To further improve the speaking styles of synthesized speeches, current text-to-speech (TTS) synthesis systems commonly employ reference speeches to stylize their outputs instead of just the input texts. These reference speeches are obtained by manual selection which is resource-consuming, or selected by semantic features. However, semantic features contain not only style-related information, but also style irrelevant information. The information irrelevant to speaking style in the text could interfere the reference audio selection and result in improper speaking styles. To improve the reference selection, we propose Contrastive Acoustic-Linguistic Module (CALM) to extract the Style-related Text Feature (STF) from the text. CALM optimizes the correlation between the speaking style embedding and the extracted STF with contrastive learning. Thus, a certain number of the most appropriate reference speeches for the input text are selected by retrieving the speeches with the top STF similarities. Then the style embeddings are weighted summarized according to their STF similarities and used to stylize the synthesized speech of TTS. Experiment results demonstrate the effectiveness of our proposed approach, with both objective evaluations and subjective evaluations on the speaking styles of the synthesized speeches outperform a baseline approach with semantic-feature-based reference selection.
This study presents a novel multimodal fusion model for three-dimensional mineral prospectivity mapping (3D MPM), effectively integrating structural and fluid information through a deep network architecture. Leveraging Convolutional Neural Networks (CNN) and Multilayer Perceptrons (MLP), the model employs canonical correlation analysis (CCA) to align and fuse multimodal features. Rigorous evaluation on the Jiaojia gold deposit dataset demonstrates the model's superior performance in distinguishing ore-bearing instances and predicting mineral prospectivity, outperforming other models in result analyses. Ablation studies further reveal the benefits of joint feature utilization and CCA incorporation. This research not only advances mineral prospectivity modeling but also highlights the pivotal role of data integration and feature alignment for enhanced exploration decision-making.
Different machines can exhibit diverse frequency patterns in their emitted sound. This feature has been recently explored in anomaly sound detection and reached state-of-the-art performance. However, existing methods rely on the manual or empirical determination of the frequency filter by observing the effective frequency range in the training data, which may be impractical for general application. This paper proposes an anomalous sound detection method using self-attention-based frequency pattern analysis and spectral-temporal information fusion. Our experiments demonstrate that the self-attention module automatically and adaptively analyses the effective frequencies of a machine sound and enhances that information in the spectral feature representation. With spectral-temporal information fusion, the obtained audio feature eventually improves the anomaly detection performance on the DCASE 2020 Challenge Task 2 dataset.
Text augmentation is a technique for constructing synthetic data from an under-resourced corpus to improve predictive performance. Synthetic data generation is common in numerous domains. However, recently text augmentation has emerged in natural language processing (NLP) to improve downstream tasks. One of the current state-of-the-art text augmentation techniques is easy data augmentation (EDA), which augments the training data by injecting and replacing synonyms and randomly permuting sentences. One major obstacle with EDA is the need for versatile and complete synonym dictionaries, which cannot be easily found in low-resource languages. To improve the utility of EDA, we propose two extensions, easy distributional data augmentation (EDDA) and type specific similar word replacement (TSSR), which uses semantic word context information and part-of-speech tags for word replacement and augmentation. In an extensive empirical evaluation, we show the utility of the proposed methods, measured by F1 score, on two representative datasets in Swedish as an example of a low-resource language. With the proposed methods, we show that augmented data improve classification performances in low-resource settings.
Heterogeneous systems manipulation, i.e., manipulating rigid objects via deformable (soft) objects, is an emerging field that remains in its early stages of research. Existing works in this field suffer from limited action and operational space, poor generalization ability, and expensive development. To address these challenges, we propose a universally applicable and effective moving primitive, Iterative Grasp-Pull (IGP), and a sample-based framework, DeRi-IGP, to solve the heterogeneous system manipulation task. The DeRi-IGP framework uses local onboard robots' RGBD sensors to observe the environment, comprising a soft-rigid body system. It then uses this information to iteratively grasp and pull a soft body (e.g., rope) to move the attached rigid body to a desired location. We evaluate the effectiveness of our framework in solving various heterogeneous manipulation tasks and compare its performance with several state-of-the-art baselines. The result shows that DeRi-IGP outperforms other methods by a significant margin. In addition, we also demonstrate the advantage of the large operational space of IGP in the long-distance object acquisition task within both simulated and real environments.
Music genre classification has become increasingly critical with the advent of various streaming applications. Nowadays, we find it impossible to imagine using the artist's name and song title to search for music in a sophisticated music app. It is always difficult to classify music correctly because the information linked to music, such as region, artist, album, or non-album, is so variable. This paper presents a study on music genre classification using a combination of Digital Signal Processing (DSP) and Deep Learning (DL) techniques. A novel algorithm is proposed that utilizes both DSP and DL methods to extract relevant features from audio signals and classify them into various genres. The algorithm was tested on the GTZAN dataset and achieved high accuracy. An end-to-end deployment architecture is also proposed for integration into music-related applications. The performance of the algorithm is analyzed and future directions for improvement are discussed. The proposed DSP and DL-based music genre classification algorithm and deployment architecture demonstrate a promising approach for music genre classification.
