Searcharxiv⌕ Search

arXiv subjects

Haizhou Li

Publications and source records attributed to Haizhou Li.

At least 55 records · Page 3Linked to original sources
arXiv2026

PAUL: Uncertainty-Guided Partition and Augmentation for Robust Cross-View Geo-Localization under Noisy Correspondence

Cross-view geo-localization is a critical task for UAV navigation, event detection, and aerial surveying, as it enables matching between drone-captured and satellite imagery. Most existing approaches embed multi-modal data into a joint feature space to maximize the similarity of paired images. However, these methods typically assume perfect alignment of image pairs during training, which rarely holds true in real-world scenarios. In practice, factors such as urban canyon effects, electromagnetic interference, and adverse weather frequently induce GPS drift, resulting in systematic alignment shifts where only partial correspondences exist between pairs. Despite its prevalence, this source of noisy correspondence has received limited attention in current research. In this paper, we formally introduce and address the Noisy Correspondence on Cross-View Geo-Localization (NC-CVGL) problem, aiming to bridge the gap between idealized benchmarks and practical applications. To this end, we propose PAUL (Partition and Augmentation by Uncertainty Learning), a novel framework that partitions and augments training data based on estimated data uncertainty through uncertainty-aware co-augmentation and evidential co-training. Specifically, PAUL selectively augments regions with high correspondence confidence and utilizes uncertainty estimation to refine feature learning, effectively suppressing noise from misaligned pairs. Distinct from traditional filtering or label correction, PAUL leverages both data uncertainty and loss discrepancy for targeted partitioning and augmentation, thus providing robust supervision for noisy samples. Comprehensive experiments validate the effectiveness of individual components in PAUL,which consistently achieves superior performance over other competitive noisy-correspondence-driven methods in various noise ratios.

cs.CV↗
arXiv2026

Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives

Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent languages may be individually high-resource, the scarcity of annotated code-switching data further compounds these challenges. In this paper, we systematically analyze CS-ASR from both model-centric and data-centric perspectives. By comparing state-of-the-art algorithmic methods, including language-specific processing and auxiliary language-aware multi-task learning, we discuss their varying effectiveness across datasets with different linguistic characteristics. On the data side, we first investigate TTS as a data augmentation method. By varying the textual characteristics and speaker accents, we analyze the impact of language confusion and accent bias on CS-ASR. To further mitigate data scarcity and enhance textual diversity, we propose a prompting strategy by simplifying the equivalence constraint theory (SECT) to guide large language models (LLMs) in generating linguistically valid code-switching text. The proposed SECT outperforms existing methods in ASR performance and linguistic quality assessments, generating code-switching text that more closely resembles real-world code-switching text. When used to generate speech-text pairs via TTS, SECT proves effective in improving CS-ASR performance. Our analysis of both model- and data-centric methods underscores that effective CS-ASR requires strategies to be carefully aligned with the specific linguistic characteristics of the code-switching data.

eess.AS↗
arXiv2026

AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow

In target speaker extraction (TSE), we aim to recover target speech from a multi-talker mixture using a short enrollment utterance as reference. Recent studies on diffusion and flow-matching generators have improved target-speech fidelity. However, multi-step sampling increases latency, and one-step solutions often rely on a mixture-dependent time coordinate that can be unreliable for real-world conversations. We present AlphaFlowTSE, a one-step conditional generative model trained with a Jacobian-vector product (JVP)-free AlphaFlow objective. AlphaFlowTSE learns mean-velocity transport along a mixture-to-target trajectory starting from the observed mixture, eliminating auxiliary mixing-ratio prediction, and stabilizes training by combining flow matching with an interval-consistency teacher-student target. Experiments on Libri2Mix and REAL-T confirm that AlphaFlowTSE improves target-speaker similarity and real-mixture generalization for downstream automatic speech recognition (ASR).

