arXiv subjects

Juan Liu

Publications and source records attributed to Juan Liu.

At least 19 recordsLinked to original sources

arXiv2026

Identity-Faithful Audio-Visual Target Speaker Extraction with REAL-2MIX and VOXBLINK2-AVSE

Audio-visual target speaker extraction should return the speaker indicated by the video, yet a separator can ignore the visual cue and repeatedly output the acoustically dominant voice. We introduce REAL-2MIX, a Mandarin AV-TSE benchmark of jointly recorded real two-speaker mixtures with synchronized multi-view video. Each scene also contains preceding A-only and B-only stages that provide in-scene speaker references. It contains 77 scenes and 7,598 clips (11.84 hours), including 6,042 dual-annotated mixtures. After processing there leave 6,038 evaluable mixtures and 12,076 target-speaker rows. We additionally curate VOXBLINK2-AVSE from VoxBlink2, comprising 250,828 synchronized audio--lip-ROI pairs from 28,421 identities and 766.17 hours of speech. Our extractor uses frozen, 1,280-dimensional projected AV-HuBERT features, target-conditioned training, and layer-wise feature modulation. We jointly evaluate content with Qwen3-ASR-1.7B CER and target identity with WeSpeaker ResNet34 plus Overlapped Speech Detection (OSD). On the complete manifest, the best archived checkpoint obtains 0.2261 CER, 82.22% strict output correctness, and 69.53% both-output strict success.

eess.AS↗

arXiv2026

Child-Oriented AIGC Video Risk Reviewing: A Benchmark and Knowledge-Supported Iterative Reasoning Framework

The rapid growth of Artificial Intelligence-generated content (AIGC) is reshaping video production and circulation, exposing children to an increasing volume of AIGC videos. Unlike traditionally produced videos, AIGC videos often exhibit greater uncertainty in visual details, narrative coherence, and content expression, which may introduce developmentally inappropriate risks for children. However, existing video safety research is largely designed for general violation detection from an adult perspective and remains insufficient for identifying the fine-grained, implicit, and context-dependent risks that children may encounter when viewing AIGC videos. To address this gap, we study child-oriented AIGC video reviewing, making three contributions. First, we construct CAVSR, a benchmark of 605 real-world videos collected from multiple platforms, and develop a hierarchical risk taxonomy comprising 6 top-level categories and 26 fine-grained labels to support systematic evaluation of children's viewing risks. Second, we propose QVRS-E, a knowledge- and experience-augmented video reviewing framework that combines multi-agent collaboration with expert and experiential knowledge to support targeted evidence acquisition and fact-grounded reviewing decisions. Third, extensive experiments demonstrate that our method significantly enhances the reviewing of child-related risks integrated with vision-language models, and yields more robust review reports.

cs.CV↗

arXiv2026

ECHOv2: Two-Level Band-Splitting Representation Learning for Anomalous Sound Detection

Machine anomalous sound detection (ASD) requires robust audio representations capable of capturing subtle deviations in machine sounds under limited supervision. Existing pre-trained audio backbones do not fully capture frequency-specific characteristics of machine sounds. To address this, we propose ECHOv2, a band-splitting model that learns localized intra-band representations to capture fine-grained spectral patterns while also incorporating a two-level self-distillation strategy with explicit inter-band supervision to model cross-frequency dependencies. The inter-band branch performs global context alignment and masked sub-band reconstruction, and multiple summary tokens are introduced for structured aggregation with controllable frequency granularity, enabling region-aware interaction across sub-bands during training. This design allows ECHOv2 to robustly handle diverse machine types and noisy operating conditions while maintaining stable representation quality. To enable fair and consistent evaluation of pre-trained audio backbones, we establish a unified ASD benchmark over DCASE 2020-2025 with two complementary protocols: embedding-based evaluation for frozen representation discriminability and adaptation-based evaluation for downstream transferability. Ablation studies confirm the effectiveness of intra-band learning, inter-band supervision, and structured aggregation granularity for robust ASD representation learning. These findings demonstrate that structured cross-band modeling provides a powerful and adaptable framework for ASD representation learning and can serve as a strong foundation for future research. The model and benchmark are fully open-sourced at https://github.com/yucongzh/ECHOv2 and https://github.com/yucongzh/ASD_Benchmark to promote reproducible research.

