arXiv_SD
-
FXplorer: A Map-Based Interface for Exploratory Audio Effect Design
2026-06-06 18:14:41Annie Chu, Jason Brent Smith, Bryan PardoAbstract
Audio effects (FX) shape sound in contemporary music practice. However, most interfaces present them as discrete modules and parameters that favor targeted adjustment over exploratory listening. This separation can make it difficult to build intuition about the broader space of possible transformations or to move fluidly between searching and refinement. We present FXplorer, an interface that organizes audio effects within a perceptually informed 2D space, allowing sound transformations to be browsed as a continuous landscape rather than as isolated presets. By combining established spatial interaction approaches and interpretable DAW-style controls with recent embedding-based machine learning methods for similarity and semantic search, the system brings exploration and parameter refinement into a single workspace. FXplorer supports composition, production, or performance by allowing users to edit and interpolate between effect presets interactively.
Abstract (translated)
URL
https://arxiv.org/abs/2606.08286
PDF
-
Paediatric-HGNN: A Hybrid Heterogeneous Graph Neural Network for Detecting Disfluency in Children's Speech via Multiscale Acoustic Fusion
2026-06-06 14:54:44Rashini Liyanarachchi, Rachael Mackay, Alison Short, Aditya Joshi, Erik MeijeringAbstract
Automated stuttering detection (ASD) systems struggle with paediatric speech due to high acoustic variability in developing voices and the subtle distinction between pathological stuttering and typical developmental disfluencies. We introduce Paediatric-HGNN, a framework using a Context-aware Part-whole Interaction Network (CaPIN) tailored for paediatric data. Instead of conventional 1D signal modelling, our approach builds a heterogeneous graph capturing hierarchical relationships between lexical units (word nodes) and fine-grained acoustic segments (frame nodes). Trained on curated paediatric corpora (UCLASS and FluencyBank), Paediatric-HGNN achieves 82.4% weighted accuracy and a Typical Disfluency F1-score of 0.386. Modelling hierarchical lexical-acoustic interactions captures developmental "searching" behaviour, offering a more robust and interpretable tool for early clinical intervention.
Abstract (translated)
URL
https://arxiv.org/abs/2606.08210
PDF
-
Assessing the Energy and Carbon Emissions of Neural Speaker Verification Model in Training and Inference
2026-06-06 10:23:18Hugo Leguillier, Driss Matrouf, Guillaume Lechien, Mickael RouvierAbstract
Deep-learning speaker verification (SV) increasingly relies on deep neural network backbones, whose environmental impact remains largely undocumented. In this paper, we conduct an evaluation of ResNet architectures trained on VoxCeleb2, varying depth, channel width, and stage distribution, and measure energy consumption and carbon footprint using node-level sensors. Results show a clear point of diminishing returns: deeper or wider models bring only marginal accuracy gains while energy consumption grows steeply. In contrast, mid-sized networks such as ResNet-50 and stage-concentrated variants achieve favorable trade-offs between performance and environmental impact. These findings provide actionable guidelines for designing energy-efficient SV systems.
Abstract (translated)
URL
https://arxiv.org/abs/2606.08087
PDF
-
On Low-Bit Quantization Errors in Speaker Verification: Diagnostic and Mitigation
2026-06-06 09:55:37Hugo Leguillier, Driss Matrouf, Guillaume Lechien, Mickael RouvierAbstract
Although low-bit quantization provides practical means to deploy speaker verification on resource-constrained devices, its effects on speaker verification performance remain poorly understood. In this paper, we study uniform K-means quantization-aware training of ResNet-36 and ResNet-200 through joint layer-wise and score-level analyses. Our layer-wise analysis highlights fragile components and shows that score degradation is not fully explained by weight distortion alone. We identify a clear knee point at 2 bits, with larger score drift and harmful decision flips concentrated near the FP32 threshold. Our score-level analysis reveals where and how score errors emerge under extreme quantization. Building on these findings, we propose a calibrated multi-precision cascade that resolves most trials at 2 bits and escalates only ambiguous cases, achieving performance close to FP32 while preserving the efficiency benefits of low-bit inference with substantially lower compute and memory costs.