cs.SD↗
arXiv2026

Neural Dynamics Self-Attention for Spiking Transformers

Integrating Spiking Neural Networks (SNNs) with Transformer architectures offers a promising pathway to balance energy efficiency and performance, particularly for edge vision applications. However, existing Spiking Transformers face two critical challenges: (i) a substantial performance gap compared to their Artificial Neural Networks (ANNs) counterparts and (ii) high memory overhead during inference. Through theoretical analysis, we attribute both limitations to the Spiking Self-Attention (SSA) mechanism: the lack of locality bias and the need to store large attention matrices. Inspired by the localized receptive fields (LRF) and membrane-potential dynamics of biological visual neurons, we propose LRF-Dyn, which uses spiking neurons with localized receptive fields to compute attention while reducing memory requirements. Specifically, we introduce a LRF method into SSA to assign higher weights to neighboring regions, strengthening local modeling and improving performance. Building on this, we approximate the resulting attention computation via charge-fire-reset dynamics, eliminating explicit attention-matrix storage and reducing inference-time memory. Extensive experiments on visual tasks confirm that our method reduces memory overhead while delivering significant performance improvements. These results establish it as a key unit for achieving energy-efficient Spiking Transformers.

cs.NE↗
arXiv2026

EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models

Speech Language Models (SLMs) have made significant progress in spoken language understanding. Yet it remains unclear whether they can fully perceive non lexical vocal cues alongside spoken words, and respond with empathy that aligns with both emotional and contextual factors. Existing benchmarks typically evaluate linguistic, acoustic, reasoning, or dialogue abilities in isolation, overlooking the integration of these skills that is crucial for human-like, emotionally intelligent conversation. We present EchoMind, the first interrelated, multi-level benchmark that simulates the cognitive process of empathetic dialogue through sequential, context-linked tasks: spoken-content understanding, vocal-cue perception, integrated reasoning, and response generation. All tasks share identical and semantically neutral scripts that are free of explicit emotional or contextual cues, and controlled variations in vocal style are used to test the effect of delivery independent of the transcript. EchoMind is grounded in an empathy-oriented framework spanning 3 coarse and 12 fine-grained dimensions, encompassing 39 vocal attributes, and evaluated using both objective and subjective metrics. Testing 12 advanced SLMs reveals that even state-of-the-art models struggle with high-expressive vocal cues, limiting empathetic response quality. Analyses of prompt strength, speech source, and ideal vocal cue recognition reveal persistent weaknesses in instruction-following, resilience to natural speech variability, and effective use of vocal cues for empathy. These results underscore the need for SLMs that integrate linguistic content with diverse vocal cues to achieve truly empathetic conversational ability.

cs.CL↗
arXiv2026

TP-Spikformer: Token Pruned Spiking Transformer

Spiking neural networks (SNNs) offer an energy-efficient alternative to traditional neural networks due to their event-driven computing paradigm. However, recent advancements in spiking transformers have focused on improving accuracy with large-scale architectures, which require significant computational resources and limit deployment on resource-constrained devices. In this paper, we propose a simple yet effective token pruning method for spiking transformers, termed TP-Spikformer, that reduces storage and computational overhead while maintaining competitive performance. Specifically, we first introduce a heuristic spatiotemporal information-retaining criterion that comprehensively evaluates tokens' importance, assigning higher scores to informative tokens for retention and lower scores to uninformative ones for pruning. Based on this criterion, we propose an information-retaining token pruning framework that employs a block-level early stopping strategy for uninformative tokens, instead of removing them outright. This also helps preserve more information during token pruning. We demonstrate the effectiveness, efficiency and scalability of TP-Spikformer through extensive experiments across diverse architectures, including Spikformer, QKFormer and Spike-driven Transformer V1 and V3, and a range of tasks such as image classification, object detection, semantic segmentation and event-based object tracking. Particularly, TP-Spikformer performs well in a training-free manner. These results reveal its potential as an efficient and practical solution for deploying SNNs in real-world applications with limited computational resources.

