The increasing complexity and workload of clinical radiology leads to inevitable oversights and mistakes in their use as diagnostic tools, causing delayed treatments and sometimes life-threatening harm to patients. While large language models (LLMs) have shown remarkable progress in many tasks, their utilities in detecting and correcting errors in radiology reporting are limited. This paper proposes a novel dual-knowledge infusion framework that enhances LLMs' capability for radiology report proofreading through systematic integration of medical expertise. Specifically, the knowledge infusion combines medical knowledge graph distillation (MKGD) with external knowledge retrieval (EXKR), enabling an effective automated approach in tackling mistakes in radiology reporting. By decomposing the complex proofreading task into three specialized stages of detection, localization, and correction, our method mirrors the systematic review process employed by expert radiologists, ensuring both precision and clinical interpretability. To perform a robust, clinically relevant evaluation, a comprehensive benchmark is also proposed using real-world radiology reports with real-world error patterns, including speech recognition confusions, terminology ambiguities, and template-related inconsistencies. Extensive evaluations across multiple LLM architectures demonstrate substantial improvements of our approach: up to 31.56% increase in error detection accuracy and 37.4% reduction in processing time. Human evaluation by radiologists confirms superior clinical relevance and factual consistency compared to existing approaches.
论文检索
输入标题、作者或关键词，从 2,480 篇学术成果中精准定位
X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and a Novel LLM-Consulted Explanation Framework
PDF ↗Hate speech detection on social media faces challenges in both accuracy and explainability, especially for underexplored Indic languages. We propose a novel explainability-guided training framework, X-MuTeST (eXplainable Multilingual haTe Speech deTection), for hate speech detection that combines high-level semantic reasoning from large language models (LLMs) with traditional attention-enhancing techniques. We extend this research to Hindi and Telugu alongside English by providing benchmark human-annotated rationales for each word to justify the assigned class label. The X-MuTeST explainability method computes the difference between the prediction probabilities of the original text and those of unigrams, bigrams, and trigrams. Final explanations are computed as the union between LLM explanations and X-MuTeST explanations. We show that leveraging human rationales during training enhances both classification performance and the model’s explainability. Moreover, combining human rationales with our explainability method to refine the model’s attention yields further improvements. We evaluate explainability using Plausibility metrics such as Token-F1 and IOU-F1, and Faithfulness metrics such as Comprehensiveness and Sufficiency. By focusing on under-resourced languages, our work advances hate speech detection across diverse linguistic contexts. Our dataset includes token-level rationale annotations for 6,004 Hindi, 4,492 Telugu, and 6,334 English samples.
mmJEPA-ECG: Cross-Posture Robust Contactless Electrocardiogram Monitoring via Millimeter Wave Radar Sensing
PDF ↗Continuous cardiac monitoring during sleep is vital for detecting silent arrhythmia and other nocturnal cardiac events. While electrocardiogram (ECG) is the clinical gold standard, its reliance on electrodes and physical contact makes it intrusive for daily long-term use. Millimeter-wave (mmWave) radar offers a compelling non-contact alternative by capturing cardiac-induced chest-wall micro-vibrations. Existing radar-to-ECG methods often rely on direct waveform regression, assuming posture-stable mappings that break under natural sleep movements and obscure true cardiac rhythms. Inspired by the modality-invariant perception observed in speech and vision, we introduce mmJEPA-ECG, a physiology-guided framework for reconstructing clinical ECGs by anchoring radar sensing to invariant cardiac dynamics. It addresses two fundamental challenges: (i) disentangling robust cardiac representations from posture-induced artifacts, and (ii) generalizing ECG reconstruction across individuals under signal ambiguity. To address these challenges, Physiology-Oriented Self-Supervised Pretraining builds on a Joint Embedding Predictive Architecture (JEPA) with domain-informed masking and heart rate consistency to extract posture-robust cardiac embeddings. Conditional Diffusion-based ECG Reconstruction then generates personalized ECG waveforms through a hierarchical conditional diffusion process by spectral fidelity and denoising constraints. Extensive experiments on both public and self-collected multi-subject datasets demonstrate that our method outperforms state-of-the-art across waveform and rhythm metrics, halving R-R peak errors even under posture shifts and arrhythmic conditions.
