arXiv_SD
-
Delayed Commitment for Representation Readiness in Stage-wise Audio-Visual Learning
2026-05-03 02:03:32Xinmeng Xu, Haoran Xie, S. Joe Qin, Lin Li, Xiaohui Tao, Fu Lee WangAbstract
Stage-wise audio-visual encoders propagate fused intermediate states across layers, making the formation of later representations depend on the readiness of earlier fusion states. Strong local audio-visual agreement provides useful correspondence evidence, yet a fused state also needs sufficient cross-layer and cross-modal support before it can reliably guide later fusion. This paper studies this issue through propagation-aware representation readiness and formulates premature perceptual commitment as a readiness-deficiency problem, where local plausibility, propagation influence, and support insufficiency jointly appear at an intermediate stage. We propose the Delayed Perceptual Commitment Network (DPC-Net), an encoder-level framework that estimates an observable readiness-deficiency surrogate, localizes the intervention-sensitive bottleneck, and applies support-aware correction with cross-layer and cross-modal evidence. DPC-Net preserves task-specific heads, losses, decoding modules, and evaluation protocols, making it applicable to different audio-visual tasks through encoder-side intervention. Experiments on audio-visual speech separation, audio-visual event localization, and audio-visual speech recognition show consistent improvements across reconstruction, localization, and recognition regimes. Further analyses on component contribution, selection criteria, counterfactual intervention, and readiness trajectories support the effectiveness of readiness-guided bottleneck correction.
Abstract (translated)
URL
https://arxiv.org/abs/2605.01673
PDF
-
Toward Fair Speech Technologies: A Comprehensive Survey of Bias and Fairness in Speech AI
2026-05-02 20:11:12Yi-Cheng Lin, Yun-Shao Tsai, Kuan-Yu Chen, Hsiao-Ying Huang, Huang-Cheng Chou, Hung-yi LeeAbstract
Speech technologies are deployed in high-stakes settings, yet fairness concerns remain fragmented across tasks and disciplines. Existing surveys either adopt a general machine-learning perspective that overlooks speech-specific properties or focus on a single task, missing failure patterns shared across the speech domain. Synthesizing over 400 studies spanning generation and perception tasks and emerging speech-language models, this survey presents a unified framework that links formal fairness definitions to evaluation, diagnosis, and mitigation. We formalize seven fairness definitions adapted to the speech modality and organize the field's conceptual evolution through three paradigms: Robustness, Representation, and Governance. We then ground evaluation metrics in the mathematical cores of these definitions and offer a decision tree for metric selection. We diagnose bias sources along the speech processing pipeline, surfacing speech-specific mechanisms such as channel bias as a demographic proxy and annotation subjectivity in emotion labels. We systematize mitigation strategies across four intervention stages, mapping each to the diagnosed sources. Finally, we identify open challenges and propose directions for future research.
Abstract (translated)
URL
https://arxiv.org/abs/2605.01597
PDF
-
MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech
2026-05-02 16:07:12Yutong Jin, Qi Li, Lingshuang Liu, Jianbing NiAbstract
In this paper, we propose MelShield, a robust, in-generation, keyed audio watermarking framework that embeds identifiable signals into AI-generated audio for copyright protection and reliable attribution. Specifically, MelShield operates in the Mel-spectrogram domain during the generation process, targeting intermediate acoustic representations in Mel-conditioned pipelines for text-to-speech (TTS) generation. The core idea is to treat the intermediate Mel-spectrogram as the host signal and embed a short binary payload via low-energy, keyed spread-spectrum perturbations distributed across carefully selected time-frequency regions prior to waveform synthesis. By performing watermarking before vocoder inference, MelShield remains plug-and-play for Mel-conditioned TTS architectures and does not require modification or retraining of the underlying TTS generation vocoder, such as DiffWave and HiFi-GAN. Moreover, the multi-user keyed construction enables scalable user-specific attribution, while the keyed verification mechanism limits unauthorized decoding, thereby reducing the risk of large-scale extractor probing and adversarial analysis. Extensive experiments on DiffWave and HiFi-GAN demonstrate that MelShield achieves reliable watermark extraction, approaching 100\% bit accuracy, even under signal distortions, e.g., compression and additive noise, while preserving high perceptual audio quality.
