Mean Opinion Scores

Human mean opinion scores (MOS) are costly to collect, and non-intrusive MOS predictors degrade sharply outside their training domain. ProxyMOS turns a pool of public MOS predictors into a single stronger model without new human labels. Eight predictors are benchmarked against human ratings; the five most informative enter a subset search under uniform, correlation-weighted, error-weighted, MSE-optimised and adaptive per-utterance routing; and the best routed four-model ensemble labels 807k unlabeled utterances that train a wav2vec 2.0 student. On URGENT the student reaches Spearman $ρ=0.802$ against $0.773$ for the best teacher. On mos260, a new Russian TTS benchmark of 4,600 utterances from 38 synthesis conditions, it reaches $ρ=0.636$ against $0.613$ per utterance and $0.95$ per condition, matching its own routed ensemble in one forward pass. Adaptive routing is the only rule that does not degrade when weak predictors are added. Model, ONNX exports and mos260 are released. It's about 950 characters; arXiv's limit is 1,920. I kept $ρ$ because arXiv renders it on the abstract page. If you'd rather avoid math, replace $ρ=0.802$ with rho = 0.802 and do the same for the other $...$ values.

We investigate whether predicted Mean Opinion Scores (MOS) can reliably support system-level comparisons of speech enhancement (SE) methods by introducing system-level preference accuracy (SPA). Although MOS prediction models are widely used to evaluate SE systems, their performance is typically assessed by correlation with human-rated MOS, which does not guarantee agreement on which system is better. SPA addresses this gap by directly evaluating whether predicted and human-rated MOS yield the same system preferences. Using SPA, we systematically evaluate three settings: single prediction models, ensembling, and domain adaptation. Through experiments, SPA varies substantially across single prediction models, from 9.4% to 76.8%. Even the best model disagrees with human judgments in approximately 23% of system comparisons. Ensembling yields only limited improvement, while domain adaptation tends to substantially improve SPA in the closed condition but brings only modest gains in the more practical open condition, where neither the target systems nor the speakers are known. These results suggest that SPA can reveal errors correlation-based evaluation alone does not expose, and that predicted MOS alone can lead to unreliable conclusions in practical SE system comparison.

Non-intrusive MOS predictors are widely used instead of subjective listening tests to evaluate and rank speech enhancement (SE) systems. If they accurately reflect perceived quality, raising their scores should lead to higher-quality speech. We present the first comprehensive analysis of test-time optimization for the SE task, which directly modifies the enhanced signal to raise the average of multiple MOS predictor scores. On seven systems from the URGENT 2026 challenge, we find that 1)~all the optimized predicted scores increase while reference-based metrics remain nearly unchanged, 2)~a non-optimized predicted score does not increase, and 3)~a MUSHRA listening test shows no improvement in perceived quality. These findings reveal a risk that such optimization can distort evaluations, e.g., biasing comparisons of SE systems regardless of their perceived quality. We believe these findings can inform future evaluation practices: they suggest that predictors used for optimization should not be used for evaluation, and that challenges should keep the predictors used for ranking undisclosed.

Full-consensus rates are often treated as indicators of collective cognition, yet depend on how participation and final states are operationalized. We replayed 100 held-out human Wason groups with matched large language model (LLM) agent groups, seeding one belief-anchored agent per participant's pre-discussion answer and scoring agents and people with the same code. Across human scoring definitions, estimates ranged from 24.0% to 57.0%; about one fifth of participants never posted, whereas agents almost always did. Agent groups remained more consensual in two post-unblinding sensitivity analyses: the submit-based comparison (n = 98) yielded gaps of 34.0 and 43.9 percentage points for chat and reasoning modes, and the participation-matched comparison (n = 45) yielded gaps of 34.1 and 44.4 points. These complementary routes reduced different measurement asymmetries yet converged within 0.5 percentage points. The gap persisted without early stopping and under a reparameterization removing the memorizable answer; reasoning-mode groups then agreed nearly unanimously, mostly on incorrect answers. Simulated consensus did not track collective accuracy, and belief-anchored agent groups were biased estimators of the human group-outcome distribution in this setting. These analyses provide a scoring-explicit basis for assessing simulated-group estimates of human deliberative outcomes.

