Combating hate speech on social media is critical for securing cyberspace, yet relies heavily on the efficacy of automated detection systems. As content formats evolve, hate speech is transitioning from solely plain text to complex multimodal expressions, making implicit attacks harder to spot. Current systems, however, often falter on these subtle cases, as they struggle with multimodal content where the emergent meaning transcends the aggregation of individual modalities. To bridge this gap, we move beyond binary classification to characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion. Guided by this fine-grained formulation, we curate the Hate via Vision-Language Interplay (H-VLI) benchmark where the true intent hinges on the intricate interplay of modalities rather than overt visual or textual slurs. To effectively decipher these complex cues, we further propose the Asymmetric Reasoning via Courtroom Agent DEbate (ARCADE) framework. By simulating a judicial process where agents actively argue for accusation and defense, ARCADE forces the model to scrutinize deep semantic cues before reaching a verdict. Extensive experiments demonstrate that ARCADE significantly outperforms state-of-the-art baselines on H-VLI, particularly for challenging implicit cases, while maintaining competitive performance on established benchmarks. Our code and data are available at:https://github.com/Sayur1n/H-VLI
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
Beyond Sentence-level Labels: Integrating Conversational Context and Personal Experience for Natural Emotional Expression
PDF ↗Emotional Text-to-Speech aims to synthesize speech with human-like naturalness and expressiveness. However, existing systems rely on sentence-level labels, which fails to capture the subtle nuances of human affect. Based on cognitive appraisal theories, we argue that emotional expression is not generated in isolation but is deeply influenced by speaker’s Personal Experience and the conversational Context.To overcome the information bottleneck inherent in traditional annotations, we present Emotional-Context-Speech, a large-scale, context-aware speech corpus derived from multi-speaker audiobooks. This dataset provides not only transcriptions but also dialogue context, personal experience, open-vocabulary emotion labels, and paralinguistic descriptions.Experimental results demonstrate that TTS model trained using additional context and experience descriptions as inputs, called Emotional-Context-TTS, significantly outperforms existing methods in terms of emotional expression accuracy and naturalness.
While Audio Large Models (ALLMs) have achieved remarkable proficiency, their robustness remains brittle in real-world deployment. Existing evaluations largely rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics—or "Acoustic Ecology"—that characterize authentic physical environments. To bridge this ecological gap, we introduce RSA-Bench, a comprehensive robustness benchmark designed to stress-test ALLMs through high-fidelity auditory scene simulations. Unlike traditional methods, we construct evaluation samples by naturally superimposing diverse environmental soundscapes—spanning Pasture, Extreme Weather, Classroom, and Outdoors—onto clean speech signals across a spectrum of interference intensities. By evaluating models on six core tasks ranging from fundamental perception to complex reasoning, our study unveils three macro-level insights: (I) The Perception-Cognition Gap: Models maintain relative resilience in low-level recognition but suffer a functional collapse in high-order reasoning tasks under stress; (II) Scenario Sensitivity: "Vocal-like" interference (e.g., children playing) proves significantly more destructive than mechanical noise, challenging the model’s auditory attention mechanisms; and (III) The Denoising Paradox: Standard speech enhancement often exacerbates performance degradation, as ALLMs prove highly sensitive to the semantic distortions introduced by denoising artifacts.
Multimodal Large Language Models (MLLMs) have increasingly supported omni-modal processing across text, vision, and speech. However, existing evaluation frameworks for such models suffer from critical limitations, including modality shortcuts and biased reasoning paths. To address these challenges, we propose OMHBench, a novel benchmark designed to rigorously evaluate omni-modal multi-hop reasoning. It consists of 6,144 questions with balanced reasoning paths that are jointly grounded across all three modalities. Extensive evaluation of 13 state-of-the-art models reveals that (1) a large performance gap exists between proprietary and open-source MLLMs and (2) even proprietary models exhibit high sensitivity to reasoning path variations, resulting in asymmetric omni-modal grounding. Notably, models struggle when processing the speech modality, underscoring the need for balanced, multi-hop evaluation of omni-modal intelligence.
Safety-Aware Dialogue System for Postoperative Oral Cancer Care with Structured Clarification and a Clinically Curated Dataset
PDF ↗Clinical dialogue systems are increasingly vital for patient education and follow-up care; however, effective responses often depend on the clinical context that patients often fail to provide in detail. Responding directly to vague messages can therefore lead to generic or clinically misaligned advice, a challenge that is particularly pronounced in post-op oral cancer (OC) care due to speech impairment and functional limitations. Moreover, post-op OC patients often experience psychological distress, making safety-aware language more likely to arise in dialogue. Dialogue systems in this setting must therefore address both clarifying missing clinical context and ensuring psychological safety. We propose a safety-aware dialogue system that applies information-gain guided clarification before RAG-based response generation and screens user utterances for emotional distress and suicidal ideation. Expert evaluations show that the proposed system improves the quality and clinical appropriateness of generated responses relative to strong baselines, while the safety module closely aligns with expert judgments on clinically concerning utterances. Furthermore, we release a clinically curated Chinese post-op OC QA dataset with expert-validated annotations, which we use throughout our experiments.
