arXiv subjects

Björn Schuller

Publications and source records attributed to Björn Schuller.

At least 19 recordsLinked to original sources

arXiv2026

PerCoV2: Ultra-Low Bit-Rate Perceptual Image Compression via Query-Based 1D Multimodal Image Tokens

Despite recent progress in learned image compression, current image codecs still struggle to maintain realistic reconstructions at low bit-rates, often producing structured artifacts such as grid patterns or repetitive textures, even when trained with perceptual or adversarial losses. We introduce PerCoV2, an ultra-low bit-rate perceptual image compression system that unifies semantic tokenization, flow-based generation, and learned entropy modeling within a single framework. Building on the fully open flow-based SANA architecture, PerCoV2 introduces a novel resolution-adaptive 1D query-based tokenizer that produces compact semantic image tokens with a dual role in flow matching: providing a data-dependent reconstruction prior for initialization and a conditioning signal for flow-based refinement. By explicitly decoupling semantic representation from perceptual generation, our dual representation simplifies the flow-based learning objective, leading to more stable optimization and improved perceptual compression performance. PerCoV2 further introduces a dedicated 1D masked entropy model to improve rate efficiency and optional decoder-side multimodal enhancement via a vision-language model (Molmo) without increasing the transmitted bit budget. On MSCOCO-30k, PerCoV2 achieves state-of-the-art statistical fidelity, measured by FID and KID, across ultra-low and extreme bit-rates (0.0015-0.025 bpp). When trained solely on the general-purpose SA-1B dataset, PerCoV2 further demonstrates strong zero-shot generalization to widely adopted high-resolution benchmarks, including DIV2K and CLIC 2020, achieving competitive statistical fidelity with the current leading method, AEIC-ME. Finally, we introduce PerCoV2-distilled, a practical single-step variant derived from multi-step flow matching that accelerates decoding by 5.37x over PerCoV1, while preserving perceptual compression performance.

cs.CV↗

arXiv2026

Multimodal Target Speaker Extraction: Towards Unified Speaker Cues Across Modalities

Target Speaker Extraction (TSE) is pivotal in speech communication and human-computer interaction, enabling the isolation of a specific speaker's voice from complex acoustic environments, i.e., the cocktail party scenario. Although traditional TSE systems conditioned on enrollment speech have progressed substantially, enrollment speech as a cue has inherent limitations. Its reliability degrades when the target and interfering speakers have similar voice characteristics, when intra-speaker variability (e.g. changes in emotion or speaking style) creates a mismatch between the enrollment and target speech, or when the enrollment itself is contaminated by noise or competing speakers. This review surveys deep-learning-based TSE from the perspective of auxiliary target cues drawn from multiple modalities. We organize existing methods according to five types of information used to isolate the target speaker: audio enrollment, visual, spatial, textual/semantic, and neural cues. We also trace the evolution from discriminative estimators to variational, diffusion, flow, codec, and foundation-model-based systems and summarize representative datasets and evaluation metrics. We review the benefits and limitations of different cues and discuss challenges involving synchronization, missing or unreliable observations, data scarcity, privacy, computational cost, and real-time operation. Finally, we summarize future directions concerning adaptive cue fusion, instruction-driven extraction, realistic evaluation, and trustworthy deployment. By jointly reviewing cue design, model architecture, training objectives, datasets, and evaluation metrics, this article provides an overview of the current landscape and open problems in multimodal TSE.

cs.SD↗

arXiv2026

A New Transformer-Based Approach for Audio-Based Kinship Verification and a New Uncontrolled Mandarin Kinship Speech Dataset

Kinship verification is a task involving determining whether two individuals share a first-order kin relation. To tackle this task, we propose CONVTRAP-TN, a new architecture for audio-based kinship verification, and conduct an ablation study on the proposed model. To the best of our knowledge, we are the first to apply the successful transformer architecture to the task of audio-based kinship verification. Furthermore, we also collect a custom speech dataset, ARKIN, which accurately reflects everyday recording conditions. We do this because only a few speech datasets with kinship labels currently exist, all of which either source extremely noisy in-the-wild data from the internet, or instruct speakers to record in specific environments. These settings fail to reflect real-world scenarios where users record on personal devices under unrestrained conditions. Additionally, we perform a series of preliminary baseline experiments on the collected dataset, including speaker verification and recognition, speech recognition, age estimation, and kinship verification, as well as cross-dataset kinship verification experiments to show that existing methods are not robust across datasets.