DETONATE – A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization
PDF ↗Alignment is crucial for text-to-image (T2I) models to ensure that the generated images faithfully capture user intent while maintaining safety and fairness. Direct Preference Optimization (DPO) has emerged as a key alignment technique for large language models (LLMs), and its influence is now extending to T2I systems. This paper introduces DPO-Kernels for T2I models, a novel extension of DPO that enhances alignment across three key dimensions: (i) Hybrid Loss, which integrates embedding-based objectives with the traditional probability-based loss to improve optimization; (ii) Kernelized Representations, leveraging Radial Basis Function (RBF), Polynomial, and Wavelet kernels to enable richer feature transformations, ensuring better separation between safe and unsafe inputs; and (iii) Divergence Selection, expanding beyond DPO’s default Kullback–Leibler (KL) regularizer by incorporating alternative divergence measures such as Wasserstein and Rényi divergences to enhance stability and robustness in alignment training. We introduce DETONATE, the first large-scale benchmark of its kind, comprising approximately 100K curated image pairs, categorized as chosen and rejected. This benchmark encapsulates three critical axes of social bias and discrimination: Race, Gender, and Disability. The prompts are sourced from the hate speech datasets, while the images are generated using state-of-the-art T2I models, including Stable Diffusion 3.5 Large (SD-3.5), Stable Diffusion XL (SD-XL), and Midjourney. Furthermore, to evaluate alignment beyond surface metrics, we introduce the Alignment Quality Index (AQI) for T2I systems: a novel geometric measure that quantifies latent space separability of safe/unsafe image activations, revealing hidden model vulnerabilities. While alignment techniques often risk overfitting, we empirically demonstrate that DPO-Kernels preserve strong generalization bounds using the theory of Heavy-Tailed Self-Regularization (HT-SR).
StyleBreak: Revealing Alignment Vulnerabilities in Large Audio-Language Models via Style-Aware Audio Jailbreak
PDF ↗Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models (LLMs). However, the security of LAMs under adversarial attacks remains underexplored, especially through audio jailbreaks that craft malicious audio prompts to bypass alignment. Existing efforts primarily rely on converting text-based attacks into speech or applying shallow signal-level perturbations, overlooking the impact of human speech’s expressive variations on LAM alignment robustness. To address this gap, we propose StyleBreak, a novel style-aware audio jailbreak framework that systematically investigates how diverse human speech attributes affect LAM alignment robustness. Specifically, StyleBreak employs a two-stage style-aware transformation pipeline that perturbs both textual content and audio to control linguistic, paralinguistic, and extralinguistic attributes. Furthermore, we develop a query-adaptive policy network that automatically searches for adversarial styles to enhance the efficiency of LAM jailbreak exploration. Extensive evaluations demonstrate that LAMs exhibit critical vulnerabilities when exposed to diverse human speech attributes. Moreover, StyleBreak achieves substantial improvements in attack effectiveness and efficiency across multiple attack paradigms, highlighting the urgent need for more robust alignment in LAMs.
Interpretability methods have recently gained significant attention, particularly in the context of large language models, enabling insights into linguistic representations, error detection, and model behaviors such as hallucinations and repetitions. However, these techniques remain underexplored in automatic speech recognition (ASR), despite their potential to advance both the performance and interpretability of ASR systems. In this work, we adapt and systematically apply established interpretability methods such as logit lens, linear probing, and activation patching, to examine how acoustic and semantic information evolves across layers in ASR systems. Our experiments reveal previously unknown internal dynamics, including specific encoder-decoder interactions responsible for repetition hallucinations and semantic biases encoded deep within acoustic representations. These insights demonstrate the benefits of extending and applying interpretability techniques to speech recognition, opening promising directions for future research on improving model transparency and robustness.