Abstract (translated)
URL
https://arxiv.org/abs/2605.01515
PDF
-
MindMelody: A Closed-Loop EEG-Driven System for Personalized Music Intervention
2026-05-02 04:15:32Yimeng Zhang, Yueru Sun, Haoyu GuAbstract
Driven by the escalating global burden of mental health conditions, music-based interventions have attracted significant attention as a non-invasive, cost-effective modality for emotion regulation and psychological stress relief. However, current digital music services rely on static preferences and fail to adapt to users' instantaneous psychological states. Furthermore, directly mapping electroencephalography (EEG) to music generation remains challenging due to severe paired-data scarcity and a lack of interpretability. To address these limitations, we propose MindMelody, a fully functional, closed-loop real-time system for EEG-driven personalized music intervention. MindMelody introduces an emotion-mediated semantic bridge. Specifically, a hybrid Transformer-GNN first decodes real-time EEG signals into global Valence-Arousal states and local temporal affect trajectories. These states are then fed into a Retrieval-Augmented Generation (RAG)-equipped Large Language Model (LLM) to formulate structured intervention plans. Subsequently, a novel Hierarchical EEG Controller injects global affect prefixes and local temporal guidance into a pretrained music backbone, enabling fine-grained controllable audio synthesis. Crucially, the system incorporates a continuous feedback loop that updates generation parameters on the fly based on the user's evolving EEG dynamics. Extensive experiments show that MindMelody improves control adherence and emotional alignment, and receives higher perceived helpfulness in a short-term listening setting, suggesting its promise as an adaptive affect-aware music generation framework.
Abstract (translated)
URL
https://arxiv.org/abs/2605.01235
PDF
-
MG-Former: A Transformer-Based Framework for Music-Driven 3D Conducting Gesture Generation
2026-05-02 02:18:29Ke Qiu, Yawen Qin, Tianzhi Jia, Xiaole Yang, Kaimin Wang, Kaixing YangAbstract
Generating expressive conducting gestures from music is a challenging cross-modal motion synthesis problem: the output must follow long-range musical structure, preserve beat-level synchronization, and remain plausible as a fine-grained 3D human performance. Existing conducting-motion studies are often limited by sparse pose representations, small-scale data, or evaluation protocols that do not directly measure whether music and gesture are mutually aligned. This paper presents TransConductor, a Transformer-based framework for music-driven conducting gesture generation. We introduce ConductorMotion, a SMPL-parameter data construction pipeline that recovers detailed body motion from conducting videos and forms a dataset targeted at professional conducting gestures. Given acoustic descriptors extracted from audio and an initial pose, TransConductor uses a Trans-Temporal Music Encoder and a Trans-Temporal Conducting Gesture Decoder to autoregressively predict SMPL pose parameters. To better assess artistic correspondence, we further build a retrieval-based evaluation model that embeds music and gestures into a shared space and yields FID, modality distance, multi-modality distance, and diversity metrics. Experiments show that TransConductor outperforms dance-generation and conducting-generation baselines, while ablations verify the benefits of the Transformer backbone and the proposed alignment loss.
Abstract (translated)
URL
https://arxiv.org/abs/2605.01197
PDF
-
BioSEN: A Bio-acoustic Signal Enhancement Network for Animal Vocalizations
2026-05-02 00:19:24Tianyu Song, Ton Viet Ta, Ngamta Thamwattana, Hisako Nomura, Linh Thi Hoai NguyenAbstract
Most work in audio enhancement targets human speech, while bioacoustics is less studied due to noisy recordings and the distinct traits of animal sounds. To fill this gap, we adapt speech enhancement methods and build BioSEN, a model made for bioacoustic signals. BioSEN has three modules: a multi-scale dual-axis attention unit for time-frequency feature extraction, a bio-harmonic multi-scale enhancement unit for capturing harmonic structures, and an energy-adaptive gating connection unit that uses frequency weights to keep vocalizations from being removed as noise. Tests on three bioacoustic datasets show that BioSEN matches or exceeds state-of-the-art speech enhancement models while using far less computation. These results show BioSEN's strength for bioacoustic audio enhancement and its promise for biodiversity monitoring and conservation.
