arXiv subjects

Lantian Li

Publications and source records attributed to Lantian Li.

At least 19 recordsLinked to original sources

arXiv2026

Training-Free Multi-Step Inference for Target Speaker Extraction

Target speaker extraction (TSE) aims to recover a target speaker's speech from a mixture using a reference utterance as a cue. Most TSE systems adopt conditional auto-encoder architectures with one-step inference. Inspired by test-time scaling, we propose a training-free multi-step inference method that enables iterative refinement with a frozen pretrained model. At each step, new candidates are generated by interpolating the original mixture and the previous estimate, and the best candidate is selected for further refinement until convergence. Experiments show that, when ground-truth target speech is available, optimizing an intrusive metric (SI-SDRi) yields consistent gains across multiple evaluation metrics. Without ground truth, optimizing non-intrusive metrics (UTMOS or SpkSim) improves the corresponding metric but may hurt others. We therefore introduce joint metric optimization to balance these objectives, enabling controllable extraction preferences for practical deployment.

cs.SD↗

arXiv2025

Understanding Typing-Related Bugs in Solidity Compiler

The correctness of the Solidity compiler is crucial for ensuring the security of smart contracts. However, the implementation complexity of its type system often introduces elusive defects. This paper presents the first systematic empirical study on typing-related bugs in the Solidity compiler. To systematically analyze these bugs, we collected 146 officially confirmed and fixed typing-related bugs from the official GitHub repository of Solidity compiler. For each bug, we conducted an in-depth analysis and classification from four dimensions: symptoms, root causes, exposure conditions, and fix strategies. Through this study, we reveal unique distribution patterns and key characteristics of such bugs, and summarize 12 core findings. We additionally give the implications of our findings, and these implications not only deepen the understanding of inherent weaknesses in the Solidity compiler but also provide new insights for detecting and fixing typing-related bugs in the Solidity compiler.

cs.SE↗

arXiv2025

MT-HuBERT: Self-Supervised Mix-Training for Few-Shot Keyword Spotting in Mixed Speech

Few-shot keyword spotting aims to detect previously unseen keywords with very limited labeled samples. A pre-training and adaptation paradigm is typically adopted for this task. While effective in clean conditions, most existing approaches struggle with mixed keyword spotting--detecting multiple overlapping keywords within a single utterance--a capability essential for real-world applications. We have previously proposed a pre-training approach based on Mix-Training (MT) to tackle the mixed keyword detection problem and demonstrated its efficiency. However, this approach is fully supervised, unable to utilize vast unlabeled data. To this end, we propose Mix-Training HuBERT (MT-HuBERT), a self-supervised learning (SSL) pre-training framework that implements the MT criterion during pre-training. MT-HuBERT predicts, in a self-supervised manner, the clean acoustic units of each constituent signal from contextual cues, in contrast to predicting compositional patterns of mixed speech. Experiments conducted on the Google Speech Commands (GSC v2) corpus demonstrate that our proposed MT-HuBERT consistently outperforms several state-of-the-art baselines in few-shot KWS tasks under both mixed and clean conditions.

cs.SD↗

arXiv2025

Understanding Inconsistent State Update Vulnerabilities in Smart Contracts

Smart contracts enable contract terms to be automatically executed and verified on the blockchain, and recent years have witnessed numerous applications of them in areas such as financial institutions and supply chains. The execution logic of a smart contract is closely related to the contract state, and thus the correct and safe execution of the contract depends heavily on the precise control and update of the contract state. However, the contract state update process can have issues. In particular, inconsistent state update issues can arise for reasons such as unsynchronized modifications. Inconsistent state update bugs have been exploited by attackers many times, but existing detection tools still have difficulty in effectively identifying them. This paper conducts the first large-scale empirical study about inconsistent state update vulnerabilities (that is, inconsistent state update bugs that are exploitable) in smart contracts, aiming to shed light for developers, researchers, tool builders, and language or library designers in order to avoid inconsistent state update vulnerabilities. We systematically investigate 116 inconsistent state update vulnerabilities in 352 real-world smart contract projects, summarizing their root causes, fix strategies, and exploitation methods. Our study provides 11 original and important findings, and we also give the implications of our findings. To illustrate the potential benefits of our research, we also develop a proof-of-concept checker based on one of our findings. The checker effectively detects issues in 64 popular GitHub projects, and 19 project owners have confirmed the detected issues at the time of writing. The result demonstrates the usefulness and importance of our findings for avoiding inconsistent state update vulnerabilities in smart contracts.

