arXiv subjects

Kun Xie

Publications and source records attributed to Kun Xie.

35 records · Page 2Linked to original sources

arXiv2025

FireRedTTS-1S: An Upgraded Streamable Foundation Text-to-Speech System

In this work, we upgrade FireRedTTS to a new version, FireRedTTS-1S, a high-quality streaming foundation text-to-speech system. FireRedTTS-1S achieves streaming speech generation via two steps: text-to-semantic decoding and semantic-to-acoustic decoding. In text-to-semantic decoding, a semantic-aware speech tokenizer converts the speech signal into semantic tokens, which can be synthesized from the text via a language model in an auto-regressive manner. Meanwhile, the semantic-to-acoustic decoding module simultaneously translates generated semantic tokens into the speech signal in a streaming way. We implement two approaches to achieve this module: 1) a chunk-wise streamable flow-matching approach, and 2) a multi-stream language model-based approach. They both present high-quality and streamable speech generation but differ in real-time factor (RTF) and latency. Specifically, flow-matching decoding can generate speech by chunks, presenting a lower RTF of 0.1 but a higher latency of 300ms. Instead, the multi-stream language model generates speech by frames in an autoregressive manner, presenting a higher RTF of 0.3 but a low latency of 150ms. In experiments on zero-shot voice cloning, the objective results validate FireRedTTS-1S as a high-quality foundation model with comparable intelligibility and speaker similarity over industrial baseline systems. Furthermore, the subjective score of FireRedTTS-1S highlights its impressive synthesis performance, achieving comparable quality to the ground-truth recordings. These results validate FireRedTTS-1S as a high-quality streaming foundation TTS system.

cs.SD↗

arXiv2025

FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications

This work proposes FireRedTTS, a foundation text-to-speech framework, to meet the growing demands for personalized and diverse generative speech applications. The framework comprises three parts: data processing, foundation system, and downstream applications. First, we comprehensively present our data processing pipeline, which transforms massive raw audio into a large-scale high-quality TTS dataset with rich annotations and a wide coverage of content, speaking style, and timbre. Then, we propose a language-model-based foundation TTS system. The speech signal is compressed into discrete semantic tokens via a semantic-aware speech tokenizer, and can be generated by a language model from the prompt text and audio. Then, a two-stage waveform generator is proposed to decode them to the high-fidelity waveform. We present two applications of this system: voice cloning for dubbing and human-like speech generation for chatbots. The experimental results demonstrate the solid in-context learning capability of FireRedTTS, which can stably synthesize high-quality speech consistent with the prompt text and audio. For dubbing, FireRedTTS can clone target voices in a zero-shot way for the UGC scenario and adapt to studio-level expressive voice characters in the PUGC scenario via few-shot fine-tuning with 1-hour recording. Moreover, FireRedTTS achieves controllable human-like speech generation in a casual style with paralinguistic behaviors and emotions via instruction tuning, to better serve spoken chatbots.

cs.SD↗

arXiv2025

EVOKE: Elevating Chest X-ray Report Generation via Multi-View Contrastive Learning and Patient-Specific Knowledge

Radiology reports are crucial for planning treatment strategies and facilitating effective doctor-patient communication. However, the manual creation of these reports places a significant burden on radiologists. While automatic radiology report generation presents a promising solution, existing methods often rely on single-view radiographs, which constrain diagnostic accuracy. To address this challenge, we propose \textbf{EVOKE}, a novel chest X-ray report generation framework that incorporates multi-view contrastive learning and patient-specific knowledge. Specifically, we introduce a multi-view contrastive learning method that enhances visual representation by aligning multi-view radiographs with their corresponding report. After that, we present a knowledge-guided report generation module that integrates available patient-specific indications (e.g., symptom descriptions) to trigger the production of accurate and coherent radiology reports. To support research in multi-view report generation, we construct Multi-view CXR and Two-view CXR datasets using publicly available sources. Our proposed EVOKE surpasses recent state-of-the-art methods across multiple datasets, achieving a 2.9\% F\textsubscript{1} RadGraph improvement on MIMIC-CXR, a 7.3\% BLEU-1 improvement on MIMIC-ABN, a 3.1\% BLEU-4 improvement on Multi-view CXR, and an 8.2\% F\textsubscript{1,mic-14} CheXbert improvement on Two-view CXR.