cs.CV↗
arXiv2026

Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems

Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradigm, requiring complete transcription and full reasoning before speech synthesis can begin, which results in high response latency. We propose the Discourse-Aware Dual-Track Streaming Response (DDTSR) framework, a low-latency architecture that enables listen-while-thinking and speak-while-thinking. DDTSR is built upon three key mechanisms: (1) connective-guided small-large model synergy, where an auxiliary small model generates minimal-committal discourse connectives while a large model performs knowledge-intensive reasoning in parallel; (2) streaming-based cross-modal collaboration, which dynamically overlaps ASR, LLM inference, and TTS to advance the earliest speakable moment; and (3) curriculum-learning-based discourse continuity enhancement, which maintains coherence and logical consistency between early responses and subsequent reasoning outputs. Experiments on two spoken dialogue benchmarks demonstrate that DDTSR reduces response latency by 19%-51% while preserving discourse quality. Further analysis shows that DDTSR functions as a plug-and-play module compatible with diverse LLM backbones, and remains robust across varying utterance lengths, indicating strong practicality and scalability for real-time spoken interaction.

cs.CL↗
arXiv2026

Robust Spiking Neural Networks Against Adversarial Attacks

Spiking Neural Networks (SNNs) represent a promising paradigm for energy-efficient neuromorphic computing due to their bio-plausible and spike-driven characteristics. However, the robustness of SNNs in complex adversarial environments remains significantly constrained. In this study, we theoretically demonstrate that those threshold-neighboring spiking neurons are the key factors limiting the robustness of directly trained SNNs. We find that these neurons set the upper limits for the maximum potential strength of adversarial attacks and are prone to state-flipping under minor disturbances. To address this challenge, we propose a Threshold Guarding Optimization (TGO) method, which comprises two key aspects. First, we incorporate additional constraints into the loss function to move neurons' membrane potentials away from their thresholds. It increases SNNs' gradient sparsity, thereby reducing the theoretical upper bound of adversarial attacks. Second, we introduce noisy spiking neurons to transition the neuronal firing mechanism from deterministic to probabilistic, decreasing their state-flipping probability due to minor disturbances. Extensive experiments conducted in standard adversarial scenarios prove that our method significantly enhances the robustness of directly trained SNNs. These findings pave the way for advancing more reliable and secure neuromorphic computing in real-world applications.

cs.CV↗
arXiv2026

CosyAccent: Duration-Controllable Accent Normalization Using Source-Synthesis Training Data

Accent normalization (AN) systems often struggle with unnatural outputs and undesired content distortion, stemming from both suboptimal training data and rigid duration modeling. In this paper, we propose a "source-synthesis" methodology for training data construction. By generating source L2 speech and using authentic native speech as the training target, our approach avoids learning from TTS artifacts and, crucially, requires no real L2 data in training. Alongside this data strategy, we introduce CosyAccent, a non-autoregressive model that resolves the trade-off between prosodic naturalness and duration control. CosyAccent implicitly models rhythm for flexibility yet offers explicit control over total output duration. Experiments show that, despite being trained without any real L2 speech, CosyAccent achieves significantly improved content preservation and superior naturalness compared to strong baselines trained on real-world data.

eess.AS↗
arXiv2026

AudioRAG: A Challenging Benchmark for Audio Reasoning and Information Retrieval

Due to recent advancements in Large Audio-Language Models (LALMs) that demonstrate remarkable performance across a range of sound-, speech- and music-related tasks, there is a growing interest in proposing benchmarks to assess these models. Existing benchmarks generally focus only on reasoning with internal knowledge, neglecting real-world scenarios that require external information grounding. To bridge this gap, we introduce AudioRAG, a novel benchmark designed to evaluate audio-based reasoning augmented by information retrieval in realistic web environments. This benchmark comprises both LLM-generated and manually curated question-answer pairs. Our evaluations reveal that even the state-of-the-art LALMs struggle to answer these questions. We therefore propose an agentic pipeline that integrates audio reasoning with retrieval-augmented generation, providing a stronger baseline for future research.

