arXiv subjects

Yi Lu

Publications and source records attributed to Yi Lu.

At least 127 records · Page 7Linked to original sources

arXiv2024

DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech

In recent years, speech diffusion models have advanced rapidly. Alongside the widely used U-Net architecture, transformer-based models such as the Diffusion Transformer (DiT) have also gained attention. However, current DiT speech models treat Mel spectrograms as general images, which overlooks the specific acoustic properties of speech. To address these limitations, we propose a method called Directional Patch Interaction for Text-to-Speech (DPI-TTS), which builds on DiT and achieves fast training without compromising accuracy. Notably, DPI-TTS employs a low-to-high frequency, frame-by-frame progressive inference approach that aligns more closely with acoustic properties, enhancing the naturalness of the generated speech. Additionally, we introduce a fine-grained style temporal modeling method that further improves speaker style similarity. Experimental results demonstrate that our method increases the training speed by nearly 2 times and significantly outperforms the baseline models.

cs.SD↗

arXiv2024

Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0

Speech synthesis technology has posed a serious threat to speaker verification systems. Currently, the most effective fake audio detection methods utilize pretrained models, and integrating features from various layers of pretrained model further enhances detection performance. However, most of the previously proposed fusion methods require fine-tuning the pretrained models, resulting in excessively long training times and hindering model iteration when facing new speech synthesis technology. To address this issue, this paper proposes a feature fusion method based on the Mixture of Experts, which extracts and integrates features relevant to fake audio detection from layer features, guided by a gating network based on the last layer feature, while freezing the pretrained model. Experiments conducted on the ASVspoof2019 and ASVspoof2021 datasets demonstrate that the proposed method achieves competitive performance compared to those requiring fine-tuning.

cs.SD↗

arXiv2024

Grafted AlGaAs/GeSn Optical Pumping Laser Operating up to 130 K

Group IV GeSn double-heterostructure (DHS) lasers offer unique advantages of a direct bandgap and CMOS compatibility. However, further improvements in laser performance have been bottlenecked by limited junction properties of GeSn through conventional epitaxy and wafer bonding. This work leverages semiconductor grafting to synthesize and characterize optically pumped ridge edge-emitting lasers (EELs) with an AlGaAs nanomembrane (NM) transfer-printed onto an epitaxially grown GeSn substrate, interfaced by an ultrathin Al2O3 layer. The grafted AlGaAs/GeSn DHS lasers show a lasing threshold of 11.06 mW at 77 K and a maximum lasing temperature of 130 K. These results highlight the potential of the grafting technique for enhancing charge carrier and optical field confinements, paving the way for room-temperature electrically injected GeSn lasers.

physics.optics↗

arXiv2024

Charge and spin instabilities in superconducting La$_3$Ni$_2$O$_7$

Motivated by the recent discovery of superconductivity in La$_3$Ni$_2$O$_7$ under high pressure, we explore its potential charge and spin instabilities through combined model analysis and first-principles calculations. Taking into account the small charge-transfer nature of high valence nickel, a fully correlated two-cluster model identifies a lattice-coupled charge instability characterized by substantial short-range fluctuations of oxygen holes. This instability is corroborated by density-functional-theory plus $U$ calculations that also reveal a strong tendency towards concurrent antiferromagnetic ordering. The charge, spin, and associated lattice instabilities are significantly suppressed with increasing external pressure, contributing to the emergence of superconductivity in pressurized La$_3$Ni$_2$O$_7$. Carrier doping is found to effectively suppress these instabilities, suggesting a viable strategy to stabilize a superconducting phase under ambient pressure.

cond-mat.supr-con↗

arXiv2024

Smart Multi-Modal Search: Contextual Sparse and Dense Embedding Integration in Adobe Express

As user content and queries become increasingly multi-modal, the need for effective multi-modal search systems has grown. Traditional search systems often rely on textual and metadata annotations for indexed images, while multi-modal embeddings like CLIP enable direct search using text and image embeddings. However, embedding-based approaches face challenges in integrating contextual features such as user locale and recency. Building a scalable multi-modal search system requires fine-tuning several components. This paper presents a multi-modal search architecture and a series of AB tests that optimize embeddings and multi-modal technologies in Adobe Express template search. We address considerations such as embedding model selection, the roles of embeddings in matching and ranking, and the balance between dense and sparse embeddings. Our iterative approach demonstrates how utilizing sparse, dense, and contextual features enhances short and long query search, significantly reduces null rates (over 70\%), and increases click-through rates (CTR). Our findings provide insights into developing robust multi-modal search systems, thereby enhancing relevance for complex queries.

cs.IR↗

arXiv2024

Characterization of AlGaAs/GeSn heterojunction band alignment via X-ray photoelectron spectroscopy