cs.SE↗

arXiv2025

IDOL: Improved Different Optimization Levels Testing for Solidity Compilers

As blockchain technology continues to evolve and mature, smart contracts have become a key driving force behind the digitization and automation of transactions. Smart contracts greatly simplify and refine the traditional business transaction processes, and thus have had a profound impact on various industries such as finance and supply chain management. However, because smart contracts cannot be modified once deployed, any vulnerabilities or design flaws within the contract cannot be easily fixed, potentially leading to significant financial losses or even legal issues. The compiler, as a critical component in the development process, directly affects the quality and security of smart contracts. This paper innovatively proposes a method, known as the Improved Different Optimization Levels (IDOL), for testing the Solidity compiler. The key idea behind IDOL is to perform reverse optimization transformations (i.e., change optimized form into unoptimized form) to generate semantically equivalent variants of the smart contracts under test, aiming to maximize the opportunities to trigger the optimization logic of compilers. We conducted a preliminary evaluation of IDOL and three confirmed compiler optimization bugs have been uncovered at the time of writing.

cs.SE↗

arXiv2025

Solsmith: Solidity Random Program Generator for Compiler Testing

Smart contracts are computer programs that run on blockchain platforms, with Solidity being the most widely used language for their development. As blockchain technology advances, smart contracts have become increasingly important across various fields. In order for smart contracts to operate correctly, the correctness of the compiler is particularly crucial. Although some research efforts have been devoted to testing Solidity compilers, they primarily focus on testing methods and do not address the core issue of generating test programs. To fill this gap, this paper designs and implements Solsmith, a test program generator specifically aimed at uncovering defects in Solidity compilers. It tests the compiler correctness by generating valid and diverse Solidity programs. We have designed a series of unique program generation strategies tailored to Solidity, including enabling optimizations more frequently, avoiding undefined behaviour, and mitigating behavioural differences caused by intermediate representations. To validate the effectiveness of Solsmith, we assess the effectiveness of the test programs generated by Solsmith using the approach of differential testing. The preliminary results show that Solsmith can generate the expected test programs and uncover four confirmed defects in Solidity compilers, demonstrating the effectiveness and potential of Solsmith.

cs.SE↗

arXiv2025

An Investigation on Speaker Augmentation for End-to-End Speaker Extraction

Target confusion, defined as occasional switching to non-target speakers, poses a key challenge for end-to-end speaker extraction (E2E-SE) systems. We argue that this problem is largely caused by the lack of generalizability and discrimination of the speaker embeddings, and introduce a simple yet effective speaker augmentation strategy to tackle the problem. Specifically, we propose a time-domain resampling and rescaling pipeline that alters speaker traits while preserving other speech properties. This generates a variety of pseudo-speakers to help establish a generalizable speaker embedding space, while the speaker-trait-specific augmentation creates hard samples that force the model to focus on genuine speaker characteristics. Experiments on WSJ0-2Mix and LibriMix show that our method mitigates the target confusion and improves extraction performance. Moreover, it can be combined with metric learning, another effective approach to address target confusion, leading to further gains.

cs.SD↗

arXiv2025

CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge

This paper presents the second Chinese Continuous Visual Speech Recognition Challenge (CNVSRC 2024), which builds on CNVSRC 2023 to advance research in Chinese Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR). The challenge evaluates two test scenarios: reading in recording studios and Internet speech. CNVSRC 2024 uses the same datasets as its predecessor CNVSRC 2023, which involves CN-CVS for training and CNVSRC-Single/Multi for development and evaluation. However, CNVSRC 2024 introduced two key improvements: (1) a stronger baseline system, and (2) an additional dataset, CN-CVS2-P1, for open tracks to improve data volume and diversity. The new challenge has demonstrated several important innovations in data preprocessing, feature extraction, model design, and training strategies, further pushing the state-of-the-art in Chinese LVC-VSR. More details and resources are available at the official website.

