Speech
-
Enhancing time-frequency resolution with optimal transport and barycentric fusion of multiple spectrogram
2026-04-16 14:23:59David Valdivia, Elsa Cazelles, C\'edric F\'evotteAbstract
Time-frequency representations, such as the short-time Fourier transform (STFT), are fundamental tools for analyzing non-stationary signals. However, their ability to achieve sharp localization in both time and frequency is inherently limited by the Gabor-Heisenberg uncertainty principle. In this paper, we address this limitation by introducing a method to generate super-resolution spectrograms through the fusion of two or more spectrograms with varying resolutions. Specifically, we compute the super-resolution spectrogram as the barycenter of input spectrograms using optimal transport (OT) divergences. Unlike existing fusion approaches, our method does not require the input spectrograms to share the same time-frequency grid. Instead, the input spectrograms can be computed using any STFT parameters, and the resulting super-resolution spectrogram can be defined on an arbitrary user-specified grid. We explore various OT divergences based on different transportation costs. Notably, we introduce a novel transportation cost that preserves time-frequency geometry while significantly reducing computational complexity compared to standard Wasserstein barycenters. We adopt the unbalanced OT framework and derive a new block majorization-minimization algorithm for efficient barycenter computation. We validate the proposed method on controlled synthetic signals and recorded speech using both quantitative and qualitative evaluations. The results show that our approach combines the best localization properties of the input spectrograms and outperforms an unsupervised state-of-the-art fusion method.
Abstract (translated)
URL
https://arxiv.org/abs/2604.15055
PDF
-
Explain the Flag: Contextualizing Hate Speech Beyond Censorship
2026-04-16 13:06:28Jason Liartis, Eirini Kaldeli, Lambrini Gyftokosta, Eleftherios Chelioudakis, Orfeas Menis MastromichalakisAbstract
Hate, derogatory, and offensive speech remains a persistent challenge in online platforms and public discourse. While automated detection systems are widely used, most focus on censorship or removal, raising concerns for transparency and freedom of expression, and limiting opportunities to explain why content is harmful. To address these issues, explanatory approaches have emerged as a promising solution, aiming to make hate speech detection more transparent, accountable, and informative. In this paper, we present a hybrid approach that combines Large Language Models (LLMs) with three newly created and curated vocabularies to detect and explain hate speech in English, French, and Greek. Our system captures both inherently derogatory expressions tied to identity characteristics and direct group-targeted content through two complementary pipelines: one that detects and disambiguates problematic terms using the curated vocabularies, and one that leverages LLMs as context-aware evaluators of group-targeting content. The outputs are fused into grounded explanations that clarify why content is flagged. Human evaluation shows that our hybrid approach is accurate, with high-quality explanations, outperforming LLM-only baselines.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14970
PDF
-
Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task
2026-04-16 11:49:13Evaldas Vaiciukynas, Paulius Danenas, Linas Ablonskis, Algirdas Sukys, Edgaras Dambrauskas, Voldemaras Zitkus, Rita Butkiene, Rimantas ButlerisAbstract
Online hate speech and abusive language pose a growing challenge for content moderation, especially in multilingual settings and for low-resource languages such as Lithuanian. This paper investigates to what extent modern multilingual sentence embedding models can support accurate hate speech detection in Lithuanian, Russian, and English, and how their performance depends on downstream modeling choices and feature dimensionality. We introduce LtHate, a new Lithuanian hate speech corpus derived from news portals and social networks, and benchmark six modern multilingual encoders (potion, gemma, bge, snow, jina, e5) on LtHate, RuToxic, and EnSuperset using a unified Python pipeline. For each embedding, we train both a one class HBOS anomaly detector and a two class CatBoost classifier, with and without principal component analysis (PCA) compression to 64-dimensional feature vectors. Across all datasets, two class supervised models consistently and substantially outperform one class anomaly detection, with the best configurations achieving up to 80.96% accuracy and AUC ROC of 0.887 in Lithuanian (jina), 92.19% accuracy and AUC ROC of 0.978 in Russian (e5), and 77.21% accuracy and AUC ROC of 0.859 in English (e5 with PCA). PCA compression preserves almost all discriminative power in the supervised setting, while showing some negative impact for the unsupervised anomaly detection case. These results demonstrate how modern multilingual sentence embeddings combined with gradient boosted decision trees provide robust soft-computing solutions for multilingual hate speech detection applications.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14907
