arXiv subjects

Shan Yang

Publications and source records attributed to Shan Yang.

At least 55 records · Page 3Linked to original sources

arXiv2024

TokSing: Singing Voice Synthesis based on Discrete Tokens

Recent advancements in speech synthesis witness significant benefits by leveraging discrete tokens extracted from self-supervised learning (SSL) models. Discrete tokens offer higher storage efficiency and greater operability in intermediate representations compared to traditional continuous Mel spectrograms. However, when it comes to singing voice synthesis(SVS), achieving higher levels of melody expression poses a great challenge for utilizing discrete tokens. In this paper, we introduce TokSing, a discrete-based SVS system equipped with a token formulator that offers flexible token blendings. We observe a melody degradation during discretization, prompting us to integrate a melody signal with the discrete token and incorporate a specially-designed melody enhancement strategy in the musical encoder. Extensive experiments demonstrate that our TokSing achieves better performance against the Mel spectrogram baselines while offering advantages in intermediate representation space cost and convergence speed.

cs.SD↗

arXiv2024

MLLMReID: Multimodal Large Language Model-based Person Re-identification

Multimodal large language models (MLLM) have achieved satisfactory results in many tasks. However, their performance in the task of ReID (ReID) has not been explored to date. This paper will investigate how to adapt them for the task of ReID. An intuitive idea is to fine-tune MLLM with ReID image-text datasets, and then use their visual encoder as a backbone for ReID. However, there still exist two apparent issues: (1) Designing instructions for ReID, MLLMs may overfit specific instructions, and designing a variety of instructions will lead to higher costs. (2) When fine-tuning the visual encoder of a MLLM, it is not trained synchronously with the ReID task. As a result, the effectiveness of the visual encoder fine-tuning cannot be directly reflected in the performance of the ReID task. To address these problems, this paper proposes MLLMReID: Multimodal Large Language Model-based ReID. Firstly, we proposed Common Instruction, a simple approach that leverages the essence ability of LLMs to continue writing, avoiding complex and diverse instruction design. Secondly, we propose a multi-task learning-based synchronization module to ensure that the visual encoder of the MLLM is trained synchronously with the ReID task. The experimental results demonstrate the superiority of our method.

cs.CV↗

arXiv2024

EffLoc: Lightweight Vision Transformer for Efficient 6-DOF Camera Relocalization

Camera relocalization is pivotal in computer vision, with applications in AR, drones, robotics, and autonomous driving. It estimates 3D camera position and orientation (6-DoF) from images. Unlike traditional methods like SLAM, recent strides use deep learning for direct end-to-end pose estimation. We propose EffLoc, a novel efficient Vision Transformer for single-image camera relocalization. EffLoc's hierarchical layout, memory-bound self-attention, and feed-forward layers boost memory efficiency and inter-channel communication. Our introduced sequential group attention (SGA) module enhances computational efficiency by diversifying input features, reducing redundancy, and expanding model capacity. EffLoc excels in efficiency and accuracy, outperforming prior methods, such as AtLoc and MapNet. It thrives on large-scale outdoor car-driving scenario, ensuring simplicity, end-to-end trainability, and eliminating handcrafted loss functions.

cs.CV↗

arXiv2024

Ultrafast lattice disordering can be accelerated by electronic collisional forces

In the prevalent picture of ultrafast structural phase transitions, the atomic motion occurs in a slowly varying potential energy surface determined adiabatically by the fast electrons. However, this ignores non-conservative forces caused by electron-lattice collisions, which can significantly influence atomic motion. Most ultrafast techniques only probe the average structure and are less sensitive to random displacements, and therefore do not detect the role played by non-conservative forces in phase transitions. Here we show that the lattice dynamics of the prototypical insulator-to-metal transition of VO2 cannot be described by a potential energy alone. We use the sample temperature to control the preexisting lattice disorder before ultrafast photoexcitation across the phase transition and our ultrafast diffuse scattering experiments show that the fluctuations characteristic of the rutile metal develop equally fast (120 fs) at initial temperatures of 100 K and 300 K. This indicates that additional non-conservative forces are responsible for the increased lattice disorder. These results highlight the need for more sophisticated descriptions of ultrafast phenomena beyond the Born-Oppenheimer approximation as well as ultrafast probes of spatial fluctuations beyond the average unit cell measured by diffraction.