Abstract (translated)
URL
https://arxiv.org/abs/2605.12534
PDF
-
AsymK-Talker: Real-Time and Long-Horizon Talking Head Generation via Asymmetric Kernel Distillation
2026-05-01 16:38:06Yuxin Lu, Qian Qiao, Jiayang Sun, Min Cao, Guibo ZhuAbstract
Recent advances in diffusion models have markedly enhanced the visual fidelity of audio-driven talking head generation. Nevertheless, existing methods are constrained by three critical limitations: causal inefficiency that impedes real-time inference, incompatibility with temporally coherent conditioning, and progressive drift over long-horizon generation, collectively hindering their deployment in real-time applications. To overcome these challenges, we introduce AsymK-Talker, a novel diffusion-distillation method designed for real-time and long-horizon talking head generation. AsymK-Talker comprises three key components: (1) Kernel-Conditioned Loop Generation (KCLG), a causal, chunk-wise generation paradigm that leverages motion kernels to enable temporally consistent propagation; (2) Temporal Reference Encoding (TRE), which converts a static identity reference into a time-aware latent representation to enhance audio-visual synchronization; and (3) Asymmetric Kernel Distillation (AKD), a teacher-student distillation framework wherein the teacher model conditions on ground-truth motion kernels for supervision, while the student learns to generate from generated kernels, thereby ensuring robustness during extended generation sequences. AsymK-Talker achieves promising results on both visual fidelity and lip synchronization metrics.
Abstract (translated)
URL
https://arxiv.org/abs/2605.02948
PDF
-
Towards Improving Speaker Distance Estimation through Generative Impulse Response Augmentation
2026-05-01 15:08:42Anton Ratnarajah, Mehmet Ergezer, Arun Nair, Mrudula AthiAbstract
The Room Acoustics and Speaker Distance Estimation (SDE) Challenge at ICASSP 2025 explores the effectiveness of augmented room impulse response (RIR) data for improving SDE model performance. This challenge at GenDARA involves generating RIRs to supplement sparse datasets and fine-tuning SDE models with the augmented data. We employ the open-source fast diffuse room impulse response generator (FastRIR) conditioned only on speaker and listener locations. We design a quality filter to ensure generated RIR alignment with challenge RIRs, and hyperparameter optimization is employed for model fine-tuning. Our approach reduces the mean absolute error (MAE) of the five positions from 1.66m to 0.6m for GWA rooms and from 2.18m to 0.69m for Treble rooms, with results demonstrating that the augmentation approach significantly improves estimation accuracy, particularly at medium to long distances.
Abstract (translated)
URL
https://arxiv.org/abs/2605.00721
PDF
-
MMAudio-LABEL: Audio Event Labeling via Audio Generation for Silent Video
2026-05-01 08:09:06Kazuya Tateishi, Akira Takahashi, Atsuo Hiroe, Hirofumi Takeda, Shusuke Takahashi, Yuki MitsufujiAbstract
Recent advances in multimodal generation have enabled high-quality audio generation from silent videos. Practical applications, such as sound production, demand not only the generated audio but also explicit sound event labels detailing the type and timing of sounds. One straightforward approach involves applying a standard sound event detection to the generated audio. However, this post-hoc pipeline is inherently limited, as it is prone to error accumulation. To address this limitation, we propose MMAudio-LABEL (LAtent-Based Event Labeling), an event-aware audio generation framework built on a foundational audio generation model as its backbone that jointly generates audio and frame-aligned sound event predictions from silent videos. We evaluate our method on the Greatest Hits dataset for onset detection and 17-class material classification. Our approach improves onset-detection accuracy from 46.7% to 75.0% and material-classification accuracy from 40.6% to 61.0% over baselines. These results suggest that jointly learning audio generation and event prediction enables a more interpretable and practical video-to-audio synthesis.