PDF
-
Listen, Pause, and Reason: Toward Perception-Grounded Hybrid Reasoning for Audio Understanding
2026-04-16 09:30:13Jieyi Wang, Yazhe Niu, Dexuan Xu, Zhongyu WeiAbstract
Recent Large Audio Language Models have demonstrated impressive capabilities in audio understanding. However, they often suffer from perceptual errors, while reliable audio reasoning is unattainable without first grounding the model's perception in structured auditory scenes. Inspired by Auditory Scene Analysis, we first introduce a Perception-Aware Question Answering (PAQA) dataset. PAQA implements a hierarchical decoupling strategy that separates speech from environmental sound and distinguishes multiple speakers, providing explicit perceptual reasoning for training. Building on this, we propose HyPeR, a two-stage Hybrid Perception-Reasoning framework. In Stage I, we finetune the model on PAQA to perceive acoustic attributes in complex audio. In Stage II, we leverage GRPO to refine the model's internal deliberation. We also introduce PAUSE tokens to facilitate latent computation during acoustically ambiguous phases and design perceptual consistency reward to align reasoning rationales with raw audio. Experiments across benchmarks demonstrate that HyPeR achieves absolute improvements over the base model, with performance comparable to large-scale models, stressing the effectiveness of hybrid perception-grounded reasoning for robust and multi-speaker audio understanding.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14806
PDF
-
ClariCodec: Optimising Neural Speech Codes for 200bps Communication using Reinforcement Learning
2026-04-16 06:01:46Junyi Wang, Chi Zhang, Jing Qian, Haifeng Luo, Hao Wang, Zengrui Jin, Chao ZhangAbstract
In bandwidth-constrained communication such as satellite and underwater channels, speech must often be transmitted at ultra-low bitrates where intelligibility is the primary objective. At such extreme compression levels, codecs trained with acoustic reconstruction losses tend to allocate bits to perceptual detail, leading to substantial degradation in word error rate (WER). This paper proposes ClariCodec, a neural speech codec operating at 200 bit per second (bps) that reformulates quantisation as a stochastic policy, enabling reinforcement learning (RL)-based optimisation of intelligibility. Specifically, the encoder is fine-tuned using WER-driven rewards while the acoustic reconstruction pipeline remains frozen. Even without RL, ClariCodec achieves 3.68% WER on the LibriSpeech test-clean set at 200 bps, already competitive with codecs operating at higher bitrates. Further RL fine-tuning reduces WER to 3.20% on test-clean and 8.93% on test-other, corresponding to a 13% relative reduction while preserving perceptual quality.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14654
PDF
-
The Acoustic Camouflage Phenomenon: Re-evaluating Speech Features for Financial Risk Prediction
Abstract
In computational paralinguistics, detecting cognitive load and deception from speech signals is a heavily researched domain. Recent efforts have attempted to apply these acoustic frameworks to corporate earnings calls to predict catastrophic stock market volatility. In this study, we empirically investigate the limits of acoustic feature extraction (pitch, jitter, and hesitation) when applied to highly trained speakers in in-the-wild teleconference environments. Utilizing a two-stream late-fusion architecture, we contrast an acoustic-based stream with a baseline Natural Language Processing (NLP) stream. The isolated NLP model achieved a recall of 66.25% for tail-risk downside events. Surprisingly, integrating acoustic features via late fusion significantly degraded performance, reducing recall to 47.08%. We identify this degradation as Acoustic Camouflage, where media-trained vocal regulation introduces contradictory noise that disrupts multimodal meta-learners. We present these findings as a boundary condition for speech processing applications in high-stakes financial forecasting.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14619