Socially assistive robots (SARs) can support structured health and well-being interventions, but hardware and cost constraints limit interaction complexity and longitudinal real-world deployments. We present DART: Deployable Architecture for Robot-Mediated Tasks, an architecture that extends SARs through a web application and cloud infrastructure, enabling visual content, user input, remote computation, and persistent data storage synergistically with the robot's physical embodiment, speech, and movement. We evaluated DART by instantiating it in an interatively-developed full-stack HRI system for helping university students with elevated generalized anxiety to complete cognitive behavioral therapy (CBT) homework exercises. The resulting system, which used the low-cost open-source Blossom robot platform, was refined and evaluated through a participatory design process and multiple user studies, and finally evaluated in an in-lab study with 103 participants, and then a six-week in-home deployment with four participants. In the in-lab evaluation, participants showed significant within-session reductions in stress, state anxiety, and negative affect, and gave the platform a mean System Usability Scale score of 78.89. In the home deployment, the mean System Usability Scale score was 87.5, with positive qualitative feedback on usability. Participants across both groups identified speech input, visual presentation, and web-robot synchronization as priorities for improvement. These findings validate DART as an effective architecture for extending the capabilities of a low-cost SAR in both in-lab single-session and in real-world longitudinal deployments.

Speech Quality Assessment (SQA) is essential for modern speech technologies, and recent non-intrusive SQA predictors increasingly rely on Speech Foundation Models (SFMs). However, because SFMs expose representations from many layers, it remains unclear which depths are most informative for MOS prediction and how multi-layer information should be combined reliably across backbones and datasets. We benchmark ten SFMs on four MOS datasets under three regimes: full fine-tuning, last-layer probing with a frozen encoder, and naive cross-layer weighted aggregation. We find that the best layer is strongly backbone- and dataset-dependent, and that naive weighted fusion can be unstable across settings. We further evaluate a layer-calibrated aggregation variant that applies per-layer adapters before pooling, which improves the robustness of multi-layer fusion and narrows the gap to full fine-tuning while keeping the backbone frozen.

Mean Opinion Score (MOS) is the gold standard for evaluating synthesized speech naturalness. However, current automatic MOS predictors are dominated by self-supervised learning (SSL) models that prioritize high-level semantics, potentially compromising their ability to capture critical acoustic details. In this paper, we systematically investigate representations from three paradigms: SSLs, acoustic-only neural audio codecs (NACs), and unified NACs that integrate semantics into reconstruction-based architectures. Extensive benchmarking on the standard BVCC and multiple out-of-domain (OOD) datasets demonstrates that features synergizing semantic understanding with fine-grained acoustic modeling achieve a higher performance upper bound in speech quality assessment. Ultimately, our findings highlight that semantics alone are not enough; a dual focus on semantic content and acoustic fidelity is essential for robust MOS prediction.

Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive. We deconstruct "naturalness" into a linguistically grounded annotation schema spanning 10 distinct perceptual dimensions, and use it to construct the first dimension-level meta-evaluation benchmark for TTS, comprising 860 utterances annotated by trained linguist raters. Results from benchmarking four MOS predictors and four Audio-LLM judges reveal that MOS predictors collapse onto acoustic signal quality, while Audio-LLM judges show selective, prompt-dependent detection that does not generalise across all dimensions. Neither class reliably captures a breadth of linguistically structured speech errors. Our dataset, annotation schema, and evaluation code are publicly released to support more targeted and interpretable TTS evaluation.