eess.AS↗

arXiv2026

M2S-AVSR: Modality-aware Multi-view Self-supervised Representation for Robust Audio-Visual Speech Recognition

Audio-Visual Speech Recognition (AVSR) enhances speech recognition robustness by leveraging visual cues, while real-world scenarios remain challenging due to viewpoint variation, audio distortion, and visual occlusion, which degrade modality quality and increase audio-visual asynchrony. In this paper, we propose a novel Modality-aware Multi-view Self-supervised representation framework for robust Audio-Visual Speech Recognition (M2S-AVSR). First, we introduce a multi-view representation learning encoder to learn view-invariant visual speech representations. Next, we employ a modality-aware module that explicitly models modality quality and cross-modal synchrony to perform fine-grained modality-aware fusion, enabling fine-grained visual information injection during decoding. In addition, we release AISHELL8-RealScene, a public multi-scenario, multi-view conversational audio-visual dataset recorded in real-world environments, and establish a speech recognition benchmark on it. Experiments on English and Mandarin benchmarks demonstrate the effectiveness of the proposed method under challenging conditions. On LRS3, M2S-AVSR achieves up to 29.4% relative improvement under viewpoint perturbation and visual degradation settings. Our method also achieves new state-of-the-art performance on the MISP2021-AVSR test set. On AISHELL8-RealScene, it achieves the best result in outdoor scenes. The proposed method and dataset provide useful support for future research on robust speech and multimodal tasks under realistic conditions.

eess.AS↗

arXiv2026

DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models

Multi-speaker automatic speech recognition (ASR) aims to transcribe conversational speech involving multiple speakers, requiring the model to capture not only what was said, but also who said it and sometimes when it was spoken. Recent Speech-LLM approaches have shown the potential of unified modeling for this task, but jointly learning speaker attribution, temporal structure, and lexical recognition remains difficult and data-intensive. At the current stage, leveraging reliable speaker diarization as an explicit structural prior provides a practical and efficient way to simplify this task. To effectively exploit such priors, we propose DM-ASR, a diarization-aware multi-speaker ASR framework that reformulates the task as a multi-turn dialogue generation process. Given an audio chunk and diarization results, DM-ASR decomposes transcription into a sequence of speaker- and time-conditioned queries, each corresponding to one speaker in one time segment. This formulation converts multi-speaker recognition into a series of structured sub-tasks, explicitly decoupling speaker-temporal structure from linguistic content and enabling effective integration of diarization cues with the reasoning capability of large language models. We further introduce an optional word-level timestamp prediction mechanism that interleaves word and timestamp tokens, yielding richer structured outputs and better transcription quality. Our analysis shows that diarization systems provide more reliable speaker identities and segment-level boundaries, while LLMs excel at modeling linguistic content and long-range dependencies, demonstrating their complementary strengths. Experiments on Mandarin and English benchmarks show that the proposed approach achieves strong performance with relatively small models and training data, while remaining competitive with or outperforming existing unified approaches.

eess.AS↗

arXiv2026

Language-Invariant Multilingual Speaker Verification for the TidyVoice 2026 Challenge

Multilingual speaker verification (SV) remains challenging due to limited cross-lingual data and language-dependent information in speaker embeddings. This paper presents a language-invariant multilingual SV system for the TidyVoice 2026 Challenge. We adopt the multilingual self-supervised w2v-BERT 2.0 model as the backbone, enhanced with Layer Adapters and Multi-scale Feature Aggregation to better exploit multi-layer representations. A language-adversarial training strategy with a Gradient Reversal Layer is applied to promote language-invariant speaker embeddings. Moreover, a multilingual zero-shot text-to-speech system is used to synthesize speech in multiple languages, improving language diversity. Experimental results demonstrate that fine-tuning the large-scale pretrained model yields competitive performance, while language-adversarial training further enhances robustness. In addition, synthetic speech augmentation provides additional gains under limited training data conditions. Source code is available at https://github.com/ZXHY-82/LI-MSV-TidyVoice2026.