PDF
-
VoxSafeBench: Not Just What Is Said, but Who, How, and Where
2026-04-16 02:24:59Yuxiang Wang, Hongyu Liu, Yijiang Xu, Qinke Ni, Li Wang, Wan Lin, Kunyu Feng, Dekun Chen, Xu Tan, Lei Wang, Jie Shi, Zhizheng WuAbstract
As speech language models (SLMs) transition from personal devices into shared, multi-user environments, their responses must account for far more than the words alone. Who is speaking, how they sound, and where the conversation takes place can each turn an otherwise benign request into one that is unsafe, unfair, or privacy-violating. Existing benchmarks, however, largely focus on basic audio comprehension, study individual risks in isolation, or conflate content that is inherently harmful with content that only becomes problematic due to its acoustic context. We introduce VoxSafeBench, among the first benchmarks to jointly evaluate social alignment in SLMs across three dimensions: safety, fairness, and privacy. VoxSafeBench adopts a Two-Tier design: Tier1 evaluates content-centric risks using matched text and audio inputs, while Tier2 targets audio-conditioned risks in which the transcript is benign but the appropriate response hinges on the speaker, paralinguistic cues, or the surrounding environment. To validate Tier2, we include intermediate perception probes and confirm that frontier SLMs can successfully detect these acoustic cues yet still fail to act on them appropriately. Across 22 tasks with bilingual coverage, we find that safeguards appearing robust on text often degrade in speech: safety awareness drops for speaker- and scene-conditioned risks, fairness erodes when demographic differences are conveyed vocally, and privacy protections falter when contextual cues arrive acoustically. Together, these results expose a pervasive speech grounding gap: current SLMs frequently recognize the relevant social norm in text but fail to apply it when the decisive cue must be grounded in speech. Code and data are publicly available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2604.14548
PDF
-
Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars
2026-04-16 02:16:36Yicheng Gong, Jiawei Zhang, Liqiang Liu, Yanwen Wang, Lei Chu, Jiahao Li, Hao Pan, Hao Zhu, Yan LuAbstract
We present a framework for explicit emotion control in feed-forward, single-image 3D head avatar reconstruction. Unlike existing pipelines where emotion is implicitly entangled with geometry or appearance, we treat emotion as a first-class control signal that can be manipulated independently and consistently across identities. Our method injects emotion into existing feed-forward architectures via a dual-path modulation mechanism without modifying their core design. Geometry modulation performs emotion-conditioned normalization in the original parametric space, disentangling emotional state from speech-driven articulation, while appearance modulation captures identity-aware, emotion-dependent visual cues beyond geometry. To enable learning under this setting, we construct a time-synchronized, emotion-consistent multi-identity dataset by transferring aligned emotional dynamics across identities. Integrated into multiple state-of-the-art backbones, our framework preserves reconstruction and reenactment fidelity while enabling controllable emotion transfer, disentangled manipulation, and smooth emotion interpolation, advancing expressive and scalable 3D head avatars.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14541
PDF
-
Diffusion Language Models for Speech Recognition
2026-04-15 15:46:15Davyd Naveriani, Albert Zeyer, Ralf Schl\"uter, Hermann NeyAbstract
Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and parallel text generation. In this work, we explore variants for their use in speech recognition. Specifically, we introduce a comprehensive guide to incorporating masked diffusion language models (MDLM) and uniform-state diffusion models (USDMs) for rescoring ASR hypotheses. Additionally, we design a new joint-decoding method that combines CTC and USDM by integrating the framewise probability distributions derived from CTC with the labelwise probability distributions computed by USDM at each decoding step, thereby generating new candidates that combine strong language knowledge from USDM and acoustic information from CTC. Our findings reveal that USDM, as well as MDLM, can significantly improve the accuracy of recognized text. We publish all our code and recipes.