Measuring neural audio synthesizers' performance is now routinely conducted using distribution based metrics such as the Fréchet Audio Distance (FAD). Although this metric can be correlated with human perception, it offers limited interpretability beyond ranking different approaches. In this paper, we introduce a deep neural timbre trait predictor composed of a pretrained audio neural embedding (CLAP), and a shallow learnable component. The latter is trained using the RWC musical instrument database and human judgments of 20 timbre descriptions (e.g., woody, percussive, rumbling, etc.) for 31 instruments. The resulting model shows strong correlation with average human ratings (r = 0.66, p < 0.001). We then demonstrate the benefit of this predictor for evaluating the performance of TokenSynth, a neural sound synthesizer. First, the Mean Absolute Error (MAE) computed over the set of generated sounds under different conditioning modalities of the model provides the same ranking as a FAD computed with the RWC database as a reference, suggesting that the proposed predictors are able to provide equivalent information on a distributional basis. Second, because the model is able to qualitatively analyze isolated sounds, we can determine which generated sounds could be improved and identify specific timbral dimensions that need adjustment.

Implicit neural representations (INRs) have recently emerged as a promising approach to video compression, delivering competitive rate-distortion performance alongside rapid decoding. However, existing neural video codecs struggle to balance complexity and scalability. Lightweight models often suffer from degraded compression performance when scaled to different bitrate/quality levels, whereas high-performance models exhibit limited scalability, as their model complexity typically increases with quality. This lack of a unified architecture capable of maintaining consistent complexity across a wide range of bitrates severely limits their diverse real-world deployment. To address these challenges, we introduce NVRC++, a novel INR-based video codec that utilizes a lightweight INR with multiple high-resolution feature grids, providing high scalability at any given complexity level. This is paired with an optimization framework that enables efficient overfitting on high-resolution grids for long video sequences, thereby exploiting spatio-temporal redundancies without prohibitive computational or memory overhead. Additionally, an advanced entropy model is designed for efficiently compressing the high-dimensional grid parameters. As a result, NVRC++ provides four complexity levels (from 7kMACs/pixel to 360kMACs/pixel), each spanning wide bitrate and quality ranges while supporting real-time decoding. The experimental results show that NVRC++ offers a much faster decoding speed (up to 7.6x) compared to the SOTA INR-based video codec, NVRC, while delivering comparable performance.

Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their training data. We study this quality gap for Khmer and Korean using VoxCPM2, a 2.4B parameter, tokenizer-free TTS model that joins a MiniCPM-4 language-model backbone with a flow-matching diffusion decoder. We build one shared, language-tagged corpus of 25.5 hours after cleaning and adapt VoxCPM2 with a single Low-Rank Adaptation (LoRA) adapter, trained on both languages at once and added to both the language model and the decoder. The adapter is zero-initialized, so training starts exactly at the original zero-shot model. In native-speaker listening tests, the Khmer Mean Opinion Score (MOS) rises from 3.85 to 4.23 with the best adapter, rank 64. This gain is highly significant under a paired Wilcoxon test with p < 0.001, and it is achieved while training only 0.19 to 3.03 percent of the parameters. Two findings stand out. First, the training loss and human ratings disagree on the best rank. The loss is lowest at rank 128, but MOS peaks at rank 64. Second, the same adapter gives no significant gain for Korean, which the base model already covers well, and a high rank even hurts quality. This shows that adaptation helps mainly where the base model is truly weak.

Voice reconstruction using Text-to-Speech (TTS) offers a communication method for people with speech disorders, which aims to retain their speaker identity while improving intelligibility. Previous work generally relies on Mean Opinion Score (MOS) to evaluate naturalness and speaker similarity, but this has limited sensitivity and reliability. We propose an evaluation framework with subjective and objective components. Subjectively, we evaluate perceived intelligibility and speaker identity using Best Worst Scaling (BWS) with situational framing. Objectively, we demonstrate that standard measures fail to predict reconstruction success for highly unintelligible speakers, so we introduce a novel dual-reference distributional measure to assess the trade-off between intelligibility and speaker identity. By evaluating the output of 17 zero-shot TTS systems for 193 speakers, we show that our framework provides a reliable and task-aligned approach for assessing voice reconstruction.