cond-mat.str-el↗

arXiv2023

A High Fidelity and Low Complexity Neural Audio Coding

Audio coding is an essential module in the real-time communication system. Neural audio codecs can compress audio samples with a low bitrate due to the strong modeling and generative capabilities of deep neural networks. To address the poor high-frequency expression and high computational cost and storage consumption, we proposed an integrated framework that utilizes a neural network to model wide-band components and adopts traditional signal processing to compress high-band components according to psychological hearing knowledge. Inspired by auditory perception theory, a perception-based loss function is designed to improve harmonic modeling. Besides, generative adversarial network (GAN) compression is proposed for the first time for neural audio codecs. Our method is superior to prior advanced neural codecs across subjective and objective metrics and allows real-time inference on desktop and mobile.

cs.SD↗

arXiv2023

MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation

Pre-training has been an important ingredient in developing strong monocular depth estimation models in recent years. For instance, self-supervised learning (SSL) is particularly effective by alleviating the need for large datasets with dense ground-truth depth maps. However, despite these improvements, our study reveals that the later layers of the SOTA SSL method are actually suboptimal. By examining the layer-wise representations, we demonstrate significant changes in these later layers during fine-tuning, indicating the ineffectiveness of their pre-trained features for depth estimation. To address these limitations, we propose MeSa, a comprehensive framework that leverages the complementary strengths of masked, geometric, and supervised pre-training. Hence, MeSa benefits from not only general-purpose representations learnt via masked pre training but also specialized depth-specific features acquired via geometric and supervised pre-training. Our CKA layer-wise analysis confirms that our pre-training strategy indeed produces improved representations for the later layers, overcoming the drawbacks of the SOTA SSL method. Furthermore, via experiments on the NYUv2 and IBims-1 datasets, we demonstrate that these enhanced representations translate to performance improvements in both the in-distribution and out-of-distribution settings. We also investigate the influence of the pre-training dataset and demonstrate the efficacy of pre-training on LSUN, which yields significantly better pre-trained representations. Overall, our approach surpasses the masked pre-training SSL method by a substantial margin of 17.1% on the RMSE. Moreover, even without utilizing any recently proposed techniques, MeSa also outperforms the most recent methods and establishes a new state-of-the-art for monocular depth estimation on the challenging NYUv2 dataset.

cs.CV↗

arXiv2023

ICAR: Image-based Complementary Auto Reasoning

Scene-aware Complementary Item Retrieval (CIR) is a challenging task which requires to generate a set of compatible items across domains. Due to the subjectivity, it is difficult to set up a rigorous standard for both data collection and learning objectives. To address this challenging task, we propose a visual compatibility concept, composed of similarity (resembling in color, geometry, texture, and etc.) and complementarity (different items like table vs chair completing a group). Based on this notion, we propose a compatibility learning framework, a category-aware Flexible Bidirectional Transformer (FBT), for visual "scene-based set compatibility reasoning" with the cross-domain visual similarity input and auto-regressive complementary item generation. We introduce a "Flexible Bidirectional Transformer (FBT)" consisting of an encoder with flexible masking, a category prediction arm, and an auto-regressive visual embedding prediction arm. And the inputs for FBT are cross-domain visual similarity invariant embeddings, making this framework quite generalizable. Furthermore, our proposed FBT model learns the inter-object compatibility from a large set of scene images in a self-supervised way. Compared with the SOTA methods, this approach achieves up to 5.3% and 9.6% in FITB score and 22.3% and 31.8% SFID improvement on fashion and furniture, respectively.