Abstract (translated)
URL
https://arxiv.org/abs/2604.14001
PDF
-
Syn-TurnTurk: A Synthetic Dataset for Turn-Taking Prediction in Turkish Dialogues
2026-04-15 08:39:26Ahmet Tu\u{g}rul Bayrak, Mustafa Serta\c{c} T\"urkel, Fatma Nur KorkmazAbstract
Managing natural dialogue timing is a significant challenge for voice-based chatbots. Most current systems usually rely on simple silence detection, which often fails because human speech patterns involve irregular pauses. This causes bots to interrupt users, breaking the conversational flow. This problem is even more severe for languages like Turkish, which lack high-quality datasets for turn-taking prediction. This paper introduces Syn-TurnTurk, a synthetic Turkish dialogue dataset generated using various Qwen Large Language Models (LLMs) to mirror real-life verbal exchanges, including overlaps and strategic silences. We evaluated the dataset using several traditional and deep learning architectures. The results show that advanced models, particularly BI-LSTM and Ensemble (LR+RF) methods, achieve high accuracy (0.839) and AUC scores (0.910). These findings demonstrate that our synthetic dataset can have a positive affect for models understand linguistic cues, allowing for more natural human-machine interaction in Turkish.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13620
PDF
-
Few-Shot and Pseudo-Label Guided Speech Quality Evaluation with Large Language Models
2026-04-15 06:23:20Ryandhimas E. Zezario, Dyah A. M. G. Wisnu, Szu-Wei Fu, Sabato Marco Siniscalchi, Hsin-Min Wang, Yu TsaoAbstract
In this paper, we introduce GatherMOS, a novel framework that leverages large language models (LLM) as meta-evaluators to aggregate diverse signals into quality predictions. GatherMOS integrates lightweight acoustic descriptors with pseudo-labels from DNSMOS and VQScore, enabling the LLM to reason over heterogeneous inputs and infer perceptual mean opinion scores (MOS). We further explore both zero-shot and few-shot in-context learning setups, showing that zero-shot GatherMOS maintains stable performance across diverse conditions, while few-shot guidance yields large gains when support samples match the test conditions. Experiments on the VoiceBank-DEMAND dataset demonstrate that GatherMOS consistently outperforms DNSMOS, VQScore, naive score averaging, and even learning-based models such as CNN-BLSTM and MOS-SSL when trained under limited labeled-data conditions. These results highlight the potential of LLM-based aggregation as a practical strategy for non-intrusive speech quality evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13528
PDF
-
Listening Alone, Understanding Together: Collaborative Context Recovery for Privacy-Aware AI
2026-04-14 23:18:06Tanmay Srivastava, Amartya Basu, Shubham Jain, Vaishnavi RanganathanAbstract
We introduce CONCORD, a privacy-aware asynchronous assistant-to-assistant (A2A) framework that leverages collaboration between proactive speech-based AI. As agents evolve from reactive to always-listening assistants, they face a core privacy risk (of capturing non-consenting speakers), which makes their social deployment a challenge. To overcome this, we implement CONCORD, which enforces owner-only speech capture via real-time speaker verification, producing a one-sided transcript that incurs missing context but preserves privacy. We demonstrate that CONCORD can safely recover necessary context through (1) spatio-temporal context resolution, (2) information gap detection, and (3) minimal A2A queries governed by a relationship-aware disclosure. Instead of hallucination-prone inferring, CONCORD treats context recovery as a negotiated safe exchange between assistants. Across a multi-domain dialogue dataset, CONCORD achieves 91.4% recall in gap detection, 96% relationship classification accuracy, and 97% true negative rate in privacy-sensitive disclosure decisions. By reframing always-listening AI as a coordination problem between privacy-preserving agents, CONCORD offers a practical path toward socially deployable proactive conversational agents.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13348
PDF
-
SEDTalker: Emotion-Aware 3D Facial Animation Using Frame-Level Speech Emotion Diarization
2026-04-14 22:55:09Farzaneh Jafari, Stefano Berretti, Anup BasuAbstract
We introduce SEDTalker, an emotion-aware framework for speech-driven 3D facial animation that leverages frame-level speech emotion diarization to achieve fine-grained expressive control. Unlike prior approaches that rely on utterance-level or manually specified emotion labels, our method predicts temporally dense emotion categories and intensities directly from speech, enabling continuous modulation of facial expressions over time. The diarized emotion signals are encoded as learned embeddings and used to condition a speech-driven 3D animation model based on a hybrid Transformer-Mamba architecture. This design allows effective disentanglement of linguistic content and emotional style while preserving identity and temporal coherence. We evaluate our approach on a large-scale multi-corpus dataset for speech emotion diarization and on the EmoVOCA dataset for emotional 3D facial animation. Quantitative results demonstrate strong frame-level emotion recognition performance and low geometric and temporal reconstruction errors, while qualitative results show smooth emotion transitions and consistent expression control. These findings highlight the effectiveness of frame-level emotion diarization for expressive and controllable 3D talking head generation.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13335
PDF
-
Giving Voice to the Constitution: Low-Resource Text-to-Speech for Quechua and Spanish Using a Bilingual Legal Corpus
2026-04-14 20:32:29John E. Ortega, Rodolfo Zevallos, Fabricio CarraroAbstract
We present a unified pipeline for synthesizing high-quality Quechua and Spanish speech for the Peruvian Constitution using three state-of-the-art text-to-speech (TTS) architectures: XTTS v2, F5-TTS, and DiFlow-TTS. Our models are trained on independent Spanish and Quechua speech datasets with heterogeneous sizes and recording conditions, and leverage bilingual and multilingual TTS capabilities to improve synthesis quality in both languages. By exploiting cross-lingual transfer, our framework mitigates data scarcity in Quechua while preserving naturalness in Spanish. We release trained checkpoints, inference code, and synthesized audio for each constitutional article, providing a reusable resource for speech technologies in indigenous and multilingual contexts. This work contributes to the development of inclusive TTS systems for political and legal content in low-resource settings.