GeSn-based SWIR lasers featuring imaging, sensing, and communications has gained dynamic development recently. However, the existing SiGeSn/GeSn double heterostructure lacks adequate electron confinement and is insufficient for room temperature lasing. The recently demonstrated semiconductor grafting technique provides a viable approach towards AlGaAs/GeSn p-i-n heterojunctions with better electron confinement and high-quality interfaces, promising for room temperature electrically pumped GeSn laser devices. Therefore, understanding and quantitatively characterizing the band alignment in this grafted heterojunction is crucial. In this study, we explore the band alignment in the grafted monocrystalline Al0.3Ga0.7As /Ge0.853Sn0.147 p-i-n heterojunction. We determined the bandgap values of AlGaAs and GeSn to be 1.81 eV and 0.434 eV by photoluminescence measurements, respectively. We further conducted X-ray photoelectron spectroscopy measurements and extracted a valence band offset of 0.19 eV and a conduction band offset of 1.186 eV. A Type-I band alignment was confirmed which effectively confining electrons at the AlGaAs/GeSn interface. This study improves our understanding of the interfacial band structure in grafted AlGaAs/GeSn heterostructure, providing experimental evidence of the Type-I band alignment between AlGaAs and GeSn, and paving the way for their application in laser technologies.

physics.app-ph↗

arXiv2024

Vision Transformer Neural Quantum States for Impurity Models

Transformer neural networks, known for their ability to recognize complex patterns in high-dimensional data, offer a promising framework for capturing many-body correlations in quantum systems. We employ an adapted Vision Transformer (ViT) architecture to model quantum impurity models, optimizing it with a subspace expansion scheme that surpasses conventional variational Monte Carlo in both accuracy and efficiency. Benchmarks against matrix product states in single- and three-orbital Anderson impurity models show that these ViT-based neural quantum states achieve comparable or superior accuracy with significantly fewer variational parameters. We further extend our approach to compute dynamical quantities by constructing a restricted excitation space that effectively captures relevant physical processes, yielding accurate core-level X-ray absorption spectra. These findings highlight the potential of ViT-based neural quantum states for accurate and efficient modeling of quantum impurity models.

cond-mat.str-el↗

arXiv2024

A Noval Feature via Color Quantisation for Fake Audio Detection

In the field of deepfake detection, previous studies focus on using reconstruction or mask and prediction methods to train pre-trained models, which are then transferred to fake audio detection training where the encoder is used to extract features, such as wav2vec2.0 and Masked Auto Encoder. These methods have proven that using real audio for reconstruction pre-training can better help the model distinguish fake audio. However, the disadvantage lies in poor interpretability, meaning it is hard to intuitively present the differences between deepfake and real audio. This paper proposes a noval feature extraction method via color quantisation which constrains the reconstruction to use a limited number of colors for the spectral image-like input. The proposed method ensures reconstructed input differs from the original, which allows for intuitive observation of the focus areas in the spectral reconstruction. Experiments conducted on the ASVspoof2019 dataset demonstrate that the proposed method achieves better classification performance compared to using the original spectral as input and pretraining the recolor network can also benefit the fake audio detection.

cs.SD↗

arXiv2024

EELE: Exploring Efficient and Extensible LoRA Integration in Emotional Text-to-Speech

In the current era of Artificial Intelligence Generated Content (AIGC), a Low-Rank Adaptation (LoRA) method has emerged. It uses a plugin-based approach to learn new knowledge with lower parameter quantities and computational costs, and it can be plugged in and out based on the specific sub-tasks, offering high flexibility. However, the current application schemes primarily incorporate LoRA into the pre-introduced conditional parts of the speech models. This fixes the position of LoRA, limiting the flexibility and scalability of its application. Therefore, we propose the Exploring Efficient and Extensible LoRA Integration in Emotional Text-to-Speech (EELE) method. Starting from a general neutral speech model, we do not pre-introduce emotional information but instead use the LoRA plugin to design a flexible adaptive scheme that endows the model with emotional generation capabilities. Specifically, we initially train the model using only neutral speech data. After training is complete, we insert LoRA into different modules and fine-tune the model with emotional speech data to find the optimal insertion scheme. Through experiments, we compare and test the effects of inserting LoRA at different positions within the model and assess LoRA's ability to learn various emotions, effectively proving the validity of our method. Additionally, we explore the impact of the rank size of LoRA and the difference compared to directly fine-tuning the entire model.

cs.SD↗

arXiv2024

Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?