Abstract (translated)
URL
https://arxiv.org/abs/2606.08078
PDF
-
Exploring the Scale and Diversity of Speech Anti-spoofing Datasets: Experiments and Analysis
2026-06-06 07:58:02Zhuolin Yi, Jun Xue, Yanzhen Ren, Yihuan Huang, Yi Chai, Daixian Li, Guanxiang Feng, Jiajun LiuAbstract
The scale of speech anti-spoofing datasets has grown exponentially over the past decade, driven by the assumption that larger data leads to better performance. However, it remains unclear whether indiscriminate scaling commensurately improves model generalization. This study challenges the "scale-first" paradigm by decoupling the impacts of training data scale versus diversity. Through experiments on representative datasets, we report two key findings: (1) Larger is not always better. Expanding data scale excessively under fixed generation methods yields negligible returns and may even degrade cross-domain generalization due to overfitting.(2) Diversity outweighs scale. A smaller composite training set featuring diverse attacks significantly outperforms larger-scale datasets with limited diversity in cross-dataset evaluations. We conclude that future dataset construction should prioritize the diversity of generation methods over scale to effectively enhance model generalization.
Abstract (translated)
URL
https://arxiv.org/abs/2606.08038
PDF
-
Mitigating Proxy-to-Wild Domain Gap in Deepfake Speech
2026-06-05 17:48:46Xuanjun Chen, Yun-Shing Wu, Wei-Chung Lu, Claire Lin, Haibin Wu, Hung-yi Lee, Jyh-Shing Roger JangAbstract
Recent neural audio codec-based speech generation (CodecFake) produces highly realistic audio, posing a challenge to existing deepfake countermeasure models. While using codec resynthesized speech (CoRS) as proxy data improves performance, it often suffers from limited generalization. We propose Domain-Shift Feature Augmentation (DSFA), which simulates "in-the-wild" variations by transforming deterministic feature statistics into stochastic distributions during fine-tuning. To evaluate generalization, we further introduce Codec-based Speech Generation Extension Evaluation (CoSG ExtEval) dataset, a more challenging extension of the CoSG Eval (from CodecFake+) dataset, featuring 40 unseen generative models and long-form audio. Experimental results demonstrate that combining a post-trained SSL backbone with DSFA effectively narrows the proxy-to-wild domain gap. This approach achieves state-of-the-art performance across diverse CodecFake attacks in both CoSG Eval and CoSG ExtEval.
Abstract (translated)
URL
https://arxiv.org/abs/2606.07494
PDF
-
Audio-Oscar: A Multi-Agent System for Complex Audio Scene Generation, Orchestration, and Refinement
2026-06-05 15:38:08Yifan Duan, Qixiang Xu, Hengtao Wu, Zhanxun Liu, Wenhao Guan, Junxi Liu, Ziyang Ma, Kelu Xu, Xie ChenAbstract
In recent years, audio generation has made significant progress in tasks such as text-to-speech (TTS), text-to-audio (TTA) and text-to-music (TTM). However, generating long-form and controllable audio from complex audio scene descriptions remains a significant challenge, as such scenes often require coordinated speech, sound effects, music, songs, temporal structure, and post-production. In this work, we introduce \textbf{Audio-Oscar}, a multi-agent framework for generating audio from complex descriptions. Audio-Oscar coordinates a set of specialist agents, each responsible for a different aspect of the audio scene, including character modeling and voice design, speech generation, fine-grained timeline planning, model selection, non-speech generation, and audio post-production. Audio-Oscar further incorporates feedback-driven refinement. In addition, to address the lack of suitable benchmarks for evaluating audio generation from complex audio scene descriptions, we construct \textbf{ASG-Bench}, an Audio Scene Generation Benchmark containing both scene descriptions paired with reference audio and text-only scene descriptions. Each scene is annotated with target audio events and temporal statements to evaluate whether the generated audio faithfully realizes the required scene content and temporal structure. Experimental results show that Audio-Oscar can effectively generate audio that matches complex scene descriptions. Project samples are available at this https URL. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2606.07397