Abstract (translated)
URL
https://arxiv.org/abs/2604.13288
PDF
-
MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models
2026-04-14 16:17:52Chung-Ming Chien, Manu Orsini, Eugene Kharitonov, Neil Zeghidour, Karen Livescu, Alexandre D\'efossezAbstract
Speech-to-speech language models have recently emerged to enhance the naturalness of conversational AI. In particular, full-duplex models are distinguished by their real-time interactivity, including handling of pauses, interruptions, and backchannels. However, improving their factuality remains an open challenge. While scaling the model size could address this gap, it would make real-time inference prohibitively expensive. In this work, we propose MoshiRAG, a modular approach that combines a compact full-duplex interface with selective retrieval to access more powerful knowledge sources. Our asynchronous framework enables the model to identify knowledge-demanding queries and ground its responses in external information. By leveraging the natural temporal gap between response onset and the delivery of core information, the retrieval process can be completed while maintaining a natural conversation flow. With this approach, MoshiRAG achieves factuality comparable to the best publicly released non-duplex speech language models while preserving the interactivity inherent to full-duplex systems. Moreover, our flexible design supports plug-and-play retrieval methods without retraining and demonstrates strong performance on out-of-domain mathematical reasoning tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12928
PDF
-
When Does Data Augmentation Help? Evaluating LLM and Back-Translation Methods for Hausa and Fongbe NLP
2026-04-14 10:14:58Mahounan Pericles Adjovi, Roald Eiselen, Prasenjit MitraAbstract
Data scarcity limits NLP development for low-resource African languages. We evaluate two data augmentation methods -- LLM-based generation (Gemini 2.5 Flash) and back-translation (NLLB-200) -- for Hausa and Fongbe, two West African languages that differ substantially in LLM generation quality. We assess augmentation on named entity recognition (NER) and part-of-speech (POS) tagging using MasakhaNER 2.0 and MasakhaPOS benchmarks. Our results reveal that augmentation effectiveness depends on task type rather than language or LLM quality alone. For NER, neither method improves over baseline for either language; LLM augmentation reduces Hausa NER by 0.24% F1 and Fongbe NER by 1.81% F1. For POS tagging, LLM augmentation improves Fongbe by 0.33% accuracy, while back-translation improves Hausa by 0.17%; back-translation reduces Fongbe POS by 0.35% and has negligible effect on Hausa POS. The same LLM-generated synthetic data produces opposite effects across tasks for Fongbe -- hurting NER while helping POS -- suggesting task structure governs augmentation outcomes more than synthetic data quality. These findings challenge the assumption that LLM generation quality predicts augmentation success, and provide actionable guidance: data augmentation should be treated as a task-specific intervention rather than a universally beneficial preprocessing step.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12540
PDF
-
X-VC: Zero-shot Streaming Voice Conversion in Codec Space
2026-04-14 08:42:10Qixi Zheng, Yuxiang Zhao, Tianrui Wang, Wenxi Chen, Kele Xu, Yikang Li, Qinyuan Chen, Xipeng Qiu, Kai Yu, Xie ChenAbstract
Zero-shot voice conversion (VC) aims to convert a source utterance into the voice of an unseen target speaker while preserving its linguistic content. Although recent systems have improved conversion quality, building zero-shot VC systems for interactive scenarios remains challenging because high-fidelity speaker transfer and low-latency streaming inference are difficult to achieve simultaneously. In this work, we present X-VC, a zero-shot streaming VC system that performs one-step conversion in the latent space of a pretrained neural codec. X-VC uses a dual-conditioning acoustic converter that jointly models source codec latents and frame-level acoustic conditions derived from target reference speech, while injecting utterance-level target speaker information through adaptive normalization. To reduce the mismatch between training and inference, we train the model with generated paired data and a role-assignment strategy that combines standard, reconstruction, and reversed modes. For streaming inference, we further adopt a chunkwise inference scheme with overlap smoothing that is aligned with the segment-based training paradigm of the codec. Experiments on Seed-TTS-Eval show that X-VC achieves the best streaming WER in both English and Chinese, strong speaker similarity in same-language and cross-lingual settings, and substantially lower offline real-time factor than the compared baselines. These results suggest that codec-space one-step conversion is a practical approach for building high-quality low-latency zero-shot VC systems. Audio samples are available at this https URL. Our code and checkpoints will also be released.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12456