Currently, Audio Language Models (ALMs) are rapidly advancing due to the developments in large language models and audio neural codecs. These ALMs have significantly lowered the barrier to creating deepfake audio, generating highly realistic and diverse types of deepfake audio, which pose severe threats to society. Consequently, effective audio deepfake detection technologies to detect ALM-based audio have become increasingly critical. This paper investigate the effectiveness of current countermeasure (CM) against ALM-based audio. Specifically, we collect 12 types of the latest ALM-based deepfake audio and utilizing the latest CMs to evaluate. Our findings reveal that the latest codec-trained CM can effectively detect ALM-based audio, achieving 0% equal error rate under most ALM test conditions, which exceeded our expectations. This indicates promising directions for future research in ALM-based deepfake audio detection.

cs.SD↗

arXiv2024

Lee-Yang edge singularities in QCD via the Dyson-Schwinger Equations

We take the Dyson-Schwinger Equation approach of QCD for the quark propagator at complex chemical potential to study the QCD phase transition. The phase transition line of the $(2+1)$-flavor QCD matter in the imaginary chemical potential region is computed via a simplified truncation scheme, whose curvature is found to be consistent with the one at real chemical potential. Moreover, the computation in the complex chemical potential plane allows us to determine the location of the Lee-Yang edge singularities. We show explicitly that the critical end point coincides with the Lee-Yang edge singularities on the real $μ_{B}^{}$ axis. We also investigate the scaling behavior of the singularities and discuss the possibility of extrapolating the CEP from a certain range of chemical potential.

hep-ph↗

arXiv2024

AlGaAs/GeSn p-i-n diode interfaced with ultrathin Al$_2$O$_3$

This study presents the fabrication and characterizations of an Al$_{0.3}$Ga$_{0.7}$As/Ge$_{0.87}$Sn$_{0.13}$/GeSn p-i-n double heterostructure (DHS) diode following the grafting approach for enhanced optoelectronic applications. By integrating ultra-thin Al$_2$O$_3$ as a quantum tunneling layer and enhancing interfacial double-side passivation, we achieved a heterostructure with a substantial 1.186 eV conduction band barrier between AlGaAs and GeSn, along with a low interfacial density of states. The diode demonstrated impressive electrical characteristics with high uniformity, including a mean ideality factor of 1.47 and a mean rectification ratio of 2.95E103 at +/-2 V across 326 devices, indicating high-quality device fabrication. Comprehensive electrical characterizations, including C-V and I-V profiling, affirm the diode's capability to provide robust electrical confinement and efficient carrier injection. These properties make the Al$_{0.3}$Ga$_{0.7}$As/Ge$_{0.87}$Sn$_{0.13}$/GeSn DHS a promising candidate for next-generation electrically pumped GeSn lasers, potentially operable at higher temperatures. Our results provide a viable pathway for further advancements in various GeSn-based devices.

physics.app-ph↗

arXiv2024

ICAGC 2024: Inspirational and Convincing Audio Generation Challenge 2024

The Inspirational and Convincing Audio Generation Challenge 2024 (ICAGC 2024) is part of the ISCSLP 2024 Competitions and Challenges track. While current text-to-speech (TTS) technology can generate high-quality audio, its ability to convey complex emotions and controlled detail content remains limited. This constraint leads to a discrepancy between the generated audio and human subjective perception in practical applications like companion robots for children and marketing bots. The core issue lies in the inconsistency between high-quality audio generation and the ultimate human subjective experience. Therefore, this challenge aims to enhance the persuasiveness and acceptability of synthesized audio, focusing on human alignment convincing and inspirational audio generation. A total of 19 teams have registered for the challenge, and the results of the competition and the competition are described in this paper.

eess.AS↗

arXiv2024

Establishing HI mass v.s. stellar mass and halo mass scaling relations using an abundance matching method

We combined data from the Sloan Digital Sky Survey (SDSS) and the Arecibo Legacy Fast ALFA Survey (ALFALFA) to establish the HI mass vs. stellar mass and halo mass scaling relations using an abundance matching method that is free of the Malmquist bias. To enable abundance matching, a cross-match between the SDSS DR7 galaxy group sample and the ALFALFA HI sources provides a catalog of 16,520 HI-galaxy pairs within 14,270 galaxy groups (halos). By applying the observational completeness reductions for both optical and HI observations, we used the remaining 8,180 ALFALFA matched sources to construct the model constraints. Taking into account the dependence of HI mass on both the galaxy and group properties, we establish two sets of scaling relations: one with a combination of stellar mass, $({g-r})$ color and halo mass, and the other with stellar mass, specific star-formation rate ($\rm sSFR$), and halo mass. We demonstrate that our models can reproduce the HI mass component as both a stellar and halo mass. Additional tests showed that the conditional HI mass distributions as a function of the cosmic web type and the satellite fractions were well recovered.

astro-ph.GA↗

arXiv2024

ASRRL-TTS: Agile Speaker Representation Reinforcement Learning for Text-to-Speech Speaker Adaptation