cs.SD↗

arXiv2026

Position Paper: Neurotransmitters as a Missing Dimension in Artificial Neural Networks

Artificial neural networks (ANNs), as core components of modern deep learning (DL) systems, lack the adaptive flexibility and long-term stability exhibited by biological systems. This limitation largely stems from the fact that conventional ANNs rely on uniform, local, and gradient-based parameter updates, while neglecting internal learning principles that are biological mechanisms such as neurotransmitters signalling or neuroplasticity. Consequently, many existing approaches focus on architectural expansion or mathematical fine-tuning techniques such as regularisation or parameter isolation. Inspired by the superior adaptability and plasticity of mammalian brains, we posit that neuromodulation with neurotransmitters constitutes a third axis of learning, complementary to neural activity and synaptic plasticity, and should be explicitly modelled in artificial neural networks. In this positional paper, we argue that incorporating neuromodulatory principles into ANN design represents a promising and underexplored research direction, and we advocate for greater attention to this perspective in the development of adaptive and continual learning systems.

cs.NE↗

arXiv2026

Perceptible or Not? Diagnosing Passive Fingerprints for Speech Deepfake Attribution

Passive fingerprints (intrinsic traces naturally left by generators) have been shown to enable attribution in speech deepfake detection, yet their persistence, reproducibility, and content-independence remain unverified. Moreover, no prior work distinguishes perceptible from imperceptible fingerprints, although the two have very different implications for attribution reliability. Perceptible fingerprints, such as emotional expression, are shaped by perceptual quality objectives and may change across model updates, whereas imperceptible fingerprints are not explicitly optimised by current training objectives and are rarely considered in existing dataset design or training strategies, as they have limited influence on downstream applications. We therefore propose a Perceptible-Imperceptible Passive-fingerprint Diagnostic Protocol (PIPDP) to define and separately analyze these two fingerprint types. PIPDP comprises three complementary analyses: multi-evidence fingerprint verification through residual-energy, reproducibility, and saliency analyses, perceptually transparent perturbations preserving audio quality, and prompt-driven emotion change that modifies perceptible fingerprints without model retraining. Experiments across ten speech generators and three attribution detectors show that imperceptible fingerprints provide persistent attribution cues. Perceptually transparent perturbations reduce attribution accuracy by up to 48.2\% on HiggsAudioV3, whereas emotion-driven changes leave attribution largely unchanged, with only about a 1.0\% accuracy variation across emotions on CosyVoice2 using w2v-bert-MLP. These results suggest that imperceptible fingerprints are more reliable for trustworthy attribution.

cs.SD↗

arXiv2026

Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models

Modern multimodal foundation models (MFMs) have made rapid progress on tasks requiring integrated perception across speech, vision, and language, including emotion recognition. However, it remains unclear whether they recognize speech and facial emotion through shared affective functional units or modality-specific pathways. We explore emotion-sensitive neurons (ESNs), sparse decoder neurons selectively associated with emotion categories, in three MFMs: Gemma-4-12B-it, MiniCPM-o-4.5, and Qwen2.5-Omni-7B. Using speech emotion recognition and facial expression recognition as complementary probes, we identify acoustic and visual ESNs. Visual ESNs are causally meaningful: deactivating them selectively impairs recognition of the associated facial emotion, whereas steering their activations selectively enhances recognition of that emotion relative to other emotion categories. Acoustic and visual ESNs further show emotion-matched overlap and similar layer-wise distributions, indicating partial structural alignment between affective representations across speech and faces. Finally, cross-modal interventions reveal bidirectional causal transfer: ESNs identified from one modality produce emotion-specific effects when applied to the other. Our findings provide one of the first cross-modality activation-level analyses of affective functional units in MFMs, suggesting that speech and facial emotion recognition partially converge onto sparse decoder-level components that can be localized and manipulated without training.