Mean opinion score (MOS) prediction models are widely used as proxy metrics in text-to-speech (TTS) research, yet their ability to capture quality differences beyond acoustic fidelity remains unclear. We investigate this via controlled perturbations on speech: acoustic degradation, prosodic errors, and manipulation of speaker-specific characteristics such as pitch and speaking rate. We obtained MOS predictions for these speech samples from both human listeners and the model, and analyzed the differences in their perceptual characteristics. Results show that most models track acoustic degradation well, while all are insensitive to prosodic errors despite large subjective score drops. For speaker characteristics, models exhibit a double dissociation: strong mean fundamental frequency (F0) biases absent in human ratings, yet insensitivity to speaking rate and F0 variability that humans notice. These findings highlight limitations of scalar MOS prediction beyond acoustic fidelity.

Mean opinion scores (MOS) are widely used for speech quality assessment, yet scalar labels are sensitive to rater variability and listening test differences. This introduces labeling noise, which limits the reliability of MOS prediction. Preference prediction reduces this variability as listeners compare signals directly, producing cleaner labels. We study MOS-free preference prediction and propose PrefSQA, which incorporates uncertainty-aware logits, an impairment attention head, and a module based on non-matching-reference comparisons. We use and refine five datasets, including MOS-derived and low-noise simulated sets with matching and non-matching content, experiment with human preference sets, and test on unseen data. Experiments show small improvements on MOS-derived data, while other sets reveal clear improvement over the baselines, highlighting the value of high-quality preference data and demonstrating the effectiveness of the proposed method.

Dysarthria is a speech disorder marked by reduced intelligibility and communicative effectiveness. Automatic utterance-level assessment of dysarthric speech can support scalable speech monitoring and therapy-related analysis. Yet training such systems is bottlenecked by the scarcity of clinically annotated dysarthric speech. This work proposes to augment dysarthric speech assessment using data from speech synthesis evaluations, specifically human-annotated utterances with Mean Opinion Score (MOS) labels from the QualiSpeech corpus. Experiments show that fine-tuning on speech synthesis assessment data consistently improves performance on both intelligibility and naturalness prediction, while joint training yields gains primarily on naturalness. These results suggest that synthesis artifacts and dysarthric speech share perceptual commonalities, and speech synthesis evaluation corpora offer a practical augmentation source that reduces reliance on scarce clinical annotations.

Evaluating text-to-music (TTM) systems remains expensive because music impression (MI) and text alignment (TA) scores rely on human mean opinion scores (MOS). Most automatic MOS estimators are trained with point-wise regression or distributional classification. These objectives do not directly optimize rank-based metrics and provide weak geometric constraints for cross-modal coherence. To address these gaps, we propose DeRA-MOS, a decoupled optimization framework for TTM evaluation. For MI, we introduce a batch-aware listwise ranking loss that models relative order within each mini-batch and better aligns with evaluation based on Spearman's rank correlation coefficient (SRCC). For TA, we introduce a score-anchored modality alignment loss that maps human scores to target audio-text similarity and regularizes the latent space before fusion. By effectively mitigating the point-wise training mismatch and modality drift, experiments on MusicEval demonstrate that our decoupled framework yields substantial improvements in both MI and TA ranking metrics, establishing a robust paradigm for large-scale TTM evaluation.