cs.CV↗

arXiv2025

Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing

Visual Speech Recognition (VSR) transcribes speech by analyzing lip movements. Recently, Large Language Models (LLMs) have been integrated into VSR systems, leading to notable performance improvements. However, the potential of LLMs has not been extensively studied, and how to effectively utilize LLMs in VSR tasks remains unexplored. This paper systematically explores how to better leverage LLMs for VSR tasks and provides three key contributions: (1) Scaling Test: We study how the LLM size affects VSR performance, confirming a scaling law in the VSR task. (2) Context-Aware Decoding: We add contextual text to guide the LLM decoding, improving recognition accuracy. (3) Iterative Polishing: We propose iteratively refining LLM outputs, progressively reducing recognition errors. Extensive experiments demonstrate that by these designs, the great potential of LLMs can be largely harnessed, leading to significant VSR performance improvement.

cs.CV↗

arXiv2024

Neural Scoring: A Refreshed End-to-End Approach for Speaker Recognition in Complex Conditions

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with multi-talker speech due to the unidentifiability of embedding vectors. In this paper, we propose Neural Scoring (NS), a refreshed end-to-end framework that directly estimates verification posterior probabilities without relying on test-side embeddings, making it more robust to complex conditions, e.g., with multiple talkers. To make the training of such an end-to-end model more efficient, we introduce a large-scale trial e2e training (LtE2E) strategy, where each test utterance pairs with a set of enrolled speakers, thus enabling the processing of large-scale verification trials per batch. Experiments on the VoxCeleb dataset demonstrate that NS consistently outperforms both the baseline and competitive methods across various conditions, achieving an overall 70.36% reduction in EER compared to the baseline.

cs.SD↗

arXiv2024

AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition

Visual Speech Recognition (VSR) aims to recognize corresponding text by analyzing visual information from lip movements. Due to the high variability and weak information of lip movements, VSR tasks require effectively utilizing any information from any source and at any level. In this paper, we propose a VSR method based on audio-visual cross-modal alignment, named AlignVSR. The method leverages the audio modality as an auxiliary information source and utilizes the global and local correspondence between the audio and visual modalities to improve visual-to-text inference. Specifically, the method first captures global alignment between video and audio through a cross-modal attention mechanism from video frames to a bank of audio units. Then, based on the temporal correspondence between audio and video, a frame-level local alignment loss is introduced to refine the global alignment, improving the utility of the audio information. Experimental results on the LRS2 and CNVSRC.Single datasets consistently show that AlignVSR outperforms several mainstream VSR methods, demonstrating its superior and robust performance.

cs.SD↗

arXiv2024

Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective

In the field of spoken language processing, audio-visual speech processing is receiving increasing research attention. Key components of this research include tasks such as lip reading, audio-visual speech recognition, and visual-to-speech synthesis. Although significant success has been achieved, theoretical analysis is still insufficient for audio-visual tasks. This paper presents a quantitative analysis based on information theory, focusing on information intersection between different modalities. Our results show that this analysis is valuable for understanding the difficulties of audio-visual processing tasks as well as the benefits that could be obtained by modality integration.

cs.SD↗

arXiv2024

E-code: Mastering Efficient Code Generation through Pretrained Models and Expert Encoder Group

Context: With the waning of Moore's Law, the software industry is placing increasing importance on finding alternative solutions for continuous performance enhancement. The significance and research results of software performance optimization have been on the rise in recent years, especially with the advancement propelled by Large Language Models(LLMs). However, traditional strategies for rectifying performance flaws have shown significant limitations at the competitive code efficiency optimization level, and research on this topic is surprisingly scarce. Objective: This study aims to address the research gap in this domain, offering practical solutions to the various challenges encountered. Specifically, we have overcome the constraints of traditional performance error rectification strategies and developed a Language Model (LM) tailored for the competitive code efficiency optimization realm. Method: We introduced E-code, an advanced program synthesis LM. Inspired by the recent success of expert LMs, we designed an innovative structure called the Expert Encoder Group. This structure employs multiple expert encoders to extract features tailored for different input types. We assessed the performance of E-code against other leading models on a competitive dataset and conducted in-depth ablation experiments. Results: Upon systematic evaluation, E-code achieved a 54.98% improvement in code efficiency, significantly outperforming other advanced models. In the ablation experiments, we further validated the significance of the expert encoder group and other components within E-code. Conclusion: The research findings indicate that the expert encoder group can effectively handle various inputs in efficiency optimization tasks, significantly enhancing the model's performance.

