Text-to-speech synthesis (TTS) is a task to convert texts into speech. Two of the factors that have been driving TTS are the advancements of probabilistic models and latent representation learning. We propose a TTS method based on latent variable conversion using a diffusion probabilistic model and the variational autoencoder (VAE). In our TTS method, we use a waveform model based on VAE, a diffusion model that predicts the distribution of latent variables in the waveform model from texts, and an alignment model that learns alignments between the text and speech latent sequences. Our method integrates diffusion with VAE by modeling both mean and variance parameters with diffusion, where the target distribution is determined by approximation from VAE. This latent variable conversion framework potentially enables us to flexibly incorporate various latent feature extractors. Our experiments show that our method is robust to linguistic labels with poor orthography and alignment errors.

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.

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。

本文介绍了一个统一的源滤波器网络，具有谐波源源激发生成机制。在以前的工作中，我们提出了统一的源滤波器gan（USFGAN），用于开发具有统一源滤波器神经网络体系结构的灵活语音可控性的高保真神经声码器。但是，USFGAN对Aperiodic源激发信号进行建模的能力不足，并且自然语音和生成的语音之间的声音质量仍然存在差距。为了改善源激发建模和产生的声音质量，提出了一个新的源激励生成网络，分别生成周期性和大约组件。还采用了Hifigan的高级对抗训练程序来代替原始USFGAN中使用的平行波甘的训练。客观和主观评估结果都表明，经过修改的USFGAN可显着提高基本USFGAN的声音质量，同时保持语音可控性。

无需清洁参考，非侵入式语音评估方法对客观评估引起了很大的关注。最近，已经应用了深度神经网络（DNN）模型来构建非侵入式语音评估方法并确认提供了有希望的性能。但是，基于DNN的大多数方法都是针对正常听力侦听者设计的，而不考虑听力损失因素。在本研究中，我们提出了一种由双向长期内存（BLSTM）模型形成的DNN的助听器语音评估网络（HASA-Net），以根据输入语音信号和指定的同时预测语音质量和可懂度分数听力损失模式。据我们所知，Hasa-net是利用统一的DNN的非侵入性模型来融入质量和可智能性评估的第一项工作。实验结果表明，HASA-NET的预测语音质量和可智能性评分与两个公知的侵入性助听剂评估指标高度相关，助听器语音质量指数（HASQI）和助听器语音感知指数（HASPI）。

Fisher's criterion is a widely used tool in machine learning for feature selection. For large search spaces, Fisher's criterion can provide a scalable solution to select features. A challenging limitation of Fisher's criterion, however, is that it performs poorly when mean values of class-conditional distributions are close to each other. Motivated by this challenge, we propose an extension of Fisher's criterion to overcome this limitation. The proposed extension utilizes the available heteroscedasticity of class-conditional distributions to distinguish one class from another. Additionally, we describe how our theoretical results can be casted into a neural network framework, and conduct a proof-of-concept experiment to demonstrate the viability of our approach to solve classification problems.

Computer vision applications have heavily relied on the linear combination of Lambertian diffuse and microfacet specular reflection models for representing reflected radiance, which turns out to be physically incompatible and limited in applicability. In this paper, we derive a novel analytical reflectance model, which we refer to as Fresnel Microfacet BRDF model, that is physically accurate and generalizes to various real-world surfaces. Our key idea is to model the Fresnel reflection and transmission of the surface microgeometry with a collection of oriented mirror facets, both for body and surface reflections. We carefully derive the Fresnel reflection and transmission for each microfacet as well as the light transport between them in the subsurface. This physically-grounded modeling also allows us to express the polarimetric behavior of reflected light in addition to its radiometric behavior. That is, FMBRDF unifies not only body and surface reflections but also light reflection in radiometry and polarization and represents them in a single model. Experimental results demonstrate its effectiveness in accuracy, expressive power, and image-based estimation.

The detection of earthquakes is a fundamental prerequisite for seismology and contributes to various research areas, such as forecasting earthquakes and understanding the crust/mantle structure. Recent advances in machine learning technologies have enabled the automatic detection of earthquakes from waveform data. In particular, various state-of-the-art deep-learning methods have been applied to this endeavour. In this study, we proposed and tested a novel phase detection method employing deep learning, which is based on a standard convolutional neural network in a new framework. The novelty of the proposed method is its separate explicit learning strategy for global and local representations of waveforms, which enhances its robustness and flexibility. Prior to modelling the proposed method, we identified local representations of the waveform by the multiple clustering of waveforms, in which the data points were optimally partitioned. Based on this result, we considered a global representation and two local representations of the waveform. Subsequently, different phase detection models were trained for each global and local representation. For a new waveform, the overall phase probability was evaluated as a product of the phase probabilities of each model. This additional information on local representations makes the proposed method robust to noise, which is demonstrated by its application to the test data. Furthermore, an application to seismic swarm data demonstrated the robust performance of the proposed method compared with those of other deep learning methods. Finally, in an application to low-frequency earthquakes, we demonstrated the flexibility of the proposed method, which is readily adaptable for the detection of low-frequency earthquakes by retraining only a local model.

共享控制可以通过协助执行用户意图来帮助进行远程处理的对象操纵。为此，需要稳健和及时的意图估计，这取决于行为观察。在这里，提出了意图估计框架，该框架使用自然目光和运动功能来预测当前的动作和目标对象。该系统在模拟环境中进行了训练和测试，并在相对混乱的场景中和双手中产生的拾音器和放置序列，另一方面可能是手动。验证是在不同的用户和手中进行的，实现了预测的准确性和优势。对单个特征的预测能力的分析表明，在当前动作的早期识别中，抓握触发器和目光的凝视特征的优势。在当前的框架中，可以将相同的概率模型用于并行和独立工作的两只手，而提出了基于规则的模型来识别所得的双人动作。最后，讨论了这种方法对更复杂，全行为操纵的局限性和观点。

本文提出了一种通过视觉解释3D卷积神经网络（CNN）的决策过程的方法，并具有闭塞灵敏度分析的时间扩展。这里的关键思想是在输入3D时间空间数据空间中通过3D掩码遮住特定的数据，然后测量输出评分中的变更程度。产生较大变化程度的遮挡体积数据被认为是分类的更关键元素。但是，虽然通常使用遮挡敏感性分析来分析单个图像分类，但将此想法应用于视频分类并不是那么简单，因为简单的固定核心无法处理动作。为此，我们将3D遮挡掩模的形状调整为目标对象的复杂运动。通过考虑从输入视频数据中提取的光流的时间连续性和空间共存在，我们的灵活面膜适应性进行了。我们进一步建议通过使用分数的一阶部分导数相对于输入图像来降低其计算成本，以近似我们的方法。我们通过与删除/插入度量的常规方法和UCF-101上的指向度量来证明我们方法的有效性。该代码可在以下网址获得：https：//github.com/uchiyama33/aosa。