Point Cloud Quality Assessment (PCQA) methods typically predict scalar Mean Opinion Scores (MOS), which quantify overall perceptual degradation but do not reveal its causes. In contrast, human observers naturally reason in terms of specific distortions such as blur, color shifts, point density changes, missing regions, and geometric deformations. To close this gap, we introduce DAL-PCQA, a distortion-aware, language-annotated dataset for PCQA. DAL-PCQA augments benchmark point clouds with multi-level distortion severity labels, discrete quality categories, and structured natural language descriptions aligned with human perception. We define a point-cloud-specific distortion taxonomy that covers both photometric and geometric artifacts. Statistical analysis reveals characteristic degradation patterns across distortion types and quality levels. To assess the utility of these annotations, we compare zero-shot and fine-tuned multimodal models for generating perceptual quality descriptions. Experiments show that distortion-aware supervision substantially improves lexical and semantic alignment with ground-truth descriptions. By enabling interpretable, distortion-level reasoning, DAL-PCQA facilitates language-driven, explainable point cloud quality assessment. The dataset is publicly available at https://github.com/swarna96/DAL-PCQA.

Evaluating speech generation still relies heavily on human judgments, such as Mean Opinion Score (MOS), which are expensive, subjective, and difficult to reproduce at scale. While a few recent studies have begun to explore AudioLLM-based judge models, existing efforts typically target only a narrow set of scenarios (e.g., utterance-level quality or single-turn dialogue) and provide limited coverage of diverse speech generation tasks and evaluation dimensions. In this work, we propose UniSRM, a unified speech reward model that can support multi-dimensional, interpretable reward signals with reliable reasoning. To support training and evaluation, we introduce UniSRM-Data and UniSRM-Bench, covering speech evaluation tasks from utterance-level quality to context-level coherence. Based on this dataset, we present the unified speech reward model, UniSRM, with a two-stage pipeline that enables reasoning-based fine-grained assessment. Furthermore, we introduce Reasoning-Consistent Rewards to improve the reliability of the reasoning process. Experiments show that UniSRM delivers more reliable and human-aligned judgments across a broad range of speech evaluation tasks, offering a practical foundation for scalable and unified evaluation of speech quality.

Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a fix. Self-evolving agents have emerged in response, but all confine evolution to text-mutable artifacts -- skill files, prompt configurations, memory schemas, workflow graphs -- and leave the agent harness untouched. Since routing, hook ordering, state invariants, and dispatch live in code rather than in any text artifact, an entire class of structural failure is physically unreachable from the text layer. We argue that source-level adaptation is a fundamentally more general medium: it is Turing-complete, a strict superset of every text-mutable scope, takes effect deterministically rather than through base-model compliance, and does not erode under long-context drift. We present MOSS, a system that performs self-rewriting at the source level on production agentic substrates. Each evolution is anchored to an automatically curated batch of production-failure evidence and proceeds through a deterministic multi-stage pipeline; code modification is delegated to a pluggable external coding-agent CLI while MOSS retains stage ordering and verdicts. Candidates are verified by replaying the batch against the candidate image in ephemeral trial workers, then promoted via user-consent-gated, in-place container swap with health-probe-gated rollback. On OpenClaw, MOSS lifts a four-task mean grader score from 0.25 to 0.61 in a single cycle without human intervention.

Multimodal large language models (LLMs) are increasingly explored as automated evaluators in clinical settings, yet their scoring behavior on ordinal clinical scales remains poorly understood. We benchmark three frontier LLM families against supervised deep learning models for scoring Clock Drawing Test (CDT) images on two public datasets using the Shulman rubric. While fully fine-tuned Vision Transformers achieve the best calibration (MAE 0.52, within-1 accuracy 91%), zero-shot LLMs remain competitive on tolerance-based agreement (GPT-5 MAE 0.67, within-1 accuracy 92%) despite higher absolute error. However, per-score analysis reveals that all three LLM families exhibit a pronounced central tendency effect (systematic endpoint compression): predictions are systematically compressed toward the middle of the scale, with over-prediction at the low end (score 0 to 1) and under-prediction at the high end (score 5 to 4). This effect disproportionately affects the clinically critical extremes where accurate scoring most impacts screening decisions for cognitive impairment. Targeted ablations show that neither few-shot exemplars spanning the full score range nor removing clinical terminology from the prompt eliminates the effect. Our findings extend the LLM-as-a-judge bias literature from NLP evaluation to clinical assessment, and highlight the need for calibration-aware evaluation and post-hoc calibration before deploying LLM-based raters in high-stakes screening workflows.

