Recent advancements in speech synthesis have significantly improved the audio quality and pronunciation of synthesized speech.To further advance toward human-like conversational speech synthesis, this paper presents Filler-Speech, a novel speech synthesis framework that enables natural filler insertion and control over filler style.To address this, we construct a filler-inclusive speech data, derived from the open-source large-scale speech corpus.This data includes fillers with pitch and duration information.For the generation and style control of natural fillers, we propose a method that tokenizes the filler style and utilizes crossattention with the input text.Furthermore, we introduce a large language model-based filler prediction method that enables natural insertion of fillers even when only text input is provided.The experimental results demonstrate that the constructed dataset is valid and that our proposed methods for filler style control and filler prediction are effective.

Infectious diseases have caused significant economic and human losses worldwide. Growing concerns exist regarding climate change potentially exacerbating the spread of these diseases, particularly those transmitted by vectors such as ticks and mosquitoes. Tick-borne diseases, such as Severe Fever with Thrombocytopenia Syndrome (SFTS), can be particularly detrimental to elderly and immunocompromised individuals. This study utilizes a mathematical modeling approach to predict changes in tick populations under climate change scenarios, incorporating tick ecology and climate-sensitive parameters. Sensitivity analysis is performed to investigate the factors influencing tick population dynamics. The study further explores effective tick control strategies and their cost-effectiveness in the context of climate change. The findings indicate that the efficacy of tick population reduction varies greatly depending on the timing of control measure implementation and the effectiveness of the control strategies exhibits a strong dependence on the duration of implementation. Furthermore, as climate change intensifies, tick populations are projected to increase, leading to a rise in control costs and SFTS cases. In light of these findings, identifying and implementing appropriate control measures to manage tick populations under climate change will be increasingly crucial.

This paper proposes a multi-emotion, multi-lingual, and multi-speaker text-to-speech (MELS-TTS) system, employing disentangled style tokens for effective emotion transfer. In speech encompassing various attributes, such as emotional state, speaker identity, and linguistic style, disentangling these elements is crucial for an efficient multi-emotion, multi-lingual, and multi-speaker TTS system. To accomplish this purpose, we propose to utilize separate style tokens to disentangle emotion, language, speaker, and residual information, inspired by the global style tokens (GSTs). Through the attention mechanism, each style token learns its respective speech attribute from the target speech. Our proposed approach yields improved performance in both objective and subjective evaluations, demonstrating the ability to generate cross-lingual speech with diverse emotions, even from a neutral source speaker, while preserving the speaker’s identity.

Multispectral (MS) imaging systems have a wide range of applications for computer vision and computational photography tasks, but do not yet enjoy widespread adoption due to their prohibitive costs. Recently, advances in the design and fabrication of photonic metamaterials have enabled the development of MS sensors suitable for integration into consumer grade mobile devices. Augmenting existing RGB cameras and their processing algorithms with richer spectral information has the potential to be utilized in many steps of the image processing pipeline, but diverse real world datasets suitable for conducting such research are not freely available. We introduce Beyond RGB1, a real-world dataset comprising thousands of multispectral and RGB images in diverse real world and lab conditions that is suitable for the development and evaluation of algorithms utilizing multispectral and RGB data. All the scenes in our dataset include a colorimetric reference and a measurement of the spectrum of the scene illuminant. Additionally, we demonstrate the practical use of our dataset through the introduction of a novel illuminant spectral estimation (ISE) algorithm. Our algorithm surpasses the current state-of-the-art (SoTA) by up to 58.6% on established benchmarks and sets a baseline performance on our own dataset.

We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into i.i.d. “bags”, and only the frequency of class labels at each bag is available. Albeit, the objective of the learner is to achieve low task loss at an individual instance level. Here we propose EASYLLP, a flexible and simple-to-implement debiasing approach based on aggregate labels, which operates on arbitrary loss functions. Our technique allows us to accurately estimate the expected loss of an arbitrary model at an individual level. We elucidate the differences between our method and standard methods based on label proportion matching, in terms of applicability and optimality conditions. We showcase the flexibility of our approach compared to alternatives by applying our method to popular learning frameworks, like Empirical Risk Minimization (ERM) and Stochastic Gradient Descent (SGD) with provable guarantees on instance level performance. Finally, we validate our theoretical results on multiple datasets, empirically illustrating the conditions under which our algorithm is expected to perform better or worse than previous LLP approaches

Multi-label classification (MLC) has wide practical importance, but the theoretical understanding of its statistical properties is still limited. As an attempt to fill this gap, we thoroughly study upper and lower regret bounds for two canonical MLC performance measures, Hamming loss and Precision@$\kappa$. We consider two different statistical and algorithmic settings, a non-parametric setting tackled by plug-in classifiers \`a la $k$-nearest neighbors, and a parametric one tackled by empirical risk minimization operating on surrogate loss functions. For both, we analyze the interplay between a natural MLC variant of the low noise assumption, widely studied in binary classification, and the label sparsity, the latter being a natural property of large-scale MLC problems. We show that those conditions are crucial in improving the bounds, but the way they are tangled is not obvious, and also different across the two settings.

In this paper, we investigate multi-speaker emotional acoustic modeling methods for convolutional neural network (CNN) based speech synthesis system. For emotion modeling, we extend to the speech synthesis system that learns a latent embedding space of emotion, derived from a desired emotional identity, and we use emotion code and mel-frequency spectrogram as an emotion identity. In order to model speaker variation in a text-to-speech (TTS) system, we use speaker representations such as trainable speaker embedding and speaker code. We have implemented speech synthesis systems combining speaker representation and emotion representation and compared them by experiments. Experimental results have demonstrated that the multi-speaker emotional speech synthesis approach using trainable speaker embedding and emotion representation from mel spectrogram achieves higher performance when compared with other approaches in terms of naturalness, speaker similarity, and emotion similarity.

We present an efficient method for training slack-rescaled structural SVM. Although finding the most violating label in a margin-rescaled formulation is often easy since the target function decomposes with respect to the structure, this is not the case for a slack-rescaled formulation, and finding the most violated label might be very difficult. Our core contribution is an efficient method for finding the most-violating-label in a slack-rescaled formulation, given an oracle that returns the most-violating-label in a (slightly modified) margin-rescaled formulation. We show that our method enables accurate and scalable training for slack-rescaled SVMs, reducing runtime by an order of magnitude compared to previous approaches to slack-rescaled SVMs.

This paper presents a novel haptic mouse system as a new human computer interface, which has a force feedback capability. A proposed haptic mouse can reflect 1 dof grabbing force as well as 2 dof translation force which can simulate more realistic virtual experience. Five-bar mechanism has been adapted to realize the 2 dof translation force feedback, and double prismatic joint type of mechanism has been used to implement the grabbing force feedback. Wire-driven mechanism is mainly used for actuation to reduce the backlash as well as to provide back-drivability. In addition, haptic rendering algorithm for the proposed haptic mouse have been developed to give feelings of weight, shape and surface texture. By adding haptic information to the visual and audio information, the haptic mouse system is expected to be useful by presenting more realistic interaction in e-commerce in the future.