cs.CV↗

arXiv2023

TotalSegmentator: robust segmentation of 104 anatomical structures in CT images

We present a deep learning segmentation model that can automatically and robustly segment all major anatomical structures in body CT images. In this retrospective study, 1204 CT examinations (from the years 2012, 2016, and 2020) were used to segment 104 anatomical structures (27 organs, 59 bones, 10 muscles, 8 vessels) relevant for use cases such as organ volumetry, disease characterization, and surgical or radiotherapy planning. The CT images were randomly sampled from routine clinical studies and thus represent a real-world dataset (different ages, pathologies, scanners, body parts, sequences, and sites). The authors trained an nnU-Net segmentation algorithm on this dataset and calculated Dice similarity coefficients (Dice) to evaluate the model's performance. The trained algorithm was applied to a second dataset of 4004 whole-body CT examinations to investigate age dependent volume and attenuation changes. The proposed model showed a high Dice score (0.943) on the test set, which included a wide range of clinical data with major pathologies. The model significantly outperformed another publicly available segmentation model on a separate dataset (Dice score, 0.932 versus 0.871, respectively). The aging study demonstrated significant correlations between age and volume and mean attenuation for a variety of organ groups (e.g., age and aortic volume; age and mean attenuation of the autochthonous dorsal musculature). The developed model enables robust and accurate segmentation of 104 anatomical structures. The annotated dataset (https://doi.org/10.5281/zenodo.6802613) and toolkit (https://www.github.com/wasserth/TotalSegmentator) are publicly available.

eess.IV↗

arXiv2023

RoSI: Recovering 3D Shape Interiors from Few Articulation Images

The dominant majority of 3D models that appear in gaming, VR/AR, and those we use to train geometric deep learning algorithms are incomplete, since they are modeled as surface meshes and missing their interior structures. We present a learning framework to recover the shape interiors (RoSI) of existing 3D models with only their exteriors from multi-view and multi-articulation images. Given a set of RGB images that capture a target 3D object in different articulated poses, possibly from only few views, our method infers the interior planes that are observable in the input images. Our neural architecture is trained in a category-agnostic manner and it consists of a motion-aware multi-view analysis phase including pose, depth, and motion estimations, followed by interior plane detection in images and 3D space, and finally multi-view plane fusion. In addition, our method also predicts part articulations and is able to realize and even extrapolate the captured motions on the target 3D object. We evaluate our method by quantitative and qualitative comparisons to baselines and alternative solutions, as well as testing on untrained object categories and real image inputs to assess its generalization capabilities.

cs.CV↗

arXiv2023

Local-to-Global Panorama Inpainting for Locale-Aware Indoor Lighting Prediction

Predicting panoramic indoor lighting from a single perspective image is a fundamental but highly ill-posed problem in computer vision and graphics. To achieve locale-aware and robust prediction, this problem can be decomposed into three sub-tasks: depth-based image warping, panorama inpainting and high-dynamic-range (HDR) reconstruction, among which the success of panorama inpainting plays a key role. Recent methods mostly rely on convolutional neural networks (CNNs) to fill the missing contents in the warped panorama. However, they usually achieve suboptimal performance since the missing contents occupy a very large portion in the panoramic space while CNNs are plagued by limited receptive fields. The spatially-varying distortion in the spherical signals further increases the difficulty for conventional CNNs. To address these issues, we propose a local-to-global strategy for large-scale panorama inpainting. In our method, a depth-guided local inpainting is first applied on the warped panorama to fill small but dense holes. Then, a transformer-based network, dubbed PanoTransformer, is designed to hallucinate reasonable global structures in the large holes. To avoid distortion, we further employ cubemap projection in our design of PanoTransformer. The high-quality panorama recovered at any locale helps us to capture spatially-varying indoor illumination with physically-plausible global structures and fine details.

cs.CV↗

arXiv2023

Aligning Multi-Sequence CMR Towards Fully Automated Myocardial Pathology Segmentation

Myocardial pathology segmentation (MyoPS) is critical for the risk stratification and treatment planning of myocardial infarction (MI). Multi-sequence cardiac magnetic resonance (MS-CMR) images can provide valuable information. For instance, balanced steady-state free precession cine sequences present clear anatomical boundaries, while late gadolinium enhancement and T2-weighted CMR sequences visualize myocardial scar and edema of MI, respectively. Existing methods usually fuse anatomical and pathological information from different CMR sequences for MyoPS, but assume that these images have been spatially aligned. However, MS-CMR images are usually unaligned due to the respiratory motions in clinical practices, which poses additional challenges for MyoPS. This work presents an automatic MyoPS framework for unaligned MS-CMR images. Specifically, we design a combined computing model for simultaneous image registration and information fusion, which aggregates multi-sequence features into a common space to extract anatomical structures (i.e., myocardium). Consequently, we can highlight the informative regions in the common space via the extracted myocardium to improve MyoPS performance, considering the spatial relationship between myocardial pathologies and myocardium. Experiments on a private MS-CMR dataset and a public dataset from the MYOPS2020 challenge show that our framework could achieve promising performance for fully automatic MyoPS.