Empathy is essential for fostering natural interactions in spoken dialogue systems, as it enables machines to recognize the emotional tone of human speech and deliver empathetic responses. Recent research has made significant progress in developing empathetic spoken chatbots based on large language models (LLMs). However, several challenges still exist when training such models, including reliance on costly empathetic speech instruction data and a lack of emotional expressiveness in the generated speech. Finetuning LLM with cross-modal empathetic instruction data may also lead to catastrophic forgetting and a degradation of its general capability. To address these challenges, we propose FreezeEmpath, an end-to-end empathetic spoken chatbot trained in a simple and efficient manner. The entire training process relies solely on existing speech instruction data and speech emotion recognition (SER) data, while keeping the LLM’s parameters frozen. Experiments demonstrate that FreezeEmpath is able to generate emotionally expressive speech and outperforms other empathetic models in empathetic dialogue, SER, and SpokenQA tasks, demonstrating the effectiveness of our training strategy.
MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free
PDF ↗Extending the input modality of Large Language Models (LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context. Existing research is limited to a dense, parameter-shared adapter to model these diverse patterns, which induces gradient conflict during optimization, as parameter updates required for distinct attributes contradict each other. To address this limitation, we introduce the MoE-Adapter, a sparse Mixture-of-Experts (MoE) architecture designed to decouple acoustic information. Specifically, it employs a dynamic gating mechanism that routes audio tokens to specialized experts capturing complementary feature subspaces while retaining shared experts for global context, thereby mitigating gradient conflicts and enabling fine-grained feature learning. Comprehensive experiments show that the MoE-Adapter achieves superior performance on both audio semantic and paralinguistic tasks, consistently outperforming dense linear baselines with comparable computational costs. To facilitate future research, our code are publicly available at https://github.com/Alittleegg/Eureka-Audio.
Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages
PDF ↗Recent speech foundation models excel at multilingual automatic speech recognition (ASR) for high-resource languages, but adapting them to low-resource languages remains challenging due to data scarcity and efficiency constraints. Full-model fine-tuning is computationally expensive and prone to overfitting, while parameter-efficient methods like LoRA apply adaptation uniformly across layers, overlooking internal representations thus compromising effectiveness and efficiency. We analyze multilingual ASR models and reveal a U-shaped adaptability pattern: early and late layers are language-specific and require more adaptation, while intermediate layers retain shared semantics and need less. Building on this observation, we propose DAMA, a Depth-Aware Model Adaptation framework that allocates adaptation capacity according to each layer’s role. DAMA also introduces Singular Value Decomposition (SVD)-based initialization to constrain adaptation and preserve the U-shaped pattern, as well as a frozen middle-layer basis for further efficiency. Evaluated on 18 low-resource languages across two benchmark datasets, DAMA matches or surpasses state-of-the-art accuracy with 80% fewer trainable parameters, achieves a 29% error reduction under extreme data scarcity, and significantly improves memory, training time, and computational efficiency over baselines. These results highlight the benefits of structure-aware adaptation for efficient, scalable multilingual ASR.
Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models
PDF ↗Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs. In this paper, we empirically revisit the necessity of such granular token-level processing. Through layer-wise oracle interventions, we unveil a structured redundancy hierarchy: while shallow layers encode essential acoustic details, deep layers exhibit extreme redundancy, allowing for aggressive compression. Motivated by these findings, we introduce Affinity Pooling, a training-free, similarity-based token merging mechanism. By strategically applying this method at both input and deep layers, we effectively compress speech representations without compromising semantic information. Extensive evaluations across three tasks demonstrate that our approach reduces prefilling FLOPs by 27.48% while maintaining competitive accuracy. Practical deployment further confirms significant efficiency gains, yielding up to \sim1.7\times memory savings and \sim1.1\times faster time-to-first-token on long utterances. Our results challenge the necessity of fully distinct token representations, providing new perspectives on LSLM efficiency.