Abstract (translated)
URL
https://arxiv.org/abs/2605.00495
PDF
-
MMAudioReverbs: Video-Guided Acoustic Modeling for Dereverberation and Room Impulse Response Estimation
2026-05-01 06:06:56Akira Takahashi, Ryosuke Sawata, Shusuke Takahashi, Yuki MitsufujiAbstract
Although recent video-to-audio (V2A) models excelled at synthesizing semantically plausible sounds from visual inputs, they do not explicitly model room-acoustic effects such as reverberation or room impulse responses (RIRs), and thus offer limited controllability over these effects. However, we hypothesize that such V2A models implicitly have semantic knowledge of the relationship between spatial audio and the corresponding vision cues. In this paper, we revisit a V2A model for the sake of the above, and propose the way to utilize the pretrained model as prior for physically grounded room-acoustic processing. Based on one of the state-of-the-art V2A models, MMAudio, we propose MMAudioReverbs that is a unified framework dealing with i) dereverberation and ii) room impulse response (RIR) estimation without network architectural modification, and fine-tuned on a small dataset. Experimental results showed that audio and visual cues respectively have advantage depending on the type of physical room acoustics. It implies that foundation V2A models can be used for physically grounded room-acoustic analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2605.00431
PDF
-
GaMMA: Towards Joint Global-Temporal Music Understanding in Large Multimodal Models
2026-05-01 03:21:57Zuyao You, Zhesong Yu, Mingyu Liu, Bilei Zhu, Yuan Wan, Zuxuan WuAbstract
In this paper, we propose GaMMA, a state-of-the-art (SoTA) large multimodal model (LMM) designed to achieve comprehensive musical content understanding. GaMMA inherits the streamlined encoder-decoder design of LLaVA, enabling effective cross-modal learning between music and language. By incorporating audio encoders in a mixture-of-experts manner, GaMMA effectively unifies both time-series and non-time-series music understanding tasks within one set of parameters. Our approach combines carefully curated datasets at scale with a progressive training pipeline, effectively pushing the boundaries of music understanding via pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL). To comprehensively assess both temporal and non-temporal capability of music LMMs, we introduce MusicBench, the largest music-oriented benchmark, comprising 3,739 human-curated multiple-choice questions covering diverse aspects of musical understanding. Extensive experiments demonstrate that GaMMA establishes new SoTA in the music domain, achieving 79.1% accuracy on MuchoMusic, 79.3% on MusicBench-Temporal, and 81.3% on MusicBench-Global, consistently outperforming previous methods.
Abstract (translated)
URL
https://arxiv.org/abs/2605.00371
PDF
-
Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation
2026-05-01 01:13:50Kuan-Po Huang, Bo-Ru Lu, Byeonggeun Kim, Mihee Lee, Zalan Fabian, Renard Korzeniowski, Qingming Tang, Greg Ver Steeg, Hung-yi Lee, Chieh-Chi Kao, Chao WangAbstract
Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a one-step sampling framework that combines an energy-distance training objective with representation-level distillation. An energy-scoring head maps Gaussian noise directly to audio latents in one step, eliminating the need for a costly recursive diffusion sampling process, while distillation from a masked autoregressive (MAR) text-to-audio model preserves the strong conditioning learned during diffusion training. On the AudioCaps benchmark, our method consistently outperforms prior one-step baselines such as ConsistencyTTA, SoundCTM, AudioLCM and AudioTurbo, on both objective and subjective metrics, while substantially narrowing the quality gap to AR diffusion systems with multi-step sampling. Compared to the state-of-the-art AR diffusion system, IMPACT, our approach achieves up to $8.5$x faster batch inference with highly competitive audio quality. These results demonstrate that combining energy-distance training with representation-level distillation provides an effective recipe for fast, high-quality text-to-audio synthesis.
Abstract (translated)
URL
https://arxiv.org/abs/2605.00329
PDF
-
From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings
2026-04-30 21:00:05Christiaan M. Geldenhuys, Thomas R. NieslerAbstract
We show that pretrained acoustic embeddings classify elephant vocalisations at a level approaching that of end-to-end supervised neural networks, without any fine-tuning of the embedding model. This result is of practical importance because annotated bioacoustic data are scarce and costly to obtain, leaving conventional supervised approaches prone to overfitting and to poor generalisation under domain shift. A broad range of embedding models drawn from general audio, speech, and bioacoustic domains is evaluated, all of which are either out-of-domain (containing no bioacoustic data) or out-of-species (containing no elephant call data). The embedding networks themselves remain fixed; only the lightweight downstream classifiers, which include a linear model and several small neural networks, are trained. Among the models considered, Perch 2.0 achieves the best cross-validated classification performance, attaining AUCs of 0.849 on African bush elephant (Loxodonta africana) calls and 0.936 on Asian elephant (Elephas maximus) calls, with Perch 1.0 close behind. The best-performing system is within 2.2 % of an end-to-end supervised elephant call classification system. A layerwise analysis of pretrained transformer encoders, considered as embedding models, shows that intermediate representations outperform final-layer outputs. The second layer of both wav2vec2.0 and HuBERT encodes sufficient information for effective elephant call classification; truncation at this layer therefore preserves classification performance whilst retaining only approximately 10 % of the parameters of the full network. Such compact embedding networks are well suited to on-device processing where computational resources are limited.