eess.IV↗

arXiv2023

Determination of nonthermal bonding origin of a novel photoexcited lattice instability in SnSe

Interatomic forces that bind materials are largely determined by an often complex interplay between the electronic band-structure and the atomic arrangements to form its equilibrium structure and dynamics. As these forces also determine the phonon dispersion, lattice dynamics measurements are often crucial tools for understanding how materials transform between different structures. This is the case for the mono-chalcogenides which feature a number of lattice instabilities associated with their network of resonant bonds and a large tunability in their functional properties. SnSe hosts a novel lattice instability upon above-bandgap photoexcitation that is distinct from the distortions associated with its high temperature phase transition, demonstrating that photoexcitation can alter the interatomic forces significantly different than thermal excitation. Here we report decisive time-resolved X-ray scattering-based measurements of the nonequlibrium lattice dynamics in SnSe. By fitting interatomic force models to the excited-state dispersion, we determine this instability as being primarily due to changes in the fourth-nearest neighbor bonds that connect bilayers, with relatively little change to the intralayer resonant bonds. In addition to providing critical insight into the nonthermal bonding origin of the instability in SnSe, such measurements will be crucial for understanding and controlling materials properties under non-equilibrium conditions.

cond-mat.mtrl-sci↗

arXiv2022

UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis

Text-to-speech (TTS) and singing voice synthesis (SVS) aim at generating high-quality speaking and singing voice according to textual input and music scores, respectively. Unifying TTS and SVS into a single system is crucial to the applications requiring both of them. Existing methods usually suffer from some limitations, which rely on either both singing and speaking data from the same person or cascaded models of multiple tasks. To address these problems, a simplified elegant framework for TTS and SVS, named UniSyn, is proposed in this paper. It is an end-to-end unified model that can make a voice speak and sing with only singing or speaking data from this person. To be specific, a multi-conditional variational autoencoder (MC-VAE), which constructs two independent latent sub-spaces with the speaker- and style-related (i.e. speak or sing) conditions for flexible control, is proposed in UniSyn. Moreover, supervised guided-VAE and timbre perturbation with the Wasserstein distance constraint are leveraged to further disentangle the speaker timbre and style. Experiments conducted on two speakers and two singers demonstrate that UniSyn can generate natural speaking and singing voice without corresponding training data. The proposed approach outperforms the state-of-the-art end-to-end voice generation work, which proves the effectiveness and advantages of UniSyn.

cs.SD↗

arXiv2022

Attention Bottlenecks for Multimodal Fusion

Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-attention, our model forces information between different modalities to pass through a small number of bottleneck latents, requiring the model to collate and condense the most relevant information in each modality and only share what is necessary. We find that such a strategy improves fusion performance, at the same time reducing computational cost. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks including Audioset, Epic-Kitchens and VGGSound. All code and models will be released.

cs.CV↗

arXiv2022

MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images

Myocardial pathology segmentation (MyoPS) can be a prerequisite for the accurate diagnosis and treatment planning of myocardial infarction. However, achieving this segmentation is challenging, mainly due to the inadequate and indistinct information from an image. In this work, we develop an end-to-end deep neural network, referred to as MyoPS-Net, to flexibly combine five-sequence cardiac magnetic resonance (CMR) images for MyoPS. To extract precise and adequate information, we design an effective yet flexible architecture to extract and fuse cross-modal features. This architecture can tackle different numbers of CMR images and complex combinations of modalities, with output branches targeting specific pathologies. To impose anatomical knowledge on the segmentation results, we first propose a module to regularize myocardium consistency and localize the pathologies, and then introduce an inclusiveness loss to utilize relations between myocardial scars and edema. We evaluated the proposed MyoPS-Net on two datasets, i.e., a private one consisting of 50 paired multi-sequence CMR images and a public one from MICCAI2020 MyoPS Challenge. Experimental results showed that MyoPS-Net could achieve state-of-the-art performance in various scenarios. Note that in practical clinics, the subjects may not have full sequences, such as missing LGE CMR or mapping CMR scans. We therefore conducted extensive experiments to investigate the performance of the proposed method in dealing with such complex combinations of different CMR sequences. Results proved the superiority and generalizability of MyoPS-Net, and more importantly, indicated a practical clinical application.