Emotional interaction is increasingly crucial for conversational AI, yet current systems lack a self-emotion determination mechanism to drive the streaming text-to-speech (TTS) synthesis. We propose an emotion-planning framework that determines the emotion prior to the textual generation, grounding the downstream emotional TTS in a streaming manner. The framework is implemented by a plug-and-play LLM module, initialized from pretrained LLMs, and trained by reinforcement learning (RL) with emotions as the actions. A hybrid reward is employed which combines imitation signals with theory-driven scoring, in which the theory of Plutchik’s wheel of emotions is adopted. By experiments on DailyDialog, EmoryNLP, IMEOCAP, and MELD, our method outperforms prompting and finetuning baselines on both emotion determination and response quality. We finally implement an entire streaming pipeline for real-time deployment, with the speech quality confirming the framework’s emotional alignment, contextual coherence, and expressive fluency. Codes, cases, and demos are available in https://sixingdeguo.github.io/EmoQ-page/.
Large audio-language models (LALMs) generalize across speech, sound, and music, but unified decoders can exhibit a temporal smoothing bias: transient acoustic cues may be underutilized in favor of temporally smooth context that is better supported by language priors, leading to less specific audio-grounded outputs. We propose Temporal Contrastive Decoding (TCD), a training-free decoding method for unified LALMs that mitigates this effect at inference time. TCD constructs a temporally blurred slow-path view by smoothing the input waveform and re-encoding it, then contrasts next-token logits from the original and slow-path views. The contrastive signal is applied as a token-level logit update restricted to a small candidate set. A self-normalized stability score sets the blur window and update scale, and a step-wise gate based on uncertainty and audio reliance activates the update only when needed. Experiments on MMAU and AIR-Bench show consistent improvements on strong unified LALMs. We further conduct ablations and an architectural applicability study to analyze the contributions of key components and how TCD behaves across large audio-language model designs.
Dataset Pruning (DP) aims to construct a coreset that achieves performance comparable to the original, full dataset. However, few studies have explored DP in the context of Speech Classification (SC) tasks. Unlike image or text classification, SC is particularly challenging due to the difficulty in capturing the acoustic, semantic, and contextual representations. In this study, we propose a novel dataset pruning method for speech datasets, termed Meltrim, which uses a two-step coarse-to-fine framework designed to address these challenges. Specifically, in Step 1, Meltrim coarsely filters utterance-level redundant samples using DBSCAN clustering on Mel-Frequency Cepstral Coefficients (MFCC) features, which are first flattened and then reduced in dimensionality using UMAP. In Step 2, we perform frame-level redundancy pruning for each utterance via utility pruning, which aims to eliminate irrelevant frames within each utterance. To the best of our knowledge, this is the first dataset pruning approach designed for Speech Classification tasks, demonstrating outstanding performance compared to classical general DP methods. Notably, for the Speech Emotion Recognition, our method achieves up to a 49.5% improvement in WA (Weighted Accuracy) on the MEAD dataset. For the Speaker Identification tasks, it results in a 41.9% reduction in EER (Equal Error Rate) on the VoxCeleb1 dataset.
Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data and the difficulty in expanding to more languages. In this paper, we introduce \textbf{C}ross-lingual \textbf{S}peech \textbf{L}anguage \textbf{M}odel (\textbf{CSLM}), an efficient training method for cross-lingual speech LLMs based on discrete speech tokens. We propose a novel alignment strategy that achieves cross-modal and cross-lingual alignment through continual pre-training. By conducting instruction fine-tuning following a speech-text interleaved chain-of-modality generation process, we enhance modal alignment at a finer granularity, thereby improving generation quality and reducing latency. CSLM aligns different modalities and languages simultaneously without the need for massive speech data, thus exhibiting good language scalability. Evaluations on cross-modal tasks, mono-lingual conversational tasks, and cross-lingual conversational tasks demonstrate CSLM’s strong cross-modal alignment capabilities and general task abilities.
Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies
PDF ↗Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT with four adaptive actions: **Sentence_Cut**, **Drop**, **Partial_Summarization** and **Pronominalization**, which enable real-time restructuring, omission, and simplification while preserving semantic fidelity. We adapt these actions in a large language model (LLM) framework and construct training references through action-aware prompting. To evaluate both quality and word-level monotonicity, we further develop a latency-aware TTS pipeline that maps textual outputs to speech with realistic timing. Experiments on the ACL60/60 English-Chinese, English-German and English-Japanese benchmarks show that our framework consistently improves semantic metrics and achieves lower delay compared to reference translations and salami-based baselines. Notably, combining **Drop** and **Sentence_Cut** leads to consistent improvements in the balance between fluency and latency. These results demonstrate that enriching the action space of LLM-based SiMT provides a promising direction for bridging the gap between human and machine interpretation.
Dialectal Arabic datasets embody a range of domain, dialect, and quality. To better understand the landscape of these datasets, we perform a computational analysis of the ‘dialectness’ and a set of measures of audio quality. This analysis of the training splits of dialectal Arabic datasets, provides a valuable complement to existing literature surveys of dialectal Arabic.To further address inconsistencies between datasets, we also introduce Arab Voices, a standardized framework for supporting Automatic Speech Recognition in dialectal Arabic. This framework provide access to 31 datasets covering 14 dialects, to better address the limited data availability encountered in dialectal Arabic speech processing. Our benchmark further provides a current evaluation of SOTA tools as well as modern multimodal LLMs at dialectal Arabic ASR.