eess.AS↗

arXiv2026

Multi-View Based Audio Visual Target Speaker Extraction

Audio-Visual Target Speaker Extraction (AVTSE) aims to separate a target speaker's voice from a mixed audio signal using the corresponding visual cues. While most existing AVTSE methods rely exclusively on frontal-view videos, this limitation restricts their robustness in real-world scenarios where non-frontal views are prevalent. Such visual perspectives often contain complementary articulatory information that could enhance speech extraction. In this work, we propose Multi-View Tensor Fusion (MVTF), a novel framework that transforms multi-view learning into single-view performance gains. During the training stage, we leverage synchronized multi-perspective lip videos to learn cross-view correlations through MVTF, where pairwise outer products explicitly model multiplicative interactions between different views of input lip embeddings. At the inference stage, the system supports both single-view and multi-view inputs. Experimental results show that in the single-view inputs, our framework leverages multi-view knowledge to achieve significant performance gains, while in the multi-view mode, it further improves overall performance and enhances the robustness. Our demo, code and data are available at https://anonymous.4open.science/w/MVTF-Gridnet-209C/

eess.AS↗

arXiv2026

Robust LLM-based Audio-Visual Speech Recognition with Sparse Modality Alignment and Visual Unit-Guided Refinement

Audio-Visual Speech Recognition (AVSR) integrates acoustic and visual information to enhance robustness in adverse acoustic conditions. Recent advances in Large Language Models (LLMs) have yielded competitive automatic speech recognition performance and shown effectiveness for AVSR. However, prior approaches project audio and visual features independently or apply shallow fusion, limiting cross-modal alignment and complementary exchange while increasing the LLM's computational load. To address this, we propose AVUR-LLM, an LLM-based Audio-Visual Speech Recognition via Sparse Modality Alignment and Visual Unit-Guided Refinement. Experiments on LRS3 demonstrate state-of-the-art results for AVSR. Under additive-noise conditions at 0 dB SNR, it achieves 37% relative improvement over the baseline system.

cs.SD↗

arXiv2025

Decoupling and Damping: Structurally-Regularized Gradient Matching for Multimodal Graph Condensation

In multimodal graph learning, graph structures that integrate information from multiple sources, such as vision and text, can more comprehensively model complex entity relationships. However, the continuous growth of their data scale poses a significant computational bottleneck for training. Graph condensation methods provide a feasible path forward by synthesizing compact and representative datasets. Nevertheless, existing condensation approaches generally suffer from performance limitations in multimodal scenarios, mainly due to two reasons: (1) semantic misalignment between different modalities leads to gradient conflicts; (2) the message-passing mechanism of graph neural networks further structurally amplifies such gradient noise. Based on this, we propose Structural Regularized Gradient Matching (SR-GM), a condensation framework for multimodal graphs. This method alleviates gradient conflicts between modalities through a gradient decoupling mechanism and introduces a structural damping regularizer to suppress the propagation of gradient noise in the topology, thereby transforming the graph structure from a noise amplifier into a training stabilizer. Extensive experiments on four multimodal graph datasets demonstrate the effectiveness of SR-GM, highlighting its state-of-the-art performance and cross-architecture generalization capabilities in multimodal graph dataset condensation.

cs.LG↗

arXiv2025

WhisperVC: Decoupled Cross-Domain Alignment and Speech Generation for Low-Resource Whisper-to-Normal Conversion

Whispered speech lacks vocal-fold excitation, making intelligible conversion challenging. We propose WhisperVC, a three-stage framework for low-resource whisper-to-normal (W2N) conversion that decouples cross-domain alignment from speech generation. Stage 1 uses limited paired whisper-normal data with a content encoder and a Conformer-based variational autoencoder (VAE) with soft-DTW alignment to learn domain-invariant semantic representations. Stage 2, trained only on normal speech, employs a Length-Channel Aligner and a two-stage speaker-conditioned mel generator for timbre and prosody modeling. Stage 3 fine-tunes a HiFi-GAN vocoder for waveform synthesis. Experimental results on AISHELL6-Whisper show competitive quality (DNSMOS 3.07, UTMOS 2.83, CER 16.93%) and WavLM speaker similarity (0.95). The framework also supports privacy-preserving communication as well as non-vocal communication and a rehabilitation tool for post-surgical vocal-fold patients. Samples are available online.