Music popularity prediction has attracted growing research interest, with relevance to artists, platforms, and recommendation systems. However, the explosive rise of AI-generated music platforms has created an entirely new and largely unexplored landscape, where a surge of songs is produced and consumed daily without the traditional markers of artist reputation or label backing. Key, yet unexplored in this pursuit is aesthetic quality. We propose APEX, the first large-scale multi-task learning framework for AI-generated music, trained on over 211k songs (10k hours of audio) from Suno and Udio, that jointly predicts engagement-based popularity signals - streams and likes scores - alongside five perceptual aesthetic quality dimensions from frozen audio embeddings extracted from MERT, a self-supervised music understanding model. Aesthetic quality and popularity capture complementary aspects of music that together prove valuable: in an out-of-distribution evaluation on the Music Arena dataset, comprising pairwise human preference battles across eleven generative music systems unseen during training, including aesthetic features consistently improves preference prediction, demonstrating strong generalisation of the learned representations across generative architectures.

Traditional image quality assessment (IQA) methods rely on mean opinion scores (MOS), which are resource-intensive to collect and fail to provide interpretable, localized feedback on specific image distortions. We overcome these limitations by shifting from absolute quality prediction to a relational and directional assessment. Our approach utilizes a self-supervised synthetic distortion engine to generate training data, eliminating the need for manual annotation. A distortion prediction network is trained with an anti-symmetric objective to produce spatially-aware, disentangled maps that identify the type, intensity, and direction of distortions relative to a reference image. Subsequently, a scoring network is trained via contrastive learning on ordinally ranked image sets to predict a relational quality score. Our method provides a more granular and interpretable approach to IQA for the targeted optimization of image processing algorithms without requiring any human-labeled quality scores.

Training neural networks is difficult to interpret, particularly for newcomers. We introduce NeuroViz, an interactive visualization tool that supports real-time exploration of fully connected neural network training. Users can configure network architecture, activation functions, learning rates, and datasets, then observe activations, weight updates, and loss progression. NeuroViz visualizes weight changes in direct correspondence with activation signals in both forward and backward passes, enabling users to distinguish pre- and post-update states within individual epochs and view dynamically updating per-neuron equations. We conduct a comparative user study with 31 participants against six established visualization tools and we achieved the highest usability score (SUS 80.97, in the 'excellent' range), with mean rankings of 2.47 for clarity and 2.23 for usefulness (lower is better). Over 70% of participants reported that the visualizations substantially increased their perception of neural network training transparency. The implemented instance is accessible at https://neuroviz.org.

Rubric-based text evaluation increasingly relies on large language models (LLMs) as scalable judges, yet frozen black-box models can interpret the same criteria inconsistently, produce score attributions that are difficult to audit, and map judgments poorly onto human scoring scales. We define this challenge as criteria transfer: translating human rubric intent into a stable, auditable inference-time scoring protocol. We introduce Rulers, which locks a task-level rubric specification, executes it through structured, evidence-grounded judgments, and calibrates the resulting signals to human score boundaries. Across four rubric-governed benchmarks and multiple frozen backbone models, Rulers achieves stronger agreement with human scores in most evaluated settings, while better matching empirical score distributions and remaining more stable under semantically equivalent rubric perturbations. Calibration controls and component ablations show that these gains cannot be attributed to post-hoc alignment alone, but depend on the combination of fixed criteria, traceable evidence, and calibrated score interpretation. These findings suggest that reliable LLM judging requires faithfully operationalizing human evaluation standards rather than relying on prompt-level scoring alone. Our code is available at https://github.com/LabRAI/Rulers.git.