cs.CL↗

arXiv2026

Multilingual Emotion Neurons in Large Audio-Language Models

Emotion is central to human communication, and its expression varies across languages. Large audio-language models (LALMs) achieve strong performance on multilingual speech tasks, yet it remains unclear whether they encode emotion through language-specific correlations or language-agnostic representations. We present the first neuron-level interpretability study of this question. We define Multilingual Emotion Neurons (MLENs) as functional units exhibiting stable emotional selectivity and aligned causal effects across languages, and introduce Consistency-Regularized Fusion (CR-Fusion) to identify them. Across four modern LALMs and 12 typologically diverse languages, emotion-sensitive neurons identified independently per language show minimal overlap, and additional monolingual identification data saturates quickly without isolating more transferable units, motivating identification from pooled cross-lingual evidence. Causal interventions demonstrate that MLENs identified by CR-Fusion provide more precise and transferable affective control than monolingual neuron sets in both zero-shot and low-resource settings. Leave-one-out ablations further reveal asymmetric transfer: individual identification languages, including low-resource ones, contribute non-redundant evidence, while several low-resource languages benefit most from the resulting cross-lingual transfer. Together, our findings provide the first causal, neuron-level account of how LALMs encode emotion across languages, and establish multilingual neuron identification as an effective mechanism for understanding cross-lingual affective behavior.

cs.CL↗

arXiv2026

Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models

Emotion is a central dimension of spoken communication, yet, we still lack a mechanistic account of how modern large audio-language models (LALMs) encode it internally. We present the first neuron-level interpretability study of emotion-sensitive neurons (ESNs) in LALMs and provide causal evidence supporting the existence of such units in Qwen2.5-Omni, Kimi-Audio, and Audio Flamingo 3. Across these three widely used open-source models, we compare frequency-, entropy-, mean-deviation-, and contrast-based neuron selectors on multiple emotion recognition benchmarks. Using inference-time interventions, we reveal a consistent emotion-specific signature: deactivating neurons selected for a given emotion disproportionately degrades recognition of that emotion while largely preserving other classes, whereas targeted steering amplifies these units to bias predictions toward the target emotion. These effects arise with modest amounts of identification data and scale systematically with intervention strength. We further observe that ESNs exhibit non-uniform layer-wise clustering with partial cross-dataset transfer. Taken together, our results offer a causal, neuron-level account of emotion decisions in LALMs and highlight targeted neuron interventions as an actionable handle for controllable affective behaviors.

cs.CL↗

arXiv2026

CueNet: Robust Audio-Visual Speaker Extraction through Cross-Modal Cue Mining and Interaction

Audio-visual speaker extraction has attracted increasing attention, as it removes the need for pre-registered speech and leverages the visual modality as a complement to audio. Although existing methods have achieved impressive performance, the issue of degraded visual inputs has received relatively little attention, despite being common in real-world scenarios. Previous attempts to address this problem have mainly involved training with degraded visual data. However, visual degradation can occur in many unpredictable ways, making it impractical to simulate all possible cases during training. In this paper, we aim to enhance the robustness of audio-visual speaker extraction against impaired visual inputs without relying on degraded videos during training. Inspired by observations from human perceptual mechanisms, we propose an audio-visual learner that disentangles speaker information, acoustic synchronisation, and semantic synchronisation as distinct cues. Furthermore, we design a dedicated interaction module that effectively integrates these cues to provide a reliable guidance signal for speaker extraction. Extensive experiments demonstrate the strong robustness of the proposed model under various visual degradations and its clear superiority over existing methods.

cs.MM↗

arXiv2026

Collapsed Effective Operators for Higher-order Structures

Higher-order structures are powerful relational modeling tools, yet existing spectral operators decompose the topology into separate ranks, leaving practitioners to fuse the information back to vertices through ad hoc choices. We introduce Collapsed Effective Operators, which condense higher-order degrees of freedom into a single vertex-level operator via Schur complementation of a graded Laplacian. This yields a (generally dense) operator that encodes long-range interactions mediated by topology and is applicable to arbitrary higher-order constructs. We show it preserves positive semi-definiteness with a spectral upper bound relative to the rank-0 Hodge Laplacian, effectively lowering system energy under higher-order connectivity. Empirically, our operator improves spectral clustering, signal smoothing, and enables the inclusion of topological features in neural network architectures via positional encoding. The project page can be found http://circle-group.github.io/research/CollapsedEffectiveOperators

cs.LG↗

arXiv2026

Towards Speech Impairment Prediction in German-Speaking Individuals with Amyotrophic Lateral Sclerosis

Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disease, often affecting speech due to bulbar dysfunction. In this study, we predict speech impairment in people with ALS (pwALS) using two clinical speech-related scores. We evaluate cross-sectional (across speakers) and personalised (within-speaker) modelling paradigms and analyse the utility of common speech tasks to contribute to the standardisation of speech data collection for pwALS. Experiments on a German-speaking cohort of 66 pwALS show that repetition tasks (/da/-/da/, /da/-/ba/) achieved the best cross-sectional performance (Concordance Correlation Coefficient (CCC) = 0.62) for predicting the Quality of Life in the Dysarthric Speaker questionnaire, while the within-speaker setting reached a CCC of 0.86. This study represents an initial step towards speech impairment prediction in German-speaking pwALS and highlights the potential of automated speech analysis as a supportive tool for speech impairment assessment.

cs.HC↗

arXiv2026

Feature-Augmented Transformers for Robust AI-Text Detection Across Domains and Generators

AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central requirement for supervised binary detectors. We train transformer-based detectors on HC3 PLUS and calibrate a single decision threshold by maximising balanced accuracy on held-out validation; this threshold is then kept fixed for all downstream test distributions, revealing domain- and generator-dependent error asymmetries under shift. We evaluate in-domain on HC3 PLUS, under cross-dataset transfer to the multi-domain, multi-generator M4 benchmark, and on the external AI-Text-Detection-Pile. Although base models achieve near-ceiling in-domain performance (up to 99.5% balanced accuracy), performance under shift is brittle and strongly model-dependent. Feature augmentation via attention-based linguistic feature fusion improves transfer, with our best model (DeBERTa-v3-base+FeatAttn) achieving 85.9% balanced accuracy on M4. Multi-seed experiments confirm high stability. Under the same fixed-threshold protocol, our model outperforms strong zero-shot baselines by up to +7.22 points. Category-level ablations further show that readability and vocabulary features contribute most to robustness under shift. Overall, these results demonstrate that feature augmentation and a modern DeBERTa backbone significantly outperform earlier BERT/RoBERTa models, while the fixed-threshold protocol provides a more realistic and informative assessment of practical detector robustness.

cs.CL↗

arXiv2026

EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs

Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in applications such as social robots and human-computer interaction, where understanding human emotions is essential. However, existing benchmarks mainly formulate emotion understanding as a static recognition problem, leaving it largely unclear whether current MLLMs can understand emotion as a dynamic process that evolves, shifts between states, and unfolds across diverse social contexts. To bridge this gap, we present EmoTrans, a benchmark for evaluating emotion dynamics understanding in multimodal videos. EmoTrans contains 1,000 carefully collected and manually annotated video clips, covering 12 real-world scenarios, and further provides over 3,000 task-specific question-answer (QA) pairs for fine-grained evaluation. The benchmark introduces four tasks, namely Emotion Change Detection (ECD), Emotion State Identification (ESI), Emotion Transition Reasoning (ETR), and Next Emotion Prediction (NEP), forming a progressive evaluation framework from coarse-grained detection to deeper reasoning and prediction. We conduct a comprehensive evaluation of 18 state-of-the-art MLLMs on EmoTrans and obtain two main findings. First, although current MLLMs show relatively stronger performance on coarse-grained emotion change detection, they still struggle with fine-grained emotion dynamics modeling. Second, socially complex settings, especially multi-person scenarios, remain substantially challenging, while reasoning-oriented variants do not consistently yield clear improvements. To facilitate future research, we publicly release the benchmark, evaluation protocol, and code at https://github.com/Emo-gml/EmoTrans.

cs.CV↗

arXiv2026

Non-Unitary Quantum Machine Learning: Fisher Efficiency Transitions from Distributed Quantum Expressivity

Quantum machine learning has faced growing scrutiny over its practical advantages compared to classical approaches, particularly following dequantization results and large scale benchmarking studies that have challenged earlier optimistic claims. This work presents a systematic empirical evaluation of non unitary quantum machine learning implemented via the Linear Combination of Unitaries framework within hybrid quantum classical neural networks. Across more than 570 experiments spanning four domains digit classification MNIST, agricultural disease detection PlantVillage, molecular property regression QM9, and medical histopathology PathMNIST non unitary quantum layers are benchmarked against structurally identical unitary baselines. Consistent performance improvements are observed across all domains, with gains ranging from +0.2 percentage to +5.8 percentage depending on dataset complexity and qubit count. A particularly notable finding is a Fisher efficiency transition in medical imaging tasks, where parameter efficiency shifts from negative to positive as qubit count increases from 10 to 12, indicating a threshold dependent efficiency regime. Additionally, non unitary IQP circuit variants reach or exceed classical baselines at 10 qubits on CIFAR 10, demonstrating that circuits with established complexity theoretic hardness guarantees remain compatible with competitive learning performance under the LCU framework. These results offer a large scale, evidence based characterisation of the conditions under which non unitary QML yields measurable empirical benefits in near term settings.