eess.IV↗

arXiv2022

Glow-WaveGAN 2: High-quality Zero-shot Text-to-speech Synthesis and Any-to-any Voice Conversion

The zero-shot scenario for speech generation aims at synthesizing a novel unseen voice with only one utterance of the target speaker. Although the challenges of adapting new voices in zero-shot scenario exist in both stages -- acoustic modeling and vocoder, previous works usually consider the problem from only one stage. In this paper, we extend our previous Glow-WaveGAN to Glow-WaveGAN 2, aiming to solve the problem from both stages for high-quality zero-shot text-to-speech and any-to-any voice conversion. We first build a universal WaveGAN model for extracting latent distribution $p(z)$ of speech and reconstructing waveform from it. Then a flow-based acoustic model only needs to learn the same $p(z)$ from texts, which naturally avoids the mismatch between the acoustic model and the vocoder, resulting in high-quality generated speech without model fine-tuning. Based on a continuous speaker space and the reversible property of flows, the conditional distribution can be obtained for any speaker, and thus we can further conduct high-quality zero-shot speech generation for new speakers. We particularly investigate two methods to construct the speaker space, namely pre-trained speaker encoder and jointly-trained speaker encoder. The superiority of Glow-WaveGAN 2 has been proved through TTS and VC experiments conducted on LibriTTS corpus and VTCK corpus.

cs.SD↗

arXiv2022

Learning Noise-independent Speech Representation for High-quality Voice Conversion for Noisy Target Speakers

Building a voice conversion system for noisy target speakers, such as users providing noisy samples or Internet found data, is a challenging task since the use of contaminated speech in model training will apparently degrade the conversion performance. In this paper, we leverage the advances of our recently proposed Glow-WaveGAN and propose a noise-independent speech representation learning approach for high-quality voice conversion for noisy target speakers. Specifically, we learn a latent feature space where we ensure that the target distribution modeled by the conversion model is exactly from the modeled distribution of the waveform generator. With this premise, we further manage to make the latent feature to be noise-invariant. Specifically, we introduce a noise-controllable WaveGAN, which directly learns the noise-independent acoustic representation from waveform by the encoder and conducts noise control in the hidden space through a FiLM module in the decoder. As for the conversion model, importantly, we use a flow-based model to learn the distribution of noise-independent but speaker-related latent features from phoneme posteriorgrams. Experimental results demonstrate that the proposed model achieves high speech quality and speaker similarity in the voice conversion for noisy target speakers.

cs.SD↗

arXiv2022

End-to-End Voice Conversion with Information Perturbation

The ideal goal of voice conversion is to convert the source speaker's speech to sound naturally like the target speaker while maintaining the linguistic content and the prosody of the source speech. However, current approaches are insufficient to achieve comprehensive source prosody transfer and target speaker timbre preservation in the converted speech, and the quality of the converted speech is also unsatisfied due to the mismatch between the acoustic model and the vocoder. In this paper, we leverage the recent advances in information perturbation and propose a fully end-to-end approach to conduct high-quality voice conversion. We first adopt information perturbation to remove speaker-related information in the source speech to disentangle speaker timbre and linguistic content and thus the linguistic information is subsequently modeled by a content encoder. To better transfer the prosody of the source speech to the target, we particularly introduce a speaker-related pitch encoder which can maintain the general pitch pattern of the source speaker while flexibly modifying the pitch intensity of the generated speech. Finally, one-shot voice conversion is set up through continuous speaker space modeling. Experimental results indicate that the proposed end-to-end approach significantly outperforms the state-of-the-art models in terms of intelligibility, naturalness, and speaker similarity.

eess.AS↗