Abstract (translated)
URL
https://arxiv.org/abs/2605.00225
PDF
-
LRS-VoxMM: A benchmark for in-the-wild audio-visual speech recognition
2026-04-30 13:50:10Doyeop Kwak, Jeongsoo Choi, Suyeon Lee, Joon Son ChungAbstract
We introduce LRS-VoxMM, an in-the-wild benchmark for audio-visual speech recognition (AVSR). The benchmark is derived from VoxMM, a dataset of diverse real-world spoken conversations with human-annotated transcriptions. We select AVSR-suitable samples and preprocess them in an LRS-style format for direct use in existing AVSR pipelines. Compared with commonly used benchmarks, LRS-VoxMM covers a more diverse range of scenarios and acoustic conditions. We also release distorted evaluation sets with additive noise, reverberation, and bandwidth limitation to support evaluation under severe acoustic degradation. Experimental results show that LRS-VoxMM is considerably harder than LRS3 and that the contribution of visual information becomes more evident as the audio signal degrades. LRS-VoxMM supports more realistic AVSR benchmarking and encourages further research on the role of visual information in challenging real-world conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2604.27866
PDF
-
Accent Conversion: A Problem-Driven Survey of Sociolinguistic and Technical Constraints
2026-04-30 00:32:14Yurii Halychanskyi, Jianfeng Steven Guo, Volodymyr KindratenkoAbstract
Accent conversion has rapidly progressed alongside growing interest in improving global cross-cultural communication. This survey presents an overview of the evolution of accent conversion methodologies, analyzing how the field has developed in response to fundamental challenges related to data alignment, representation disentanglement, and resource scarcity. We trace the progression from early rule-based digital signal processing approaches such as spectral manipulation and formant-based analysis to modern neural architectures capable of flexible and reference-free accent transformation. In addition, the survey situates accent conversion within its linguistic foundations and examines how different application requirements impose varying constraints on the balance between accent modification and speaker identity preservation. Finally, it reviews commonly used speech datasets and evaluation methodologies, identifies persistent challenges, and outlines directions for future research aimed at achieving more controllable and perceptually consistent accent conversion.
Abstract (translated)
URL
https://arxiv.org/abs/2604.27281
PDF
-
Predicting Upcoming Stuttering Events from Three-Second Audio: Stratified Evaluation Reveals Severity-Selective Precursors, and the Model Deploys Fully On-Device
Abstract
Audio-based stuttering systems to date have been trained for detection -- what disfluency is present now -- leaving prediction, the capability needed for closed-loop intervention, unstudied at deployable scale. We train a 616K-parameter CNN on SEP-28k (Apple, 20,131 three-second clips) to predict whether the next contiguous clip contains any disfluency. (1) Severity-selective precursor signal: on the episode-grouped test set, aggregate preblock AUC is modest (0.581 [0.542, 0.619]), but stratifying by upcoming event type reveals concentration on clinically severe events -- blocks 0.601 [0.554, 0.651] and sound repetitions 0.617 [0.567, 0.667] both exclude chance, while fillers (0.45) and word repetitions (0.49) are at chance. The aggregate objective converges to a severity-selective predictor because severe events carry prosodic precursors; fillers do not. (2) Cross-population transfer: without fine-tuning, the same checkpoint applied to 1,024 pediatric Children-Who-Stutter utterances (FluencyBank Teaching) attains AUC 0.674 detection and 0.655 prediction; DisfluencySpeech and LibriStutter reach 0.58-0.60 AUC. (3) Deployable on-device: lossless export to CoreML (1.19 MB), ONNX (40 KB), TFLite. Neural-Engine latency per 3 s window: 0.25 ms (iPhone 17 Pro Max, A19 Pro) to 0.55 ms (iPhone SE 3rd-gen and M1 Max). A 4 Hz streaming simulation uses 0.54% of the real-time budget. Platt-calibrated outputs (test ECE 0.010, from 0.177 raw). Five negative ablations -- output-level Future-Guided Learning, multi-clip GRU, time-axis concatenation, asymmetric focal loss, direct block-targeted training -- none improved over the vanilla baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2604.27279
PDF
-
Few-Shot Accent Synthesis for ASR with LLM-Guided Phoneme Editing
2026-04-30 00:05:03Yurii Halychanskyi, Nimet Beyza Bozdag, Mark Hasegawa-Johnson, Dilek Hakkani-T\"ur, Volodymyr KindratenkoAbstract
Accented automatic speech recognition (ASR) often degrades due to the limited availability of accented training data. Prior work has explored accent modeling in low-resource settings, but existing approaches typically require minutes to hours of labeled speech, which may still be impractical for truly scarce accent scenarios. We propose a pipeline that adapts a text-to-speech (TTS) decoder to a target-accent speaker using fewer than ten reference utterances and employs large language model (LLM)-based phoneme editing to generate accent-conditioned pronunciations. The resulting synthetic speech is used to fine-tune a self-supervised ASR model. Experiments demonstrate consistent word error rate (WER) reductions on real accented speech, including cross-speaker evaluation and ultra-low data regimes. A matched-rate random phoneme baseline shows that phoneme-space perturbation itself is a strong form of augmentation, while LLM-guided edits provide additional gains through accent-conditioned structure.