Speaker adaptation, which involves cloning voices from unseen speakers in the Text-to-Speech task, has garnered significant interest due to its numerous applications in multi-media fields. Despite recent advancements, existing methods often struggle with inadequate speaker representation accuracy and overfitting, particularly in limited reference speeches scenarios. To address these challenges, we propose an Agile Speaker Representation Reinforcement Learning strategy to enhance speaker similarity in speaker adaptation tasks. ASRRL is the first work to apply reinforcement learning to improve the modeling accuracy of speaker embeddings in speaker adaptation, addressing the challenge of decoupling voice content and timbre. Our approach introduces two action strategies tailored to different reference speeches scenarios. In the single-sentence scenario, a knowledge-oriented optimal routine searching RL method is employed to expedite the exploration and retrieval of refinement information on the fringe of speaker representations. In the few-sentence scenario, we utilize a dynamic RL method to adaptively fuse reference speeches, enhancing the robustness and accuracy of speaker modeling. To achieve optimal results in the target domain, a multi-scale fusion scoring mechanism based reward model that evaluates speaker similarity, speech quality, and intelligibility across three dimensions is proposed, ensuring that improvements in speaker similarity do not compromise speech quality or intelligibility. The experimental results on the LibriTTS and VCTK datasets within mainstream TTS frameworks demonstrate the extensibility and generalization capabilities of the proposed ASRRL method. The results indicate that the ASRRL method significantly outperforms traditional fine-tuning approaches, achieving higher speaker similarity and better overall speech quality with limited reference speeches.

eess.AS↗

arXiv2024

Structural and Electrical Properties of Grafted Si/GaAsSb Heterojunction

The short-wave infrared (SWIR) wavelength, especially 1.55 um, has attracted significant attention in various areas such as high-speed optical communication and LiDAR systems. Avalanche photodiodes (APDs) are a critical component as a receiver in these systems due to their internal gain which enhances the system performance. Silicon-based APDs are promising since they are CMOS compatible, but they are limited in detecting 1.55 um light detection. This study proposes a p-type Si on n-type GaAs0.51Sb0.49 (GaAsSb) lattice matched to InP substrates heterojunction formed using a grafting technique for future GaAsSb/Si APD technology. A p+Si nanomembrane is transferred onto the GaAsSb/AlInAs/InP substrate, with an ultrathin ALD-Al2O3 oxide at the interface, which behaves as both double-side passivation and quantum tunneling layers. The devices exhibit excellent surface morphology and interface quality, confirmed by atomic force microscope (AFM) and transmission electron microscope (TEM). Also, the current-voltage (I-V) of the p+Si/n-GaAsSb heterojunction shows ideal rectifying characteristics with an ideality factor of 1.15. The I-V tests across multiple devices confirm high consistency and yield. Furthermore, the X-ray photoelectron spectroscopy (XPS) measurement reveals that GaAsSb and Si are found to have type-II band alignment with a conduction band offset of 50 meV which is favorable for the high-bandwidth APD application. The demonstration of the GaAsSb/Si heterojunction highlights the potential to advance current SWIR PD technologies.

physics.app-ph↗

arXiv2024

Zero-Shot Long-Form Video Understanding through Screenplay

The Long-form Video Question-Answering task requires the comprehension and analysis of extended video content to respond accurately to questions by utilizing both temporal and contextual information. In this paper, we present MM-Screenplayer, an advanced video understanding system with multi-modal perception capabilities that can convert any video into textual screenplay representations. Unlike previous storytelling methods, we organize video content into scenes as the basic unit, rather than just visually continuous shots. Additionally, we developed a ``Look Back'' strategy to reassess and validate uncertain information, particularly targeting breakpoint mode. MM-Screenplayer achieved highest score in the CVPR'2024 LOng-form VidEo Understanding (LOVEU) Track 1 Challenge, with a global accuracy of 87.5% and a breakpoint accuracy of 68.8%.

cs.CV↗

arXiv2024

A multi-speaker multi-lingual voice cloning system based on vits2 for limmits 2024 challenge

This paper presents the development of a speech synthesis system for the LIMMITS'24 Challenge, focusing primarily on Track 2. The objective of the challenge is to establish a multi-speaker, multi-lingual Indic Text-to-Speech system with voice cloning capabilities, covering seven Indian languages with both male and female speakers. The system was trained using challenge data and fine-tuned for few-shot voice cloning on target speakers. Evaluation included both mono-lingual and cross-lingual synthesis across all seven languages, with subjective tests assessing naturalness and speaker similarity. Our system uses the VITS2 architecture, augmented with a multi-lingual ID and a BERT model to enhance contextual language comprehension. In Track 1, where no additional data usage was permitted, our model achieved a Speaker Similarity score of 4.02. In Track 2, which allowed the use of extra data, it attained a Speaker Similarity score of 4.17.

cs.SD↗