音识别错误的影响。在这项研究中，我们提出了一个端到端模型，该模型将语音作为输入并输出标点的文本。在使用声学信息时，该模型有望在语音识别错误方面可靠地预测标点符号。我们还建议使用辅助损失，以使用中间层和未插入文本的输出来训练模型。通过实验，我们将提出的模型的性能与级联系统的性能进行比较。所提出的模型比级联系统获得更高的标点符号预测准确性，而无需牺牲语音识别错误率。还证明，使用中间输出针对未插入文本的多任务学习有效。此外，与级联系统相比，提出的模型仅具有约1/7的参数。

口语理解（SLU）系统提取文本成绩单和语义与意图和插槽相关的语言。 SLU系统通常由（1）自动语音识别（ASR）模块组成，（2）接口来自ASR相关输出的接口模块，以及（3）自然语言理解（NLU）模块。 SLU系统中的接口随附文本转录或更丰富的信息（例如从ASR到NLU）的信息。在本文中，我们研究界面如何影响与口语理解的联合培训。最值得注意的是，我们在公开可用的50小时SLURP数据集中获得了最新结果。我们首先利用通过文本界面连接的大型ASR和NLU模型，然后通过序列损耗函数共同训练这两个模型。对于未利用预位模型的场景，使用更丰富的神经界面通过联合序列损失训练获得了最佳结果。最后，我们显示了利用预期模型随培训数据规模增加的总体减少影响。

Nowadays, time-stamped web documents related to a general news query floods spread throughout the Internet, and timeline summarization targets concisely summarizing the evolution trajectory of events along the timeline. Unlike traditional document summarization, timeline summarization needs to model the time series information of the input events and summarize important events in chronological order. To tackle this challenge, in this paper, we propose a Unified Timeline Summarizer (UTS) that can generate abstractive and extractive timeline summaries in time order. Concretely, in the encoder part, we propose a graph-based event encoder that relates multiple events according to their content dependency and learns a global representation of each event. In the decoder part, to ensure the chronological order of the abstractive summary, we propose to extract the feature of event-level attention in its generation process with sequential information remained and use it to simulate the evolutionary attention of the ground truth summary. The event-level attention can also be used to assist in extracting summary, where the extracted summary also comes in time sequence. We augment the previous Chinese large-scale timeline summarization dataset and collect a new English timeline dataset. Extensive experiments conducted on these datasets and on the out-of-domain Timeline 17 dataset show that UTS achieves state-of-the-art performance in terms of both automatic and human evaluations.

诸如学术文章和商业报告之类的长期文件一直是详细说明重要问题和需要额外关注的复杂主题的标准格式。自动汇总系统可以有效地将长文档置于简短而简洁的文本中，以封装最重要的信息，从而在帮助读者的理解中很重要。最近，随着神经体系结构的出现，已经做出了重大的研究工作，以推动自动文本摘要系统，以及有关将这些系统扩展到长期文档领域的挑战的大量研究。在这项调查中，我们提供了有关长期文档摘要的研究的全面概述，以及其研究环境的三个主要组成部分的系统评估：基准数据集，汇总模型和评估指标。对于每个组成部分，我们在长期汇总的背景下组织文献，并进行经验分析，以扩大有关当前研究进度的观点。实证分析包括一项研究基准数据集的内在特征，摘要模型的多维分析以及摘要评估指标的综述。根据总体发现，我们通过提出可能在这个快速增长的领域中提出未来探索的方向来得出结论。

Summarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build. In this work, we propose a fully data-driven approach to abstractive sentence summarization. Our method utilizes a local attention-based model that generates each word of the summary conditioned on the input sentence. While the model is structurally simple, it can easily be trained end-to-end and scales to a large amount of training data. The model shows significant performance gains on the DUC-2004 shared task compared with several strong baselines.

Information overloading requires the need for summarizers to extract salient information from the text. Currently, there is an overload of dialogue data due to the rise of virtual communication platforms. The rise of Covid-19 has led people to rely on online communication platforms like Zoom, Slack, Microsoft Teams, Discord, etc. to conduct their company meetings. Instead of going through the entire meeting transcripts, people can use meeting summarizers to select useful data. Nevertheless, there is a lack of comprehensive surveys in the field of meeting summarizers. In this survey, we aim to cover recent meeting summarization techniques. Our survey offers a general overview of text summarization along with datasets and evaluation metrics for meeting summarization. We also provide the performance of each summarizer on a leaderboard. We conclude our survey with different challenges in this domain and potential research opportunities for future researchers.

通过言语技术的最新进步和智能助理的引入，如亚马逊Alexa，Apple Siri和Google Home，越来越多的用户通过语音命令与各种应用程序进行交互。电子商务公司通常在其网页上显示较短的产品标题，在需要简洁时，可以在其网页上进行人工策划或算法生成。然而，这些标题与自然语言不同。例如，“幸运的魅力面筋无麸质谷物，20.5盎司盒装幸运魅力含有无麸质”可以在网页上显示，而在基于语音的文本到语音应用程序中不能使用类似的标题。在这种对话系统中，易于理解的句子，例如“20.5盎司的幸运魅力麸质谷物”是优选的。与显示设备相比，可以向用户呈现图像和详细的产品信息，在与语音助手相互作用时，需要传达最重要信息的产品的短标题。我们提出Ebert，通过进一步预先训练电子商务产品描述语料库中的BERT嵌入来进行序列到序列方法，然后微调结果模型，以产生来自输入Web标题的短，自然的语言标题。我们对现实世界行业数据集的广泛实验，以及对模型输出的人类评估，表明Ebert摘要优于相当的基线模型。由于该模型的功效，该模型的版本已在真实世界中进行部署。

Transformers are among the state of the art for many tasks in speech, vision, and natural language processing, among others. Self-attentions, which are crucial contributors to this performance have quadratic computational complexity, which makes training on longer input sequences challenging. Prior work has produced state-of-the-art transformer variants with linear attention, however, current models sacrifice performance to achieve efficient implementations. In this work, we develop a novel linear transformer by examining the properties of the key-query product within self-attentions. Our model outperforms state of the art approaches on speech recognition and speech summarization, resulting in 1 % absolute WER improvement on the Librispeech-100 speech recognition benchmark and a new INTERVIEW speech recognition benchmark, and 5 points on ROUGE for summarization with How2.