quant-ph↗

arXiv2026

Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level Dropin & Neuroplasticity Mechanisms

Current audio deepfake detection has achieved remarkable performance using diverse deep learning architectures such as ResNet, and has seen further improvements with the introduction of large models (LMs) like Wav2Vec. The success of large language models (LLMs) further demonstrates the benefits of scaling model parameters, but also highlights one bottleneck where performance gains are constrained by parameter counts. Simply stacking additional layers, as done in current LLMs, is computationally expensive and requires full retraining. Furthermore, existing low-rank adaptation methods are primarily applied to attention-based architectures, which limits their scope. Inspired by the neuronal plasticity observed in mammalian brains, we propose novel algorithms, dropin and further plasticity, that dynamically adjust the number of neurons in certain layers to flexibly modulate model parameters. We evaluate these algorithms on multiple architectures, including ResNet, Gated Recurrent Neural Networks, and Wav2Vec. Experimental results using the widely recognised ASVSpoof2019 LA, PA, and FakeorReal dataset demonstrate consistent improvements in computational efficiency with the dropin approach and a maximum of around 39% and 66% relative reduction in Equal Error Rate with the dropin and plasticity approach among these dataset, respectively. The code and supplementary material are available at Github link.

cs.SD↗

arXiv2026

Explainable Speech Emotion Recognition: Weighted Attribute Fairness to Model Demographic Contributions to Social Bias

Speech Emotion Recognition (SER) systems have growing applications in sensitive domains such as mental health and education, where biased predictions can cause harm. Traditional fairness metrics, such as Equalised Odds and Demographic Parity, often overlook the joint dependency between demographic attributes and model predictions. We propose a fairness modelling approach for SER that explicitly captures allocative bias by learning the joint relationship between demographic attributes and model error. We validate our fairness metric on synthetic data, then apply it to evaluate HuBERT and WavLM models finetuned on the CREMA-D dataset. Our results indicate that the proposed fairness model captures more mutual information between protected attributes and biases and quantifies the absolute contribution of individual attributes to bias in SSL-based SER models. Additionally, our analysis reveals indications of gender bias in both HuBERT and WavLM.

eess.AS↗

arXiv2026

Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models

Large audio-language models (LALMs) can produce expressive speech, yet reliable emotion control remains elusive: conversions often miss the target affect and may degrade linguistic fidelity through refusals, hallucinations, or paraphrase. We present, to our knowledge, the first neuron-level study of emotion control in speech-generative LALMs and demonstrate that compact emotion-sensitive neurons (ESNs) are causally actionable, enabling training-free emotion steering at inference time. ESNs are identified via success-filtered activation aggregation enforcing both emotion realization and content preservation. Across three LALMs (Qwen2.5-Omni-7B, MiniCPM-o 4.5, Kimi-Audio), ESN interventions yield emotion-specific gains that generalize to unseen speakers and are supported by automatic and human evaluation. Controllability depends on selector design, mask sparsity, filtering, and intervention strength. Our results establish a mechanistic framework for training-free emotion control in speech generation.

cs.CL↗

arXiv2026

EmoSURA: Towards Accurate Evaluation of Detailed and Long-Context Emotional Speech Captions

Recent advancements in speech captioning models have enabled the generation of rich, fine-grained captions for emotional speech. However, the evaluation of such captions remains a critical bottleneck: traditional N-gram metrics fail to capture semantic nuances, while LLM judges often suffer from reasoning inconsistency and context-collapse when processing long-form descriptions. In this work, we propose EmoSURA, a novel evaluation framework that shifts the paradigm from holistic scoring to atomic verification. EmoSURA decomposes complex captions into Atomic Perceptual Units, which are self-contained statements regarding vocal or emotional attributes, and employs an audio-grounded verification mechanism to validate each unit against the raw speech signal. Furthermore, we address the scarcity of standardized evaluation resources by introducing SURABench, a carefully balanced and stratified benchmark. Our experiments show that EmoSURA achieves a positive correlation with human judgments, offering a more reliable assessment for long-form captions compared to traditional metrics, which demonstrated negative correlations due to their sensitivity to caption length.

cs.SD↗