PDF
-
How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling
2026-06-05 14:49:24Jinju LeeAbstract
Harmony is a compact symbolic layer where mathematical pitch relations, acoustic consonance, and musical convention meet. This report treats chord-symbol sequences not as a complete representation of music, but as an interpretable, controllable time series for genre-local harmonic modeling. Starting from a frozen pop-jazz Music Transformer checkpoint, I evaluate how far small adaptation interfaces can extend the model to eleven target genres: blues, bossa nova, Bach chorales, country, electronic, folk, funk, gospel, hip-hop, R&B/soul, and rock. The main evaluation compares LoRA, IA3, BitFit, prefix tuning, and full fine-tuning over 11 genres and 3 seeds, a complete 165-cell grid. All five methods improve over the frozen base on held-out chord prediction, with macro gains from +2.89 to +3.61 points; LoRA and IA3 score highest, but Wilcoxon tests with Holm and Benjamini-Hochberg correction do not support a decisive winner. A matched-data-size control sharpens this: when genres are sub-sampled to a common corpus size, IA3 stays on top but LoRA's full-data edge disappears and it falls to last, indicating the small gaps are partly data-driven. A control-token baseline is also strong, and wrong-genre adapters often beat the frozen base, suggesting much of the effect comes from lightweight conditioning over a reusable harmonic base rather than one particular adapter family. Additional diagnostics (rank sweeps, wrong-genre rotation, a base-checkpoint ablation, chord-only genre classification, generated-output statistics, real-song evaluation, and duplicate analysis) support a bounded conclusion: chord-symbol adaptation reliably improves genre-local harmonic prediction, but chord symbols alone do not carry complete genre identity. The report therefore avoids claims about perceived genre authenticity or full musical quality, which require controlled listener or musician evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2606.07334
PDF
-
TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion
2026-06-05 14:05:19Constantin Alexander AugaAbstract
Speech Emotion Conversion (SEC) aims to transform the emotion of a source utterance into a target emotion while preserving content and speaker identity. SEC on in-the-wild data is challenging due to the non-parallel nature of training data and complex real-world acoustics. Existing fixed-duration approaches either struggle to shift the emotion effectively (high quality, low conversion) or degrade speech naturalness (low quality, high conversion). We propose TargetSEC, an embedding-driven latent diffusion framework that generates emotion-focused style embeddings conditioned on speaker identity and continuous emotion. Unlike methods that diffuse over spectrograms, TargetSEC operates in a compact latent space. Experiments on the MSP-Podcast dataset show that TargetSEC outperforms current non-duration baselines in conversion accuracy while maintaining high speech quality, and achieves performance comparable to duration-prediction systems without explicit temporal modeling.
Abstract (translated)
URL
https://arxiv.org/abs/2606.07293
PDF
-
Assessing True Generalisability of Audio-Visual Speech Recognisers
2026-06-05 13:35:10Zhaofeng Lin, Stavros Petridis, Maja Pantic, Naomi HarteAbstract
Current Audio-Visual Speech Recognition (AVSR) models achieve near-perfect performance on the standard LRS3 benchmark, raising concerns of adaptive overfitting. To systematically assess true generalisability, we construct a highly controlled, unseen evaluation set subsampled from the massive MultiVSR dataset. Unlike standard out-of-distribution benchmarks, our subset strictly matches the acoustic, visual, and demographic distributions of the LRS3 test set. Evaluating five state-of-the-art architectures reveals a universal performance collapse, proving that current systems fail to generalise even under strictly aligned conditions. Through a fine-grained attribute analysis across seven factors, we isolate the specific drivers of this degradation. Furthermore, we uncover a profound lexical bias, expose distinct error patterns, and surprisingly reveal that audio-visual performance even lags behind audio-only settings. We release our matched test set for future benchmarking.