The opaque nature of deep learning models presents significant challenges for the ethical deployment of hate speech detection systems. To address this limitation, we introduce Supervised Rational Attention (SRA), a framework that explicitly aligns model attention with human rationales, improving both interpretability and fairness in hate speech classification. SRA integrates a supervised attention mechanism into transformer-based classifiers, optimizing a joint objective that combines standard classification loss with an alignment loss term that minimizes the discrepancy between attention weights and human-annotated rationales. We evaluated SRA on hate speech benchmarks in English (HateXplain) and Portuguese (HateBRXplain) with rationale annotations. Empirically, SRA achieves 2.4× better explainability compared to current baselines, and produces token-level explanations that are more faithful and human-aligned. In terms of fairness, SRA achieves competitive fairness across all measures, with second-best performance in detecting toxic posts targeting identity groups, while maintaining comparable results on other metrics. These findings demonstrate that incorporating human rationales into attention mechanisms can enhance interpretability and faithfulness without compromising fairness.
BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards
PDF ↗Short-video platforms now host vast multimodal ads whose deceptive visuals, speech and subtitles demand finer-grained, policy-driven moderation than community safety filters. We present BLM-Guard, a content-audit framework for commercial ads that fuses Chain-of-Thought reasoning with rule-based policy principles and a critic-guided reward. A rule-driven ICoT data-synthesis pipeline jump-starts training by generating structured scene descriptions, reasoning chains and labels, cutting annotation costs. Reinforcement learning then refines the model using a composite reward balancing causal coherence with policy adherence. A multitask architecture models intra-modal manipulations (e.g., exaggerated imagery) and cross-modal mismatches (e.g., subtitle–speech drift), boosting robustness. Experiments on real short-video ads show BLM-Guard surpasses strong baselines in accuracy, consistency and generalization.
The rapid advancement of audio generation technologies has escalated the risks of malicious deepfake audio across speech, sound, singing voice, and music, threatening multimedia security and trust. While existing countermeasures (CMs) perform well in single-type audio deepfake detection (ADD), their performance declines in cross-type scenarios. This paper is dedicated to studying the all-type ADD task. We are the first to comprehensively establish an all-type ADD benchmark to evaluate current CMs, incorporating cross-type deepfake detection across speech, sound, singing voice, and music. Then, we introduce the prompt tuning self-supervised learning (PT-SSL) training paradigm, which optimizes SSL front-end by learning specialized prompt tokens for ADD, requiring 458× fewer trainable parameters than fine-tuning (FT). Considering the auditory perception of different audio types, we propose the wavelet prompt tuning (WPT)-SSL method to capture type-invariant auditory deepfake information from the frequency domain without requiring additional training parameters, thereby enhancing performance over FT in the all-type ADD task. To achieve an universally CM, we utilize all types of deepfake audio for co-training. Experimental results demonstrate that WPT-XLSR-AASIST achieved the best performance, with an average EER of 3.58% across all evaluation sets.
Accurate jailbreak evaluation is critical for LLM red team testing and jailbreak research. Mainstream methods rely on binary classification (string matching, toxic text classifiers, and LLM-based methods), outputting only "yes/no" labels without quantifying harm severity. Emerged multi-dimensional frameworks (e.g., Security Violation, Relative Truthfulness and Informativeness) use unified evaluation standards across scenarios, leading to scenario-specific mismatches (e.g., "Relative Truthfulness" is irrelevant to "hate speech"), undermining evaluation accuracy. To address these, we propose SceneJailEval, with key contributions: (1) A pioneering scenario-adaptive multi-dimensional framework for jailbreak evaluation, overcoming the critical "one-size-fits-all" limitation of existing multi-dimensional methods, and boasting robust extensibility to seamlessly adapt to customized or emerging scenarios. (2) A novel 14-scenario dataset featuring rich jailbreak variants and regional cases, addressing the long-standing gap in high-quality, comprehensive benchmarks for scenario-adaptive evaluation. (3) SceneJailEval delivers state-of-the-art performance with an F1 score of 0.917 on our full-scenario dataset (+6% over SOTA) and 0.995 on JBB (+3% over SOTA), breaking through the accuracy bottleneck of existing evaluation methods in heterogeneous scenarios and solidifying its superiority.