PDF
-
On the Distillation Loss Functions of Speech VAE for Unified Reconstruction, Understanding, and Generation
2026-04-14 07:17:55Changhao Cheng, Wei Wang, Wangyou Zhang, Dongya Jia, Jian Wu, Zhuo Chen, Yanmin QianAbstract
Continuous speech representations based on Variational Autoencoders (VAEs) have emerged as a promising alternative to traditional spectrogram or discrete token based features for speech generation and reconstruction. Recent research has tried to enrich the structural information in VAE latent representations by aligning with self-supervised learning (SSL) features, aiming for better generation performance. However, it remains unclear whether the widely-used alignment approach based on time-axis distillation is optimal when considering more tasks. To address this problem, this paper systematically explores different alignment approaches and analyzes their impact on the performances over three axes: reconstruction, understanding, and generation. We investigate various design choices in the distillation loss. Extensive experiments show that the joint-marginal alignment approach with adaptive weighting can achieve the best overall performance while allowing for a controllable balance.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12383
PDF
-
CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing
2026-04-14 05:03:57Gaoxiang Cong, Liang Li, Jiaxin Ye, Zhedong Zhang, Hongming Shan, Yuankai Qi, Qingming HuangAbstract
Movie dubbing aims to synthesize speech that preserves the vocal identity of a reference audio while synchronizing with the lip movements in a target video. Existing methods fail to achieve precise lip-sync and lack naturalness due to explicit alignment at the duration level. While implicit alignment solutions have emerged, they remain susceptible to interference from the reference audio, triggering timbre and pronunciation degradation in in-the-wild scenarios. In this paper, we propose a novel flow matching-based movie dubbing framework driven by the Cognitive Synchronous Diffusion Transformer (CoSync-DiT), inspired by the cognitive process of professional actors. This architecture progressively guides the noise-to-speech generative trajectory by executing acoustic style adapting, fine-grained visual calibrating, and time-aware context aligning. Furthermore, we design the Joint Semantic and Alignment Regularization (JSAR) mechanism to simultaneously constrain frame-level temporal consistency on the contextual outputs and semantic consistency on the flow hidden states, ensuring robust alignment. Extensive experiments on both standard benchmarks and challenging in-the-wild dubbing benchmarks demonstrate that our method achieves the state-of-the-art performance across multiple metrics.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12292
PDF
-
The Enforcement and Feasibility of Hate Speech Moderation on Twitter
2026-04-14 05:01:55Manuel Tonneau, Dylan Thurgood, Diyi Liu, Niyati Malhotra, Victor Orozco-Olvera, Ralph Schroeder, Scott A. Hale, Manoel Horta Ribeiro, Paul R\"ottger, Samuel P. FraibergerAbstract
Online hate speech is associated with substantial social harms, yet it remains unclear how consistently platforms enforce hate speech policies or whether enforcement is feasible at scale. We address these questions through a global audit of hate speech moderation on Twitter (now X). Using a complete 24-hour snapshot of public tweets, we construct representative samples comprising 540,000 tweets annotated for hate speech by trained annotators across eight major languages. Five months after posting, 80% of hateful tweets remain online, including explicitly violent hate speech. Such tweets are no more likely to be removed than non-hateful tweets, with neither severity nor visibility increasing the likelihood of removal. We then examine whether these enforcement gaps reflect technical limits of large-scale moderation systems. While fully automated detection systems cannot reliably identify hate speech without generating large numbers of false positives, they effectively prioritize likely violations for human review. Simulations of a human-AI moderation pipeline indicate that substantially reducing user exposure to hate speech is economically feasible at a cost below existing regulatory penalties. These results suggest that the persistence of online hate cannot be explained by technical constraints alone but also reflects institutional choices in the allocation of moderation resources.
Abstract (translated)
URL
https://arxiv.org/abs/2604.12289
PDF