cs.CV↗

arXiv2025

Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation

Automated radiology report generation offers an effective solution to alleviate radiologists' workload. However, most existing methods focus primarily on single or fixed-view images to model current disease conditions, which limits diagnostic accuracy and overlooks disease progression. Although some approaches utilize longitudinal data to track disease progression, they still rely on single images to analyze current visits. To address these issues, we propose enhanced contrastive learning with Multi-view Longitudinal data to facilitate chest X-ray Report Generation, named MLRG. Specifically, we introduce a multi-view longitudinal contrastive learning method that integrates spatial information from current multi-view images and temporal information from longitudinal data. This method also utilizes the inherent spatiotemporal information of radiology reports to supervise the pre-training of visual and textual representations. Subsequently, we present a tokenized absence encoding technique to flexibly handle missing patient-specific prior knowledge, allowing the model to produce more accurate radiology reports based on available prior knowledge. Extensive experiments on MIMIC-CXR, MIMIC-ABN, and Two-view CXR datasets demonstrate that our MLRG outperforms recent state-of-the-art methods, achieving a 2.3% BLEU-4 improvement on MIMIC-CXR, a 5.5% F1 score improvement on MIMIC-ABN, and a 2.7% F1 RadGraph improvement on Two-view CXR.

cs.CV↗

arXiv2025

Towards More Accurate Full-Atom Antibody Co-Design

Antibody co-design represents a critical frontier in drug development, where accurate prediction of both 1D sequence and 3D structure of complementarity-determining regions (CDRs) is essential for targeting specific epitopes. Despite recent advances in equivariant graph neural networks for antibody design, current approaches often fall short in capturing the intricate interactions that govern antibody-antigen recognition and binding specificity. In this work, we present Igformer, a novel end-to-end framework that addresses these limitations through innovative modeling of antibody-antigen binding interfaces. Our approach refines the inter-graph representation by integrating personalized propagation with global attention mechanisms, enabling comprehensive capture of the intricate interplay between local chemical interactions and global conformational dependencies that characterize effective antibody-antigen binding. Through extensive validation on epitope-binding CDR design and structure prediction tasks, Igformer demonstrates significant improvements over existing methods, suggesting that explicit modeling of multi-scale residue interactions can substantially advance computational antibody design for therapeutic applications.

q-bio.BM↗

arXiv2025

Fast and Accurate Antibody Sequence Design via Structure Retrieval

Recent advancements in protein design have leveraged diffusion models to generate structural scaffolds, followed by a process known as protein inverse folding, which involves sequence inference on these scaffolds. However, these methodologies face significant challenges when applied to hyper-variable structures such as antibody Complementarity-Determining Regions (CDRs), where sequence inference frequently results in non-functional sequences due to hallucinations. Distinguished from prevailing protein inverse folding approaches, this paper introduces Igseek, a novel structure-retrieval framework that infers CDR sequences by retrieving similar structures from a natural antibody database. Specifically, Igseek employs a simple yet effective multi-channel equivariant graph neural network to generate high-quality geometric representations of CDR backbone structures. Subsequently, it aligns sequences of structurally similar CDRs and utilizes structurally conserved sequence motifs to enhance inference accuracy. Our experiments demonstrate that Igseek not only proves to be highly efficient in structural retrieval but also outperforms state-of-the-art approaches in sequence recovery for both antibodies and T-Cell Receptors, offering a new retrieval-based perspective for therapeutic protein design.

q-bio.BM↗

arXiv2024

Drone Data Analytics for Measuring Traffic Metrics at Intersections in High-Density Areas

This study employed over 100 hours of high-altitude drone video data from eight intersections in Hohhot to generate a unique and extensive dataset encompassing high-density urban road intersections in China. This research has enhanced the YOLOUAV model to enable precise target recognition on unmanned aerial vehicle (UAV) datasets. An automated calibration algorithm is presented to create a functional dataset in high-density traffic flows, which saves human and material resources. This algorithm can capture up to 200 vehicles per frame while accurately tracking over 1 million road users, including cars, buses, and trucks. Moreover, the dataset has recorded over 50,000 complete lane changes. It is the largest publicly available road user trajectories in high-density urban intersections. Furthermore, this paper updates speed and acceleration algorithms based on UAV elevation and implements a UAV offset correction algorithm. A case study demonstrates the usefulness of the proposed methods, showing essential parameters to evaluate intersections and traffic conditions in traffic engineering. The model can track more than 200 vehicles of different types simultaneously in highly dense traffic on an urban intersection in Hohhot, generating heatmaps based on spatial-temporal traffic flow data and locating traffic conflicts by conducting lane change analysis and surrogate measures. With the diverse data and high accuracy of results, this study aims to advance research and development of UAVs in transportation significantly. The High-Density Intersection Dataset is available for download at https://github.com/Qpu523/High-density-Intersection-Dataset.

eess.IV↗

arXiv2024

Factual Serialization Enhancement: A Key Innovation for Chest X-ray Report Generation