Existing audio adversarial attack methods suffer from poor transferability, primarily due to insufficient exploration of model decision mechanisms and overreliance on heuristic-driven algorithm design. This paper aims to alleviate this gap. Specifically, through observations across three mainstream audio tasks (Automatic Speech Recognition, Speaker Verification, and Keyword Spotting), we reveal that these models primarily rely on local temporal features—inputs with time shuffled retain 83.7% of original accuracy. The SHAP-based visualization further validated that time shuffle leads to a significant shift in the salient regions of the model, but the samples can still be correctly identified, indicating the presence of redundant features that can affect decision-making. Inspired by these findings, we propose Time-Shuffle (TS) adversarial attack (including segments-based TS and phoneme-level-based TS-p). This method divides audio or phonemes into segments, randomly shuffles them, and computes gradients on the shuffled structure. By forcing perturbations to exploit transferable local temporal features and reduce overfitting to source-specific patterns, TS/TS-p inherently enhances transferability. As a model-agnostic framework, TS/TS-p can seamlessly integrate with existing attack methods. Comprehensive experiments demonstrate that TS-p achieved SOTA and boosts transferability by about 23%/14.7%/6.3% on ASR/ASV/KWS.
IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
PDF ↗Existing autoregressive large-scale text-to-speech (TTS) models have advantages in speech naturalness, but their token-by-token generation mechanism makes it difficult to precisely control the duration of synthesized speech. This becomes a significant limitation in applications requiring strict audio-visual synchronization, such as video dubbing. This paper introduces IndexTTS2, which proposes a novel, general, and autoregressive model-friendly method for speech duration control. The method supports two generation modes: one explicitly specifies the number of generated tokens to precisely control speech duration; the other freely generates speech in an autoregressive manner without specifying the number of tokens, while faithfully reproducing the prosodic features of the input prompt. Furthermore, IndexTTS2 achieves disentanglement between emotional expression and speaker identity, enabling independent control over timbre and emotion. In the zero-shot setting, the model can accurately reconstruct the target timbre (from the timbre prompt) while perfectly reproducing the specified emotional tone (from the style prompt). To enhance speech clarity in highly emotional expressions, we incorporate GPT latent representations and design a novel three-stage training paradigm to improve the stability of the generated speech. Additionally, to lower the barrier for emotional control, we designed a soft instruction mechanism based on text descriptions by fine-tuning Qwen3, effectively guiding the generation of speech with the desired emotional orientation. Finally, experimental results on multiple datasets show that IndexTTS2 outperforms state-of-the-art zero-shot TTS models in terms of word error rate, speaker similarity, and emotional fidelity.
Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, large language diffusion models have emerged as a promising alternative to the autoregressive paradigm, offering improved controllability, bidirectional context modeling, and robust generation. However, their application to the audio modality remains underexplored. In this work, we introduce DIFFA, the first diffusion-based large audio-language model designed to perform spoken language understanding. DIFFA integrates a frozen diffusion language model with a lightweight dual-adapter architecture that bridges speech understanding and natural language reasoning. We employ a two-stage training pipeline: first, aligning semantic representations via an ASR objective; then, learning instruction-following abilities through synthetic audio-caption pairs automatically generated by prompting LLMs. Despite being trained on only 960 hours of ASR and 127 hours of synthetic instruction data, DIFFA demonstrates competitive performance on major benchmarks, including MMSU, MMAU, and VoiceBench, outperforming several autoregressive open-source baselines. Our results reveal the potential of large language diffusion models for efficient and scalable audio understanding, opening a new direction for speech-driven AI.
Say More with Less: Variable-Frame-Rate Speech Tokenization via Adaptive Clustering and Implicit Duration Coding
PDF ↗Existing speech tokenizers typically assign a fixed number of tokens per second, regardless of the varying information density or temporal fluctuations in the speech signal. This uniform token allocation mismatches the intrinsic structure of speech, where information is distributed unevenly over time. To address this, we propose VARSTok, a VAriable-frame-Rate Speech Tokenizer that adapts token allocation based on local feature similarity. VARSTok introduces two key innovations: (1) a temporal-aware density peak clustering algorithm that adaptively segments speech into variable-length units, and (2) a novel implicit duration coding scheme that embeds both content and temporal span into a single token index, eliminating the need for auxiliary duration predictors. Extensive experiments show that VARSTok significantly outperforms strong fixed-rate baselines. Notably, it achieves superior reconstruction naturalness while using up to 23% fewer tokens than a 40 Hz fixed-frame-rate baseline. VARSTok further yields lower word error rates and improved naturalness in zero-shot text-to-speech synthesis. To the best of our knowledge, this is the first work to demonstrate that a fully dynamic, variable-frame-rate acoustic speech tokenizer can be seamlessly integrated into downstream speech language models.
Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven effective in other generative domains like text and image generation, its application to generative speech restoration remains largely under-explored. This work investigates the challenges of applying preference-based post-training to this task, focusing on how to define a robust preference signal and curate high-quality data to avoid reward hacking. To address these challenges, we propose a multi-metric preference alignment strategy. We construct a new dataset, GenSR-Pref, comprising 80K preference pairs, where each chosen sample is unanimously favored by a complementary suite of metrics covering perceptual quality, signal fidelity, content consistency, and timbre preservation. This principled approach ensures a holistic preference signal. Applying Direct Preference Optimization (DPO) with our dataset, we observe consistent and significant performance gains across three diverse generative paradigms: autoregressive models (AR), masked generative models (MGM), and flow-matching models (FM) on various restoration benchmarks, in both objective and subjective evaluations. Ablation studies confirm the superiority of our multi-metric strategy over single-metric approaches in mitigating reward hacking. Furthermore, we demonstrate that our aligned models can serve as powerful ''data annotators'', generating high-quality pseudo-labels to serve as a supervision signal for traditional discriminative models in data-scarce scenarios like singing voice restoration.
Recently, End-to-End Speech Translation (E2E-ST) methods leveraging large language models (LLMs) have demonstrated strong generalization capabilities and excellent scalability by integrating pre-trained speech encoders with LLMs, where Low-Rank Adaptation (LoRA) is commonly used for parameter-efficient fine-tuning to reduce training costs. However, LoRA's low-rank assumption often fails in multilingual tasks, as the inherent complexity of cross-lingual semantic relationships and syntactic variations exceeds the representational capacity of low-rank matrices. This leads to parameter conflicts across languages, resulting in suboptimal performance. To address this issue, we propose Mixture of Low-Rank Adaptations (MoLoRA), which integrates the Mixture of Experts (MoE) mechanism with LoRA. MoLoRA effectively enhances the model's expressive capacity while maintaining parameter efficiency during training. Specifically, we treat multiple LoRA modules as low-rank experts and introduce a routing mechanism to dynamically activate language-specific experts. Additionally, shared experts are incorporated and consistently activated to model cross-lingual general knowledge. Furthermore, to enhance the robustness and accuracy of speech representations, we propose a Multi-Granularity Representation Fusion module (MGRF). This module mitigates local distortions in frame-level speech representations caused by noise by fusing frame-level and sentence-level features, thereby providing the LLM with more accurate high-level semantic information. We conduct multilingual experiments on the MuST-C and CoVoST-2 datasets. Our method achieves an average BLEU score of 32.2 across eight language pairs on the MuST-C dataset and an average of 36.3 across three language pairs on the CoVoST-2 dataset, establishing a new state-of-the-art (SOTA) performance.
EA-VAE: Learning to Reconstruct Dysarthric Speech via Variational Autoencoder with Encoding Alignment
PDF ↗Dysarthric speech reconstruction (DSR) aims to enhance the intelligibility of dysarthric speech. Compared with normal speech, the dysarthric speech is characterized by its pathological features, including discontinuous pronunciation, slow speech, hoarseness, and improper pauses. Significant disparities in the feature space between normal and dysarthric speech may result in suboptimal speech reconstruction, thereby degrading speech intelligibility. To enhance the reconstruction ability of speech feature spaces, this paper proposes a DSR model named the Encoding-Aligned Variational Autoencoder (EA-VAE). By incorporating alignment modules of frame-level embedding features, prior distributions, and duration into the encoder of the VAE, the model explicitly aligns the dysarthric speech encoding with a representation of the parallel normal speech. A shared decoder is then used to generate speech with improved intelligibility. Experimental results on the UASpeech benchmark confirm that EA-VAE achieves state-of-the-art performance, with a 31.7% relative word error rate reduction and the highest subjective MOS score (4.48), thoroughly validating the effectiveness and advancements of the proposed method in dysarthric speech reconstruction.