We present VoiceStar, the first zero-shot TTS model that achieves both output duration control and extrapolation. VoiceStar is an autoregressive encoder-decoder neural codec language model, that leverages a novel Progress-Monitoring Rotary Position Embedding (PM-RoPE) and is trained with Continuation-Prompt Mixed (CPM) training. PM-RoPE enables the model to better align text and speech tokens, indicates the target duration for the generated speech, and also allows the model to generate speech waveforms much longer in duration than those seen during training. CPM training also helps to mitigate the training/inference mismatch, and significantly improves the quality of the generated speech in terms of speaker similarity and intelligibility. VoiceStar outperforms or is on par with current state-of-the-art models on short-form benchmarks such as LibriSpeech and Seed-TTS, and significantly outperforms these models on long-form/extrapolation benchmarks (20-50s) in terms of intelligibility and naturalness. Code and model: https://github.com/jasonppy/VoiceStar. Audio samples: https://jasonppy.github.io/VoiceStar_web.
We present a neuromuscular speech interface that translates silently voiced articulations directly into text. We record surface electromyographic (EMG) signals from multiple articulatory sites on the face and neck as participants *silently* articulate speech, enabling direct EMG-to-text translation. Such an interface has the potential to restore communication for individuals who have lost the ability to produce intelligible speech due to laryngectomy, neuromuscular disease, stroke, or trauma-induced damage (e.g., radiotherapy toxicity) to the speech articulators. Prior work has largely focused on mapping EMG collected during *audible* articulation to time-aligned audio targets or transferring these targets to *silent* EMG recordings, which inherently requires audio and limits applicability to patients who can no longer speak. In contrast, we propose an efficient representation of high-dimensional EMG signals and demonstrate direct sequence-to-sequence EMG-to-text conversion at the phonemic level without relying on time-aligned audio.
Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplored. We conduct a comprehensive study across 96 languages to analyze the underlying structure of S3M representations, with particular attention to phonological vectors.We first show that there exist linear directions within the model’s representation space that correspond to phonological features. We further demonstrate that the scale of these phonological vectors correlate to the degree of acoustic realization of their corresponding phonological features in a continuous manner. For example, the difference between [d] and [t] yields a voicing vector: adding this vector to [p] produces [b], while scaling it results in a continuum of voicing. Together, these findings indicate that S3Ms encode speech using phonologically interpretable and compositional vectors, demonstrating phonological vector arithmetic.All code and interactive demos are available at https://github.com/juice500ml/phonetic-arithmetic.
Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between patient needs and the availability of mental health support. However, current LLMs struggle to consistently provide effective responses to client speeches, largely due to the lack of supervision from high-quality real psycho-counseling data, whose content is typically inaccessible due to client privacy concerns. Furthermore, the quality of therapists’ responses in available sessions can vary significantly based on their professional training and experience. Assessing the quality of therapists’ responses remains an open challenge. We address these challenges by first proposing a set of professional and comprehensive principles to evaluate therapists’ responses to client speeches. Using these principles, we create a **Psy**cho-**Co**unseling **Pref**erence dataset, **PsyCoPref**, which contains 36k high-quality preference comparison pairs. This dataset aligns with the preferences of professional psychotherapists, providing a robust foundation for evaluating and improving LLMs in psycho-counseling. Experiments on reward modeling and preference learning demonstrate that PsyCoPref is an excellent resource for LLMs to acquire essential skills for responding to clients in a counseling session. Our best-aligned model achieves an impressive win rate of 87% against GPT-4o.
Standard Large Language Models (LLMs) are predominantly designed for static inference with pre-defined inputs, which limits their applicability in dynamic, real-time scenarios. To address this gap, the streaming LLM paradigm has emerged. However, existing definitions of streaming LLMs remain fragmented, conflating streaming generation, streaming inputs, and interactive streaming architectures, while a systematic taxonomy is still lacking. This paper provides a comprehensive overview and analysis of streaming LLMs. First, we establish a unified definition of streaming LLMs based on data flow and dynamic interaction to clarify existing ambiguities. Building on this definition, we propose a systematic taxonomy of current streaming LLMs and provide an in-depth discussion of their underlying methodologies across text, speech, and video streaming scenarios. Furthermore, we explore the applications of streaming LLMs in real-world scenarios and outline promising research directions to support ongoing advances in streaming intelligence. We maintain a continuously updated repository of relevant papers at https://github.com/EIT-NLP/Awesome-Streaming-LLMs.