A radiology report comprises presentation-style vocabulary, which ensures clarity and organization, and factual vocabulary, which provides accurate and objective descriptions based on observable findings. While manually writing these reports is time-consuming and labor-intensive, automatic report generation offers a promising alternative. A critical step in this process is to align radiographs with their corresponding reports. However, existing methods often rely on complete reports for alignment, overlooking the impact of presentation-style vocabulary. To address this issue, we propose FSE, a two-stage Factual Serialization Enhancement method. In Stage 1, we introduce factuality-guided contrastive learning for visual representation by maximizing the semantic correspondence between radiographs and corresponding factual descriptions. In Stage 2, we present evidence-driven report generation that enhances diagnostic accuracy by integrating insights from similar historical cases structured as factual serialization. Experiments on MIMIC-CXR and IU X-ray datasets across specific and general scenarios demonstrate that FSE outperforms state-of-the-art approaches in both natural language generation and clinical efficacy metrics. Ablation studies further emphasize the positive effects of factual serialization in Stage 1 and Stage 2. The code is available at https://github.com/mk-runner/FSE.

eess.IV↗

arXiv2024

SoCodec: A Semantic-Ordered Multi-Stream Speech Codec for Efficient Language Model Based Text-to-Speech Synthesis

The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to address this issue. It compresses speech into a shorter, multi-stream discrete semantic sequence with multiple tokens at each frame. Meanwhile, the ordered product quantization is proposed to constrain this sequence into an ordered representation. It can be applied with a multi-stream delayed LM to achieve better autoregressive generation along both time and stream axes in TTS. The experimental result strongly demonstrates the effectiveness of the proposed approach, achieving superior performance over baseline systems even if compressing the frameshift of speech from 20ms to 240ms (12x). The ablation studies further validate the importance of learning the proposed ordered multi-stream semantic representation in pursuing shorter speech sequences for efficient LM-based TTS.

cs.SD↗

arXiv2022

Modeling driver's evasive behavior during safety-critical lane changes:Two-dimensional time-to-collision and deep reinforcement learning

Lane changes are complex driving behaviors and frequently involve safety-critical situations. This study aims to develop a lane-change-related evasive behavior model, which can facilitate the development of safety-aware traffic simulations and predictive collision avoidance systems. Large-scale connected vehicle data from the Safety Pilot Model Deployment (SPMD) program were used for this study. A new surrogate safety measure, two-dimensional time-to-collision (2D-TTC), was proposed to identify the safety-critical situations during lane changes. The validity of 2D-TTC was confirmed by showing a high correlation between the detected conflict risks and the archived crashes. A deep deterministic policy gradient (DDPG) algorithm, which could learn the sequential decision-making process over continuous action spaces, was used to model the evasive behaviors in the identified safety-critical situations. The results showed the superiority of the proposed model in replicating both the longitudinal and lateral evasive behaviors.

cs.AI↗

arXiv2021

Federated Route Leak Detection in Inter-domain Routing with Privacy Guarantee

In the inter-domain network, a route leak occurs when a routing announcement is propagated outside of its intended scope, which is a violation of the agreed routing policy. The route leaks can disrupt the internet traffic and cause large outages. The accurately detection of route leaks requires the share of AS business relationship information of ASes. However, the business relationship information between ASes is confidential due to economic issues. Thus, ASes are usually unwilling to revealing this information to the other ASes, especially their competitors. Recent advancements in federated learning make it possible to share data while maintaining privacy. Motivated by this, in this paper we study the route leak problem by considering the privacy of business relationships between ASes, and propose a method for route leak detection with privacy guarantee by using blockchain-based federated learning framework, in which ASes can train a global detection model without revealing their business relationships directly. Moreover, the proposed method provides a self-validation scheme by labeling AS triples with local routing policies, which mitigates route leaks' lack of ground truth. We evaluate the proposed method under a variety of datasets including unbalanced and balanced datasets. The different deployment strategies of the proposed method under different topologies are also examined. The results show that the proposed method has a better performance in detecting route leaks than a single AS detection regardless of whether using balanced or unbalanced datasets. In the analysis of the deployment, the results show that ASes with more peers have more possible route leaks and can contribute more on the detection of route leaks with the proposed method.

cs.NI↗

arXiv2021

Learning Based Proximity Matrix Factorization for Node Embedding

Node embedding learns a low-dimensional representation for each node in the graph. Recent progress on node embedding shows that proximity matrix factorization methods gain superb performance and scale to large graphs with millions of nodes. Existing approaches first define a proximity matrix and then learn the embeddings that fit the proximity by matrix factorization. Most existing matrix factorization methods adopt the same proximity for different tasks, while it is observed that different tasks and datasets may require different proximity, limiting their representation power. Motivated by this, we propose {\em Lemane}, a framework with trainable proximity measures, which can be learned to best suit the datasets and tasks at hand automatically. Our method is end-to-end, which incorporates differentiable SVD in the pipeline so that the parameters can be trained via backpropagation. However, this learning process is still expensive on large graphs. To improve the scalability, we train proximity measures only on carefully subsampled graphs, and then apply standard proximity matrix factorization on the original graph using the learned proximity. Note that, computing the learned proximities for each pair is still expensive for large graphs, and existing techniques for computing proximities are not applicable to the learned proximities. Thus, we present generalized push techniques to make our solution scalable to large graphs with millions of nodes. Extensive experiments show that our proposed solution outperforms existing solutions on both link prediction and node classification tasks on almost all datasets.