Automatic presentation slide generation can greatly streamline content creation. However, since preferences of each user may vary, existing under-specified formulations often lead to suboptimal results that fail to align with individual user needs. We introduce a novel task that conditions paper-to-slides generation on user-specified preferences. We propose a human behavior-inspired agentic framework, SlideTailor, that progressively generates editable slides in a user-aligned manner. Instead of requiring users to write their preferences in detailed textual form, our system only asks for a paper-slides example pair and a visual template—natural and easy-to-provide artifacts that implicitly encode rich user preferences across content and visual style. Despite the implicit and unlabeled nature of these inputs, our framework effectively distills and generalizes the preferences to guide customized slide generation. We also introduce a novel chain-of-speech mechanism to align slide content with planned oral narration. Such a design significantly enhances the quality of generated slides and enables downstream applications like video presentations. To support this new task, we construct a benchmark dataset that captures diverse user preferences, with carefully designed interpretable metrics for robust evaluation. Extensive experiments demonstrate the effectiveness of our framework.
WhisperDiari: A Whisper-Based Speaker Diarization Framework in Token Space Leveraging Semantic and Speaker Information for Better Text Adaptability
PDF ↗Speaker diarization is a fundamental task in speech processing aims to determine 'who speaks when'. When combined with ASR, it enables speaker-labeled transcription with broad practical value. Most existing methods rely on frame-level classification, but the high cost of annotating mixed-speaker audio limits the availability of large-scale, accurately labeled datasets. As a result, even state-of-the-art models struggle with imprecise speaker boundary detection and semantic segmentation errors, which degrade timestamp accuracy and downstream ASR performance. To address these challenges, we propose WhisperDiari, a unified framework for speaker diarization and ASR. We first construct LibriDiari, a dataset derived from LibriSpeech, containing 2–4 speaker mixed audio annotated with transcripts and speaker labels. WhisperDiari builds on the Whisper model, incorporating speaker adapters and Speaker Similarity Matrix Supervision to enhance speaker representation. In addition, a dedicated speaker decoder fuses speaker embeddings with contextual semantics from Whisper's decoder, enabling token-level diarization. This design effectively resolves segmentation ambiguity, aligns diarization with semantic units, and jointly models 'who speaks what and when', producing accurate, timestamped transcripts. We train the model on LibriDiari and evaluate it on both LibriDiari and the real-world AMI corpus. Experimental results demonstrate that WhisperDiari consistently outperforms state-of-the-art open-source baselines.
SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models
PDF ↗The Speaker Diarization and Recognition (SDR) task aims to predict ``who spoke when and what'' within an audio clip, which is a crucial task in various real-world multi-speaker scenarios such as meeting transcription and dialogue systems. Existing SDR systems typically adopt a cascaded framework, combining multiple modules such as speaker diarization (SD) and automatic speech recognition (ASR). The cascaded systems suffer from several limitations, such as error propagation, difficulty in handling overlapping speech, and lack of joint optimization for exploring the synergy between SD and ASR tasks. To address these limitations, we introduce SpeakerLM, a unified multimodal large language model for SDR that jointly performs SD and ASR in an end-to-end manner. Moreover, to facilitate diverse real-world scenarios, we incorporate a flexible speaker registration mechanism into SpeakerLM, enabling SDR under different speaker registration settings. SpeakerLM is progressively developed with a multi-stage training strategy on large-scale real data. Extensive experiments show that SpeakerLM demonstrates strong data scaling capability and generalizability, outperforming state-of-the-art cascaded baselines on both in-domain and out-of-domain public SDR benchmarks. Furthermore, experimental results show that the proposed speaker registration mechanism effectively ensures robust SDR performance of SpeakerLM across diverse speaker registration conditions and varying numbers of registered speakers.