Maps are essential to mobile robotics tasks like localization and planning. We propose the open street map (osm) XML based Area Graph file format to store hierarchical, topometric semantic multi-floor maps of indoor and outdoor environments, since currently no such format is popular within the robotics community. Building on-top of osm we leverage the available open source editing tools and libraries of osm, while adding the needed mobile robotics aspect with building-level obstacle representation yet very compact, topometric data that facilitates planning algorithms. Through the use of common osm keys as well as custom ones we leverage the power of semantic annotation to enable various applications. For example, we support planning based on robot capabilities, to take the locomotion mode and attributes in conjunction with the environment information into account. The provided C++ library is integrated into ROS. We evaluate the performance of osmAG using real data in a global path planning application on a very big osmAG map, demonstrating its convenience and effectiveness for mobile robots.
Hypergraphs can naturally model group-wise relations (e.g., a group of users who co-purchase an item) as hyperedges. Hyperedge prediction is to predict future or unobserved hyperedges, which is a fundamental task in many real-world applications (e.g., group recommendation). Despite the recent breakthrough of hyperedge prediction methods, the following challenges have been rarely studied: (C1) How to aggregate the nodes in each hyperedge candidate for accurate hyperedge prediction? and (C2) How to mitigate the inherent data sparsity problem in hyperedge prediction? To tackle both challenges together, in this paper, we propose a novel hyperedge prediction framework (CASH) that employs (1) context-aware node aggregation to precisely capture complex relations among nodes in each hyperedge for (C1) and (2) self-supervised contrastive learning in the context of hyperedge prediction to enhance hypergraph representations for (C2). Furthermore, as for (C2), we propose a hyperedge-aware augmentation method to fully exploit the latent semantics behind the original hypergraph and consider both node-level and group-level contrasts (i.e., dual contrasts) for better node and hyperedge representations. Extensive experiments on six real-world hypergraphs reveal that CASH consistently outperforms all competing methods in terms of the accuracy in hyperedge prediction and each of the proposed strategies is effective in improving the model accuracy of CASH. For the detailed information of CASH, we provide the code and datasets at: https://github.com/yy-ko/cash.
Semantic reasoning and dynamic planning capabilities are crucial for an autonomous agent to perform complex navigation tasks in unknown environments. It requires a large amount of common-sense knowledge, that humans possess, to succeed in these tasks. We present SayNav, a new approach that leverages human knowledge from Large Language Models (LLMs) for efficient generalization to complex navigation tasks in unknown large-scale environments. SayNav uses a novel grounding mechanism, that incrementally builds a 3D scene graph of the explored environment as inputs to LLMs, for generating feasible and contextually appropriate high-level plans for navigation. The LLM-generated plan is then executed by a pre-trained low-level planner, that treats each planned step as a short-distance point-goal navigation sub-task. SayNav dynamically generates step-by-step instructions during navigation and continuously refines future steps based on newly perceived information. We evaluate SayNav on a new multi-object navigation task, that requires the agent to utilize a massive amount of human knowledge to efficiently search multiple different objects in an unknown environment. SayNav outperforms an oracle based Point-nav baseline, achieving a success rate of 95.35% (vs 56.06% for the baseline), under the ideal settings on this task, highlighting its ability to generate dynamic plans for successfully locating objects in large-scale new environments. In addition, SayNav also enables efficient generalization from simulation to real environments.
This paper introduces the first two pixel retrieval benchmarks. Pixel retrieval is segmented instance retrieval. Like semantic segmentation extends classification to the pixel level, pixel retrieval is an extension of image retrieval and offers information about which pixels are related to the query object. In addition to retrieving images for the given query, it helps users quickly identify the query object in true positive images and exclude false positive images by denoting the correlated pixels. Our user study results show pixel-level annotation can significantly improve the user experience. Compared with semantic and instance segmentation, pixel retrieval requires a fine-grained recognition capability for variable-granularity targets. To this end, we propose pixel retrieval benchmarks named PROxford and PRParis, which are based on the widely used image retrieval datasets, ROxford and RParis. Three professional annotators label 5,942 images with two rounds of double-checking and refinement. Furthermore, we conduct extensive experiments and analysis on the SOTA methods in image search, image matching, detection, segmentation, and dense matching using our pixel retrieval benchmarks. Results show that the pixel retrieval task is challenging to these approaches and distinctive from existing problems, suggesting that further research can advance the content-based pixel-retrieval and thus user search experience. The datasets can be downloaded from \href{https://github.com/anguoyuan/Pixel_retrieval-Segmented_instance_retrieval}{this link}.