Abstract (translated)
URL
https://arxiv.org/abs/2606.07259
PDF
-
A Large-Scale Per-Speaker Analysis of Re-identification Risk in Speech Anonymization
2026-06-05 12:21:25Orane Dufour, Paul Magron, Mickael Rouvier, Emmanuel VincentAbstract
Speech anonymization is commonly evaluated using averagecase metrics such as the equal error rate, which can hide large disparities in re-identification risks across individuals. In this paper, we conduct a large-scale per-speaker privacy analysis using a linkability-based metric under a worst-case scenario. Nearly 5,000 speakers are evaluated across multiple anonymization systems, attacker architectures, and conversation lengths. While linkability scores are highly polarized at the speaker level, the sets of easy to re-identify and hard to re-identify speakers vary substantially across configurations. We show that no single factor explains speaker vulnerability. Instead, the re-identification risk emerges from the interaction between the attacker, the anonymizer, and the amount of available speech. These results challenge the notion of intrinsic speaker-level privacy risks and emphasize the need for evaluation protocols that are explicitly conditioned on the attacker and anonymizer.
Abstract (translated)
URL
https://arxiv.org/abs/2606.07210
PDF
-
Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development
Abstract
Confidence-based loss weighting is usually avoided in generative models because it accelerates errors when the model is confidently wrong, but this intuition breaks down in supervised diffusion training. We introduce the Eisbach log-barrier, a parameter-free weight derived from the entropy of the DiT output's spatial energy distribution: high entropy damps the gradient, while low entropy preserves it. Applied to LoRA fine-tuning of Stable Audio 3 Medium on MusicCaps, it unexpectedly yields stronger thematic development, clearer acoustic differentiation, and higher textural diversity than unweighted training, the opposite of mode collapse. This works because in supervised diffusion the gradient direction is locked to ground truth, so confidence only scales the step size, and because temporal entropy downweights flat samples while preserving high-contrast ones. The result is an online, self-referential data curriculum that emerges purely from the forward pass, with analyzed noise-level dynamics and testable predictions.
Abstract (translated)
URL
https://arxiv.org/abs/2606.07207
PDF
-
MyGardenBird: A Machine-Learning-Ready Bird Sound Dataset for Twelve Common Malaysian Birds
2026-06-05 07:07:22Muhammad Mun'im Ahmad Zabidi, Mohd Yamani Idna Idris, Norisma IdrisAbstract
Bioacoustic datasets from tropical regions remain limited, in part due to the absence of reproducible workflows for aggregating recordings from public archives. We present \textbf{MyGardenBird}, a curated dataset of bird vocalisations representing twelve common species across Peninsular Malaysia and the Indo-Malayan region. Recordings were sourced from Xeno-canto and processed through species-level filtering, manual spectrogram segmentation, and quality control checks. The primary release comprises 7,200 manually validated audio clips (16 kHz, 16-bit PCM mono WAV), balanced at 600 three-second clips per species (6.0 hours total) derived from 1,381 distinct recordings. Metadata includes geospatial coordinates, vocalisation categories, and signal-to-noise ratio (SNR) values (range: 0.83--59.18 dB; mean: 15.80 dB). A supplementary 44.1 kHz version is also provided. To mitigate data leakage, dataset partitions are defined at the source-recording level. Baseline classification experiments using convolutional neural networks on Mel-spectrograms achieved test accuracies of 92--96\%, indicating strong interspecies separability. Limitations include reliance on single-annotator curation; however, validation with BirdNET confirmed label consistency. MyGardenBird is openly available at this https URL under a CC BY-NC-SA 4.0 licence. Complete preprocessing code accompanies the release to support reproducibility and future expansion.
Abstract (translated)
URL
https://arxiv.org/abs/2606.06975
PDF
-
Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models
2026-06-05 06:11:38Zhixian Zhao, Shuiyuan Wang, Wenjie Tian, Jingbin Hu, Ziyu Zhang, Lei XieAbstract
While Audio Language Models (ALMs) demonstrate strong semantic understanding, they struggle with complex affective interactions. Specifically, textual semantic dominance often overshadows acoustic nuances, and a lack of cognitive depth leads to generic, emotion-agnostic responses. We propose CogAudio-LLM\footnote{ \urlstyle{same} this https URL, a novel cognitive affective reasoning framework. To mitigate semantic dominance, we build LIME-440K, a ``lexically-identical, multi-emotion'' dataset designed to facilitate acoustic-semantic decoupling. We introduce EIPS, a 4-step Chain-of-Thought (CoT) mechanism incorporating psychological reasoning. For inference efficiency, multi-stage training explicitly establishes EIPS via supervised fine-tuning, then distills this logic into an implicit generation process. Finally, we design DR-SAPO (Dual-Route Soft Adaptive Policy Optimization) to dynamically balance the logical rigor of the CoT with the empathetic quality of the direct response.