cs.SE↗

arXiv2024

Serialized Output Training by Learned Dominance

Serialized Output Training (SOT) has showcased state-of-the-art performance in multi-talker speech recognition by sequentially decoding the speech of individual speakers. To address the challenging label-permutation issue, prior methods have relied on either the Permutation Invariant Training (PIT) or the time-based First-In-First-Out (FIFO) rule. This study presents a model-based serialization strategy that incorporates an auxiliary module into the Attention Encoder-Decoder architecture, autonomously identifying the crucial factors to order the output sequence of the speech components in multi-talker speech. Experiments conducted on the LibriSpeech and LibriMix databases reveal that our approach significantly outperforms the PIT and FIFO baselines in both 2-mix and 3-mix scenarios. Further analysis shows that the serialization module identifies dominant speech components in a mixture by factors including loudness and gender, and orders speech components based on the dominance score.

cs.SD↗

arXiv2024

CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge

The first Chinese Continuous Visual Speech Recognition Challenge aimed to probe the performance of Large Vocabulary Continuous Visual Speech Recognition (LVC-VSR) on two tasks: (1) Single-speaker VSR for a particular speaker and (2) Multi-speaker VSR for a set of registered speakers. The challenge yielded highly successful results, with the best submission significantly outperforming the baseline, particularly in the single-speaker task. This paper comprehensively reviews the challenge, encompassing the data profile, task specifications, and baseline system construction. It also summarises the representative techniques employed by the submitted systems, highlighting the most effective approaches. Additional information and resources about this challenge can be accessed through the official website at http://cnceleb.org/competition.

cs.CL↗

arXiv2024

SE/BN Adapter: Parametric Efficient Domain Adaptation for Speaker Recognition

Deploying a well-optimized pre-trained speaker recognition model in a new domain often leads to a significant decline in performance. While fine-tuning is a commonly employed solution, it demands ample adaptation data and suffers from parameter inefficiency, rendering it impractical for real-world applications with limited data available for model adaptation. Drawing inspiration from the success of adapters in self-supervised pre-trained models, this paper introduces a SE/BN adapter to address this challenge. By freezing the core speaker encoder and adjusting the feature maps' weights and activation distributions, we introduce a novel adapter utilizing trainable squeeze-and-excitation (SE) blocks and batch normalization (BN) layers, termed SE/BN adapter. Our experiments, conducted using VoxCeleb for pre-training and 4 genres from CN-Celeb for adaptation, demonstrate that the SE/BN adapter offers significant performance improvement over the baseline and competes with the vanilla fine-tuning approach by tuning just 1% of the parameters.

cs.SD↗

arXiv2024

Zero-Shot Fake Video Detection by Audio-Visual Consistency

Recent studies have advocated the detection of fake videos as a one-class detection task, predicated on the hypothesis that the consistency between audio and visual modalities of genuine data is more significant than that of fake data. This methodology, which solely relies on genuine audio-visual data while negating the need for forged counterparts, is thus delineated as a `zero-shot' detection paradigm. This paper introduces a novel zero-shot detection approach anchored in content consistency across audio and video. By employing pre-trained ASR and VSR models, we recognize the audio and video content sequences, respectively. Then, the edit distance between the two sequences is computed to assess whether the claimed video is genuine. Experimental results indicate that, compared to two mainstream approaches based on semantic consistency and temporal consistency, our approach achieves superior generalizability across various deepfake techniques and demonstrates strong robustness against audio-visual perturbations. Finally, state-of-the-art performance gains can be achieved by simply integrating the decision scores of these three systems.

cs.SD↗

arXiv2024

A Comprehensive Investigation on Speaker Augmentation for Speaker Recognition

Data augmentation (DA) has played a pivotal role in the success of deep speaker recognition. Current DA techniques primarily focus on speaker-preserving augmentation, which does not change the speaker trait of the speech and does not create new speakers. Recent research has shed light on the potential of speaker augmentation, which generates new speakers to enrich the training dataset. In this study, we delve into two speaker augmentation approaches: speed perturbation (SP) and vocal tract length perturbation (VTLP). Despite the empirical utilization of both methods, a comprehensive investigation into their efficacy is lacking. Our study, conducted using two public datasets, VoxCeleb and CN-Celeb, revealed that both SP and VTLP are proficient at generating new speakers, leading to significant performance improvements in speaker recognition. Furthermore, they exhibit distinct properties in sensitivity to perturbation factors and data complexity, hinting at the potential benefits of their fusion. Our research underscores the substantial potential of speaker augmentation, highlighting the importance of in-depth exploration and analysis.

cs.SD↗