cs.LG↗

arXiv2020

Efficient Offline Monitoring of Linear Temporal Logic with Bit Vectors

A bitmap is a data structure designed to compactly represent sets of integers; it provides very fast operations for querying and manipulating such sets, exploiting bit-level parallelism. In this paper, we describe a technique for the offline verification of arbitrary expressions of Linear Temporal Logic using bitmap manipulation. An event trace is first preprocessed and transformed into a set of bitmaps. The LTL expression is then evaluated through a recursive procedure manipulating these bitmaps. Experimental results show that, for complex LTL formulas containing almost 20 operators, event traces can be evaluated at a throughput of millions of events per second.

cs.LO↗

arXiv2020

Increasing Security Degree of Freedom in Multi-user and Multi-eve Systems

Secure communication in the Multi-user and Multi-eavesdropper (MUME) scenario is considered in this paper. It has be shown that secrecy can be improved when the transmitter simultaneously transmits information-bearing signal to the intended receivers and artificial noise to confuse the eavesdroppers. Several processing schemes have been proposed to limit the co-channel interference (CCI). In this paper, we propose the increasing security degree of freedom (ISDF) method, which takes idea from the dirty-paper coding (DPC) and ZF beam-forming. By means of known interference pre-cancelation at the transmitter, we design each precoder according to the previously designed precoding matrices, rather than other users' channels, which in return provides extra freedom for the design of precoders. Simulations demonstrate that the proposed method achieves the better performance and relatively low complexity.

cs.IT↗

arXiv2019

Large-area, periodic, and tunable intrinsic pseudo-magnetic fields in low-angle twisted bilayer graphene

A properly strained graphene monolayer or bilayer is expected to harbour periodic pseudo-magnetic fields with high symmetry, yet to date, a convincing demonstration of such pseudo-magnetic fields has been lacking, especially for bilayer graphene. Here, we report the first definitive experimental proof for the existence of large-area, periodic pseudo-magnetic fields, as manifested by vortex lattices in commensurability with the moiré patterns of low-angle twisted bilayer graphene. The pseudo-magnetic fields are strong enough to confine the massive Dirac electrons into circularly localized pseudo-Landau levels, as observed by scanning tunneling microscopy/spectroscopy, and also corroborated by tight-binding calculations. We further demonstrate that the geometry, amplitude, and periodicity of the pseudo-magnetic field can be fine-tuned by both the rotation angle and heterostrain applied to the system. Collectively, the present study substantially enriches twisted bilayer graphene as a powerful enabling platform for exploration of new and exotic physical phenomena, including quantum valley Hall effects and quantum anomalous Hall effects.

cond-mat.str-el↗

arXiv2019

Adaptive wavefront correction of dynamic multimode beam based on modal decomposition

We propose and demonstrate a method for the adaptive wavefront correction of dynamic multimode fiber beams for the first time. The wavefront of incident beam is reconstructed in real-time based on the complete modal information, which obtained by using the modal decomposition of correlation filter method. For the proof of principle, both of the modal decomposition and the wavefront correction are implemented using the same computer-generated hologram, which encoded into a phase-only spatial light modulator. We demonstrate the wavefront correction of dynamic multimode beam at a rate of 5Hz and achieve a 1.73-fold improvement on the average power-in-the-bucket. The experimental results indicate the feasibility of the real-time wavefront correction for the large mode area fiber laser by adaptive optics.

physics.optics↗

arXiv2015

Pushing towards the Limit of Sampling Rate: Adaptive Chasing Sampling

Measurement samples are often taken in various monitoring applications. To reduce the sensing cost, it is desirable to achieve better sensing quality while using fewer samples. Compressive Sensing (CS) technique finds its role when the signal to be sampled meets certain sparsity requirements. In this paper we investigate the possibility and basic techniques that could further reduce the number of samples involved in conventional CS theory by exploiting learning-based non-uniform adaptive sampling. Based on a typical signal sensing application, we illustrate and evaluate the performance of two of our algorithms, Individual Chasing and Centroid Chasing, for signals of different distribution features. Our proposed learning-based adaptive sampling schemes complement existing efforts in CS fields and do not depend on any specific signal reconstruction technique. Compared to conventional sparse sampling methods, the simulation results demonstrate that our algorithms allow $46\%$ less number of samples for accurate signal reconstruction and achieve up to $57\%$ smaller signal reconstruction error under the same noise condition.

cs.IT↗