Abstract (translated)
URL
https://arxiv.org/abs/2606.06940
PDF
-
VoxCPM2 Technical Report
2026-06-05 05:43:15Yixuan Zhou, Guoyang Zeng, Xin Liu, Xiang Li, Renjie Yu, Jiancheng Gui, Jiaheng Wu, Ziyang Wang, Xudong Shen, Runchuan Ye, Zhisheng Zhang, Jiuyang Zhou, Bingsong Bai, Weiyue Sun, Mengyuan Deng, Qundong Shi, Zhiyong Wu, Zhiyuan LiuAbstract
We present VoxCPM2, a https://info.arxiv.org/help/prep#abstractsfully open-source multilingual and controllable speech generation foundation model that extends the hierarchical diffusion-autoregressive modeling paradigm of VoxCPM. VoxCPM2 advances the framework in three key dimensions: (i) capability, by unifying 30 languages, 9 Chinese dialects, natural-language voice design, style-controllable voice cloning, and high-fidelity continuation cloning within a single backbone; (ii) quality, through an asymmetric AudioVAE that encodes at 16 kHz and reconstructs at 48 kHz, enabling implicit super-resolution with high encoding efficiency; and (iii) scale, by jointly scaling the model to 2B parameters and the training data to over 2 million hours of multilingual speech. To support these diverse capabilities within one model, we introduce a unified sequence organization that expresses all generation modes through different arrangements of the same input building blocks, allowing joint training under a single set of parameters and objective. VoxCPM2 achieves state-of-the-art or competitive performance on public zero-shot and instruction-following TTS benchmarks. On our internal 30-language evaluation set, it attains an average WER of 1.68%. These results demonstrate that hierarchical continuous-latent modeling, without relying on any external discrete speech tokenizer, offers a viable and powerful foundation for large-scale multilingual and controllable speech generation. The model weights, fine-tuning code, and inference tools are publicly released under the Apache 2.0 license to foster community research and development.
Abstract (translated)
URL
https://arxiv.org/abs/2606.06928
PDF
-
Towards Event-Robust Acoustic Scene Classification
2026-06-05 05:35:03Yiqiang Cai, Bohan Hu, Yu Yang, Pengwei Lu, Shengchen Li, Xi ShaoAbstract
This paper introduces the Event-Shifted Acoustic Scene (ESAS) dataset, a novel benchmark for evaluating the robustness of Acoustic Scene Classification (ASC) systems against unknown sound events. Existing ASC datasets typically contain recordings of clean and consistent audio, while real-world environments often include diverse and unexpected sound events. To bridge this gap, ESAS simulates real-world acoustic variability by injecting foreground sound events into background scenes with the assistance of large language models. In this work, we present the construction methodology, dataset statistics, and evaluation protocols. Furthermore, a comprehensive evaluation of state-of-the-art ASC systems is conducted using the ESAS benchmark. Experimental results reveal that existing ASC models suffer significant performance degradation when facing the event-shift challenge. The introduction of the ESAS dataset aims to drive future research toward event-robust ASC.