eess.AS↗
arXiv2026

EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis

Achieving precise and controllable emotional expression is crucial for producing natural and context-appropriate speech in text-to-speech (TTS) synthesis. However, many emotion-aware TTS systems, including large language model (LLM)-based designs, rely on scaling fixed emotion embeddings or external guidance, limiting their ability to model emotion-specific latent characteristics. To address this gap, we present EmoShift, a lightweight activation-steering framework incorporating a EmoSteer layer, which learns a steering vector for each target emotion in the output embedding space to capture its latent offset and maintain stable, appropriate expression across utterances and categories. With only 10M trainable parameters,less than 1/30 of full fine-tuning, EmoShift outperforms zero-shot and fully fine-tuned baselines in objective and subjective evaluations, enhancing emotional expressiveness while preserving naturalness and speaker similarity. Further analysis confirms the proposed EmoSteer layer's effectiveness and reveals its potential for controllable emotional intensity in speech synthesis.

eess.AS↗
arXiv2026

Adaptive Per-Channel Energy Normalization Front-end for Robust Audio Signal Processing

In audio signal processing, learnable front-ends have shown strong performance across diverse tasks by optimizing task-specific representation. However, their parameters remain fixed once trained, lacking flexibility during inference and limiting robustness under dynamic complex acoustic environments. In this paper, we introduce a novel adaptive paradigm for audio front-ends that replaces static parameterization with a closed-loop neural controller. Specifically, we simplify the learnable front-end LEAF architecture and integrate a neural controller for adaptive representation via dynamically tuning Per-Channel Energy Normalization. The neural controller leverages both the current and the buffered past subband energies to enable input-dependent adaptation during inference. Experimental results on multiple audio classification tasks demonstrate that the proposed adaptive front-end consistently outperforms prior fixed and learnable front-ends under both clean and complex acoustic conditions. These results highlight neural adaptability as a promising direction for the next generation of audio front-ends.

eess.AS↗
arXiv2025

CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation

Theme detection is a fundamental task in user-centric dialogue systems, aiming to identify the latent topic of each utterance without relying on predefined schemas. Unlike intent induction, which operates within fixed label spaces, theme detection requires cross-dialogue consistency and alignment with personalized user preferences, posing significant challenges. Existing methods often struggle with sparse, short utterances for accurate topic representation and fail to capture user-level thematic preferences across dialogues. To address these challenges, we propose CATCH (Controllable Theme Detection with Contextualized Clustering and Hierarchical Generation), a unified framework that integrates three core components: (1) context-aware topic representation, which enriches utterance-level semantics using surrounding topic segments; (2) preference-guided topic clustering, which jointly models semantic proximity and personalized feedback to align themes across dialogue; and (3) a hierarchical theme generation mechanism designed to suppress noise and produce robust, coherent topic labels. Experiments on a multi-domain customer dialogue benchmark (DSTC-12) demonstrate the effectiveness of CATCH with 8B LLM in both theme clustering and topic generation quality.

cs.CL↗
arXiv2025

Binary Event-Driven Spiking Transformer

Transformer-based Spiking Neural Networks (SNNs) introduce a novel event-driven self-attention paradigm that combines the high performance of Transformers with the energy efficiency of SNNs. However, the larger model size and increased computational demands of the Transformer structure limit their practicality in resource-constrained scenarios. In this paper, we integrate binarization techniques into Transformer-based SNNs and propose the Binary Event-Driven Spiking Transformer, i.e. BESTformer. The proposed BESTformer can significantly reduce storage and computational demands by representing weights and attention maps with a mere 1-bit. However, BESTformer suffers from a severe performance drop from its full-precision counterpart due to the limited representation capability of binarization. To address this issue, we propose a Coupled Information Enhancement (CIE) method, which consists of a reversible framework and information enhancement distillation. By maximizing the mutual information between the binary model and its full-precision counterpart, the CIE method effectively mitigates the performance degradation of the BESTformer. Extensive experiments on static and neuromorphic datasets demonstrate that our method achieves superior performance to other binary SNNs, showcasing its potential as a compact yet high-performance model for resource-limited edge devices. The repository of this paper is available at https://github.com/CaoHLin/BESTFormer.