eess.AS↗

arXiv2025

Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling

Audio-visual speech enhancement (AVSE) is a task that uses visual auxiliary information to extract a target speaker's speech from mixed audio. In real-world scenarios, there often exist complex acoustic environments, accompanied by various interfering sounds and reverberation. Most previous methods struggle to cope with such complex conditions, resulting in poor perceptual quality of the extracted speech. In this paper, we propose an effective AVSE system that performs well in complex acoustic environments. Specifically, we design a "separation before dereverberation" pipeline that can be extended to other AVSE networks. The 4th COGMHEAR Audio-Visual Speech Enhancement Challenge (AVSEC) aims to explore new approaches to speech processing in multimodal complex environments. We validated the performance of our system in AVSEC-4: we achieved excellent results in the three objective metrics on the competition leaderboard, and ultimately secured first place in the human subjective listening test.

cs.SD↗

arXiv2025

CrossStateECG: Multi-Scale Deep Convolutional Network with Attention for Rest-Exercise ECG Biometrics

Current research in Electrocardiogram (ECG) biometrics mainly emphasizes resting-state conditions, leaving the performance decline in rest-exercise scenarios largely unresolved. This paper introduces CrossStateECG, a robust ECG-based authentication model explicitly tailored for cross-state (rest-exercise) conditions. The proposed model creatively combines multi-scale deep convolutional feature extraction with attention mechanisms to ensure strong identification across different physiological states. Experimental results on the exercise-ECGID dataset validate the effectiveness of CrossStateECG, achieving an identification accuracy of 92.50% in the Rest-to-Exercise scenario (training on resting ECG and testing on post-exercise ECG) and 94.72% in the Exercise-to-Rest scenario (training on post-exercise ECG and testing on resting ECG). Furthermore, CrossStateECG demonstrates exceptional performance across both state combinations, reaching an accuracy of 99.94% in Rest-to-Rest scenarios and 97.85% in Mixed-to-Mixed scenarios. Additional validations on the ECG-ID and MIT-BIH datasets further confirmed the generalization abilities of CrossStateECG, underscoring its potential as a practical solution for post-exercise ECG-based authentication in dynamic real-world settings.

cs.LG↗

arXiv2025

Spatially-Augmented Sequence-to-Sequence Neural Diarization for Meetings

This paper proposes a Spatially-Augmented Sequence-to-Sequence Neural Diarization (SA-S2SND) framework, which integrates direction-of-arrival (DOA) cues estimated by SRP-DNN into the S2SND backbone. A two-stage training strategy is adopted: the model is first trained with single-channel audio and DOA features, and then further optimized with multi-channel inputs under DOA guidance. In addition, a simulated DOA generation scheme is introduced to alleviate dependence on matched multi-channel corpora. On the AliMeeting dataset, SA-S2SND consistently outperform the S2SND baseline, achieving a 7.4% relative DER reduction in the offline mode and over 19% improvement when combined with channel attention. These results demonstrate that spatial cues are highly complementary to cross-channel modeling, yielding good performance in both online and offline settings.

eess.AS↗

arXiv2025

Bridging the Gap: Enhancing Gaze-Performance Link in Children with ASD through Dual-Level Visual Guidance in MR-DMT

Autism Spectrum Disorder (ASD) is marked by action imitation deficits stemming from visuomotor integration impairments, posing challenges to imitation-based learning, such as dance movement therapy in mixed reality (MR-DMT). Previous gaze-guiding interventions in ASD have mainly focused on optimizing gaze in isolation, neglecting the crucial "gaze-performance link". This study investigates enhancing this link in MR-DMT for children with ASD. Initially, we experimentally confirmed the weak link: longer gaze durations didn't translate to better performance. Then, we proposed and validated a novel dual-level visual guidance system that operates on both perceptual and transformational levels: not only directing attention to task-relevant areas but also explicitly scaffolding the translation from gaze perception to performance execution. Our results demonstrate its effectiveness in boosting the gaze-performance link, laying key foundations for more precisely tailored and effective MR-DMT interventions for ASD.

