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。
translated by 谷歌翻译
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%。
translated by 谷歌翻译
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。
translated by 谷歌翻译
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.
translated by 谷歌翻译
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.
translated by 谷歌翻译
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.
translated by 谷歌翻译
当前的文本到视频检索方法(T2VR)经过培训和测试,并在视频捕获方向的数据集(例如MSVD,MSR-VTT和VATEX)上进行了测试。这些数据集的一个关键属性是,假定视频在短时间内被暂时预先修剪,而提供的字幕很好地描述了视频内容的要旨。因此,对于给定的配对视频和标题,该视频应该与标题完全相关。但是,实际上,由于查询尚不清楚,因此预处理的视频剪辑可能不包含足够的内容来完全满足查询。这表明文学与现实世界之间存在差距。为了填补空白,我们在本文中提出了一个新颖的T2VR子任务,称为部分相关的视频检索(PRVR)。未修剪的视频被认为是部分相关的W.R.T.给定的文本查询是否包含与查询相关的时刻。 PRVR旨在从大量未修剪视频中检索此类相关视频。 PRVR与单个视频时刻检索和视频语料库时刻的检索有所不同,因为后两个是要检索时刻而不是未修剪的视频。我们将PRVR作为多个实例学习(MIL)问题,同时将视频视为一袋视频片段和一袋视频帧。剪辑和帧表示不同时间尺度的视频内容。我们提出了一个多尺度的相似性学习(MS-SL)网络,该网络共同学习PRVR的剪辑规模和框架尺度相似性。在三个数据集(TVR,ActivityNet字幕和Charades-STA)上进行了广泛的实验,证明了该方法的可行性。我们还表明,我们的方法可用于改善视频语料库时刻的检索。
translated by 谷歌翻译
由于其在许多有影响力的领域中的广泛应用,归因网络上的图形异常检测已成为普遍的研究主题。在现实情况下,属性网络中的节点和边缘通常显示出不同的异质性,即不同类型的节点的属性显示出大量的多样性,不同类型的关系表示多种含义。在这些网络中,异常在异质性的各个角度上的表现通常与大多数不同。但是,现有的图异常检测方法不能利用归因网络中的异质性,这与异常检测高度相关。鉴于这个问题,我们提出了前方的提议:基于编码器解码器框架的异质性无监督图异常检测方法。具体而言,对于编码器,我们设计了三个关注级别,即属性级别,节点类型级别和边缘级别的关注,以捕获网络结构的异质性,节点属性和单个节点的信息。在解码器中,我们利用结构,属性和节点类型重建项来获得每个节点的异常得分。广泛的实验表明,与无监督环境中的艺术品相比,在几个现实世界中的异质信息网络上,前方的优势。进一步的实验验证了我们三重注意力,模型骨干和解码器的有效性和鲁棒性。
translated by 谷歌翻译
胎儿超声(US)中胎盘的自动分割由于(i)(i)胎盘外观的高度多样性而具有挑战性我们禁止在妊娠晚期进行整个胎盘评估的观点。在这项工作中,我们通过多任务学习方法解决了这三个挑战,该方法结合了单个卷积神经网络中胎盘位置(例如,前,后部)和语义胎盘分段的分类。通过分类任务,模型可以从更大,更多样化的数据集中学习,同时在有限的训练集条件下提高分割任务的准确性。通过这种方法,我们研究了多个评估者的注释的变异性,并表明我们的自动分割(前胎盘的骰子为0.86,后胎盘的骰子为0.83),与观察者内和观察者间的变异性相比,我们的自动段性能达到了人级的性能。最后,我们的方法可以使用由三个阶段组成的多视图US采集管道提供整个胎盘分割:多探针图像采集,图像融合和图像分段。这会导致对较大结构(例如胎盘中的胎盘)的高质量分割,其图像伪像降低,这超出了单个探针的视野。
translated by 谷歌翻译
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。
translated by 谷歌翻译