Abstract (translated)
URL
https://arxiv.org/abs/2606.06921
PDF
-
Leveraging Soft Distributions of SSL-Derived Discrete Speech Tokens for Downstream Inference
2026-06-05 01:14:12Kentaro Onda, Satoru Fukayama, Daisuke Saito, Nobuaki MinematsuAbstract
Discrete speech tokens obtained from self-supervised learning (SSL) models provide efficient data compression while maintaining strong performance, and have been widely used as intermediate representations in various tasks. However, discretization inevitably causes information loss, leading to degraded performance compared with continuous SSL features. In this work, we propose to apply soft token assignment only during downstream inference. This approach preserves the efficiency of hard discretization during training while enhancing the expressiveness of the tokens at inference. The proposed method outperforms conventional hard assignment on both ASR and speech synthesis tasks, and exhibits particularly strong generalizability to out-of-domain data. For ASR of non-native speech, it even surpasses models using continuous SSL features. Moreover, analysis of the resulting representations shows they align more accurately with phonemes compared with conventional hard assignment.
Abstract (translated)
URL
https://arxiv.org/abs/2606.06806
PDF
-
BiEAR: A Human Auditory-Inspired Adaptive Binaural Front-end for Multi-Speaker Localisation and Distance Estimation
2026-06-05 00:45:28Hanyu Meng, Eliathamby Ambikairajah, Vidhyasaharan Sethu, Qiquan Zhang, Haizhou LiAbstract
We present BiEAR, a human auditory-inspired adaptive binaural front-end for multi-speaker localisation and distance estimation. Inspired by medial olivocochlear (MOC) feedback in human hearing, BiEAR uses a neural controller to adaptively adjust the frequency selectivity of a binaural auditory filterbank during inference. This yields time-frequency adaptive representations for ears, enabling the model to respond to changing acoustic conditions. We evaluate BiEAR on multi-speaker localisation and distance estimation in anechoic and real-room environments. Results show that the adaptive front-end improves localisation accuracy and robustness to unseen speakers and rooms compared with commonly used fixed binaural front-ends. Visualisation and analysis of learned filter adaptations show that BiEAR emphasises informative frequency bands over time. These findings suggest that adaptive, biologically inspired binaural front-ends can improve machine hearing robustness in complex acoustic scenes.
Abstract (translated)
URL
https://arxiv.org/abs/2606.06795
PDF
-
A Hierarchical Feature Engineering Framework for Automated Classification of Phonotraumatic and Non-Phonotraumatic Vocal Hyperfunction
2026-06-04 17:39:33June-Woo Kim, Kangwook Jang, Minu Kim, Hyunju LeeAbstract
Ambulatory neck-surface acceleration enables non-invasive monitoring of vocal hyperfunction, yet robust biomarkers for its subtypes remain limited. This study investigates the NeckVibe Challenge dataset to distinguish phonotraumatic (PVH) and non-phonotraumatic (NPVH) from healthy controls. We propose a hierarchical feature engineering framework comprising: (i) static, (ii) dynamic, (iii) ratio-based, (iv) coupling features capturing source filter interactions. While univariate statistical analysis shows strong separability for PVH but limited significance for NPVH, our machine learning pipeline, tailored for high-dimensional feature integration, identifies that coupling features are crucial for both tasks. We achieve an AUC of 0.891 for PVH and 0.728 for NPVH, suggesting that while PVH is near-linearly separable, NPVH discrimination benefits from modeling non-linear feature interactions.
Abstract (translated)
URL
https://arxiv.org/abs/2606.07673
PDF
-
F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation
2026-06-04 16:25:07Dinghao Zhou, Xingchen Song, Di Wu, Pengyu Cheng, Shengfan Shen, Sixiang LvAbstract
Continuous audio autoencoders reconstruct waveforms well but often produce latents with weak structure for understanding, while self-supervised audio encoders capture semantics but are not directly decodable. This mismatch complicates a single audio tokenizer that must support both understanding and generation. We adapt continuous autoencoder latents to this setting with two components: a noise-regularized autoencoder bottleneck and a latent-side representation encoder. The bottleneck uses channel normalization and stochastic perturbation instead of KL-based variational training, yielding scale-controlled continuous latents for reconstruction and autoregressive generation. The representation encoder is trained on frozen autoencoder latents with RQ-MTP and frozen-LLM supervision. The resulting tokenizer provides high-dimensional representations for understanding while preserving normalized continuous latents as generation targets
Abstract (translated)
URL
https://arxiv.org/abs/2606.06357
PDF