Abstract (translated)
URL
https://arxiv.org/abs/2604.27273
PDF
-
Full band denoising of room impulse response in the wavelet domain with dictionary learning
2026-04-29 13:38:03Th\'eophile Dupr\'e, Romain Couderc, Miguel Moleron, Axel Coulon, R\'emy Bruno, Arnaud LaborieAbstract
Conventional wavelet-domain methods for room impulse response denoising rely on thresholding detail coefficients, which is unsuited for low frequencies. In this work, we introduce a wavelet-based post-processing algorithm that extends denoising to approximation coefficients by means of sparse dictionary learning with a time-varying error tolerance. The proposed method leverages an exponential decay envelope model to adapt reconstruction accuracy according to the local signal-to-noise ratio. This approach significantly improves low-frequency denoising of synthetic and measured room impulse responses compared to the baseline method, leading to more accurate estimation of acoustic parameters such as decay time.
Abstract (translated)
URL
https://arxiv.org/abs/2604.26669
PDF
-
Diffusion Reconstruction towards Generalizable Audio Deepfake Detection
2026-04-29 09:21:26Bo Cheng, Songjun Cao, Xiaoming Zhang, Jie Chen, Long Ma, Fei ChenAbstract
Achieving robust generalization against unseen attacks remains a challenge in Audio Deepfake Detection (ADD), driven by the rapid evolution of generative models. To address this, we propose a framework centered on hard sample classification. The core idea is that a model capable of distinguishing challenging hard samples is inherently equipped to handle simpler cases effectively. We investigate multiple reconstruction paradigms, identifying the diffusion-based method as optimal for generating hard samples. Furthermore, we leverage multi-layer feature aggregation and introduce a Regularization-Assisted Contrastive Learning (RACL) objective to enhance generalizability. Experiments demonstrate the superior generalization of our approach, with our best model achieving a significant reduction in the average Equal Error Rate (EER) compared to the baseline.
Abstract (translated)
URL
https://arxiv.org/abs/2604.26465
PDF
-
DiffAnon: Diffusion-based Prosody Control for Voice Anonymization
2026-04-29 04:22:59Ismail Rasim Ulgen, Zexin Cai, Nicholas Andrews, Philipp Koehn, Berrak SismanAbstract
To preserve or not to preserve prosody is a central question in voice anonymization. Prosody conveys meaning and affect, yet is tightly coupled with speaker identity. Existing methods either discard prosody for privacy or lack a principled mechanism to control the utility-privacy trade-off, operating at fixed design points. We propose DiffAnon, a diffusion-based anonymization method with classifier-free guidance (CFG) that provides explicit, continuous inference-time control over prosody preservation. DiffAnon refines acoustic detail over semantic embeddings of an RVQ codec, enabling smooth interpolation between anonymization strength and prosodic fidelity within a single model. To the best of our knowledge, it is the first voice anonymization framework to provide structured, interpolatable inference-time prosody control. Experiments demonstrate structured trade-off behavior, achieving strong utility while maintaining competitive privacy across controllable operating points.
Abstract (translated)
URL
https://arxiv.org/abs/2604.26281
PDF