cs.HC↗

arXiv2025

AISHELL6-whisper: A Chinese Mandarin Audio-visual Whisper Speech Dataset with Speech Recognition Baselines

Whisper speech recognition is crucial not only for ensuring privacy in sensitive communications but also for providing a critical communication bridge for patients under vocal restraint and enabling discrete interaction in noise-sensitive environments. The development of Chinese mandarin audio-visual whisper speech recognition is hindered by the lack of large-scale datasets. We present AISHELL6-Whisper, a large-scale open-source audio-visual whisper speech dataset, featuring 30 hours each of whisper speech and parallel normal speech, with synchronized frontal facial videos. Moreover, we propose an audio-visual speech recognition (AVSR) baseline based on the Whisper-Flamingo framework, which integrates a parallel training strategy to align embeddings across speech types, and employs a projection layer to adapt to whisper speech's spectral properties. The model achieves a Character Error Rate (CER) of 4.13% for whisper speech and 1.11% for normal speech in the test set of our dataset, and establishes new state-of-the-art results on the wTIMIT benchmark. The dataset and the AVSR baseline codes are open-sourced at https://zutm.github.io/AISHELL6-Whisper.

eess.AS↗

arXiv2025

Robust Audio-Visual Target Speaker Extraction with Emotion-Aware Multiple Enrollment Fusion

Audio-Visual Target Speaker Extraction (AVTSE) is crucial for cocktail party scenarios. Leveraging multiple cues --such as utterance-level speaker embeddings or steady face images, and frame-level lip motion or facial expression features --can significantly improve performance. However, real-world applications often suffer from intermittent signal loss, especially for frame-level cues. This paper systematically investigates the robustness of multi-enrollment fusion under varying degrees of modality missing. Results show that while full multimodal fusion excels under ideal conditions, its performance degrades sharply when encountering unseen modalities missing during the testing. Crucially, training with a high missing rate dramatically enhances robustness, maintaining stable performance even under severe test-time modality missing. We demonstrate that fusing the complementary one frame of face image with frame-level lip features achieves both strong performance and robustness for the AVTSE task. The model and codes are shared.

eess.AS↗

arXiv2025

Multi-scale Scanning Network for Machine Anomalous Sound Detection

Machine sounds exhibit consistent and repetitive patterns in both the frequency and time domains, which vary significantly across scales for different machine types. For instance, rotating machines often show periodic features in short time intervals, while reciprocating machines exhibit broader patterns spanning the time domain. While prior studies have leveraged these patterns to improve Anomalous Sound Detection (ASD), the variation of patterns across scales remains insufficiently explored. To address this gap, we introduce a Multi-scale Scanning Network (MSN) designed to capture patterns at multiple scales. MSN employs kernel boxes of varying sizes to scan audio spectrograms and integrates a lightweight convolutional network with shared weights for efficient and scalable feature representation. Experimental evaluations on the DCASE 2020 and DCASE 2023 Task 2 datasets demonstrate that MSN achieves state-of-the-art performance, highlighting its effectiveness in advancing ASD systems.

cs.SD↗

arXiv2025

LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions

Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive capability in visual tasks, but their fine-tuning often suffers from bias in class-imbalanced scene. Recent works have introduced large language models (LLMs) to enhance VLM fine-tuning with supplementing semantic information. However, they often overlook inherent class imbalance in VLMs' pre-training, which may lead to bias accumulation in downstream tasks. To address this problem, this paper proposes a Multi-dimensional Dynamic Prompt Routing (MDPR) framework. MDPR constructs a comprehensive knowledge base for classes, spanning five visual-semantic dimensions. During fine-tuning, the dynamic routing mechanism aligns global visual classes, retrieves optimal prompts, and balances fine-grained semantics, yielding stable predictions through logits fusion. Extensive experiments on long-tailed benchmarks, including CIFAR-LT, ImageNet-LT, and Places-LT, demonstrate that MDPR achieves comparable results with current SOTA methods. Ablation studies further confirm the effectiveness of our semantic library for tail classes, and show that our dynamic routing incurs minimal computational overhead, making MDPR a flexible and efficient enhancement for VLM fine-tuning under data imbalance.

cs.CV↗