cs.CV↗
arXiv2025

ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extraction

Audio-visual target speaker extraction (AV-TSE) models primarily rely on visual cues from the target speaker. However, humans also leverage linguistic knowledge, such as syntactic constraints, next word prediction, and prior knowledge of conversation, to extract target speech. Inspired by this observation, we propose ELEGANCE, a novel framework that incorporates linguistic knowledge from large language models (LLMs) into AV-TSE models through three distinct guidance strategies: output linguistic constraints, intermediate linguistic prediction, and input linguistic prior. Comprehensive experiments with RoBERTa, Qwen3-0.6B, and Qwen3-4B on two AV-TSE backbones demonstrate the effectiveness of our approach. Significant improvements are observed in challenging scenarios, including visual cue impaired, unseen languages, target speaker switches, increased interfering speakers, and out-of-domain test set. Demo page: https://alexwxwu.github.io/ELEGANCE/.

cs.SD↗
arXiv2025

Leveraging Language Information for Target Language Extraction

Target Language Extraction aims to extract speech in a specific language from a mixture waveform that contains multiple speakers speaking different languages. The human auditory system is adept at performing this task with the knowledge of the particular language. However, the performance of the conventional extraction systems is limited by the lack of this prior knowledge. Speech pre-trained models, which capture rich linguistic and phonetic representations from large-scale in-the-wild corpora, can provide this missing language knowledge to these systems. In this work, we propose a novel end-to-end framework to leverage language knowledge from speech pre-trained models. This knowledge is used to guide the extraction model to better capture the target language characteristics, thereby improving extraction quality. To demonstrate the effectiveness of our proposed approach, we construct the first publicly available multilingual dataset for Target Language Extraction. Experimental results show that our method achieves improvements of 1.22 dB and 1.12 dB in SI-SNR for English and German extraction, respectively, from mixtures containing both languages.

eess.AS↗
arXiv2025

Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing

Speech foundation models have significantly advanced various speech-related tasks by providing exceptional representation capabilities. However, their high-dimensional output features often create a mismatch with downstream task models, which typically require lower-dimensional inputs. A common solution is to apply a dimensionality reduction (DR) layer, but this approach increases parameter overhead, computational costs, and risks losing valuable information. To address these issues, we propose Nested Res2Net (Nes2Net), a lightweight back-end architecture designed to directly process high-dimensional features without DR layers. The nested structure enhances multi-scale feature extraction, improves feature interaction, and preserves high-dimensional information. We first validate Nes2Net on CtrSVDD, a singing voice deepfake detection dataset, and report a 22% performance improvement and an 87% back-end computational cost reduction over the state-of-the-art baseline. Additionally, extensive testing across four diverse datasets: ASVspoof 2021, ASVspoof 5, PartialSpoof, and In-the-Wild, covering fully spoofed speech, adversarial attacks, partial spoofing, and real-world scenarios, consistently highlights Nes2Net's superior robustness and generalization capabilities. The code package and pre-trained models are available at https://github.com/Liu-Tianchi/Nes2Net.

eess.AS↗
arXiv2025

S$^2$NN: Sub-bit Spiking Neural Networks

Spiking Neural Networks (SNNs) offer an energy-efficient paradigm for machine intelligence, but their continued scaling poses challenges for resource-limited deployment. Despite recent advances in binary SNNs, the storage and computational demands remain substantial for large-scale networks. To further explore the compression and acceleration potential of SNNs, we propose Sub-bit Spiking Neural Networks (S$^2$NNs) that represent weights with less than one bit. Specifically, we first establish an S$^2$NN baseline by leveraging the clustering patterns of kernels in well-trained binary SNNs. This baseline is highly efficient but suffers from \textit{outlier-induced codeword selection bias} during training. To mitigate this issue, we propose an \textit{outlier-aware sub-bit weight quantization} (OS-Quant) method, which optimizes codeword selection by identifying and adaptively scaling outliers. Furthermore, we propose a \textit{membrane potential-based feature distillation} (MPFD) method, improving the performance of highly compressed S$^2$NN via more precise guidance from a teacher model. Extensive results on vision tasks reveal that S$^2$NN outperforms existing quantized SNNs in both performance and efficiency, making it promising for edge computing applications.

cs.CV↗