arXiv_SD
-
NeuMark: Neural Codec Resynthesis-Robust Audio Watermarking in the Codec Latent Space
2026-09-22 05:47:51Annan Wu, Wen-Chin Huang, Tomoki TodaAbstract
Audio watermarking is increasingly important for tracing generated speech. Several audio watermarking methods have been proposed to embed the watermark in various domains, such as waveform, timbre feature, or latent representations, for making the embedded watermark robust against traditional digital signal processing (DSP) attacks. On the other hand, modern neural codecs introduce a different threat from DSP attacks: they resynthesize speech through quantized acoustic representations and can remove the embedded watermark evi- dence that is not aligned with codec-preserved structure. In this paper, we propose NeuMark, a codec-latent audio watermarking framework that embeds watermark evidence into SpeechTok- enizer acoustic tokens to address this resynthesis threat. NeuMark uses cross-attention to inject a 16-bit message across residual vector quantization (RVQ) layers, distributing the watermark over codec-aligned latent structure. Experimental results show that NeuMark substantially improves robustness under neural- codec resynthesis while supporting both watermark detection and message recovery. We also analyze the trade-off between reconstruction-referenced transparency and original-referenced robustness.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25719
PDF
-
Interactive TTS: Dynamic Speaking Style Adaptation for Expressive Speech Synthesis
2026-09-22 05:25:02Wenjie Tian, Kangxiang Xia, Jingbin Hu, Xinfa Zhu, HangRui Hu, Ziyue Jiang, Kexin Huang, Ting He, Lei Xie, Jin XuAbstract
Dynamic speaking style adaptation in multi-turn multimodal interaction remains a major challenge for text-to-speech (TTS) systems. Existing context-aware TTS (CTTS) methods typically map dialogue context to speech in an end-to-end manner. Such implicit modeling makes contextual style decisions difficult to supervise, while the entanglement of style, timbre, and content often leads to weak instruction-following and severe timbre drift across turns. To overcome these limitations, we propose Interactive TTS, a dynamic, style-adaptive framework for contextually appropriate and speaker-consistent speech generation. Interactive TTS decouples the process by explicitly modeling contextual style decisions as executable instructions. To bridge the gap between style decisions and speech generation, we introduce Iterative Rejection Sampling Fine-Tuning (Iterative RSFT) and Context-Aware Direct Preference Optimization (CADPO), which significantly enhance instruction-following and align the generated speech with conversational contexts. Extensive experiments demonstrate that Interactive TTS outperforms state-of-the-art models on VStyle and SpeechParaling-Bench. Demo is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2609.25707
PDF
-
SRF-SVB: Style-Consistent Singing Voice Beautifying via Rectified Flow
2026-09-22 03:07:36Wenhui Li, Biao Dong, Liwei Hu, Jiqing Han, Yongjun HeAbstract
Singing voice beautifying (SVB) aims to correct pitch and rhythm of amateur singing while enhancing vocal quality, preserving lyrics and the singer's timbre. Existing methods, however, suffer from limited generation quality and efficiency, and tend to neglect the preservation of the singer's style. We propose SRF-SVB, a style-consistent model for SVB via rectified flow, which achieves high-fidelity and efficient beautification covering pitch and rhythm correction. Furthermore, we design a context-guided masked mel-spectrogram inpainting mechanism that effectively preserves the amateur singer's style, including unique timbre and expressive patterns. Experiments on both English and Chinese test sets show that SRF-SVB outperforms baseline models in most objective and subjective metrics.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25610
PDF
-
Synthesis and editing of multi-instrument audio mixtures using scalar-quantised latents with MIDI Span conditioning
2026-09-22 01:21:39Sungkyun Chang, Keshav Bhandari, Simon Dixon, Emmanouil BenetosAbstract
Music creation often involves iterative refinement, changing selected musical details while retaining the rest. To support such refinement, we introduce SpanSynth-Edit, a flow-matching model for MIDI-guided synthesis and editing of multi-instrument audio mixtures using low-frame-rate scalar-quantised latents. MIDI Span encodes instrument-labelled note lifecycles as unordered event sets with continuous-valued attributes and pools each set into one conditioning vector per audio-latent frame. The model uses contextual audio for instrument-specific timbre guidance and supports editing by resynthesising the target region from revised MIDI. Experiments on single- and multi-instrument benchmarks show competitive performance and demonstrate within-frame onset control. We also discuss limitations of transcription-based note-adherence evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25546
PDF
-
Narrowband Voice Communication Using Streaming Neural Compression
2026-09-21 20:22:26Dahong Luo, Anannya Trehan, Aritrik Ghosh, Nirupam RoyAbstract
Low-bitrate speech communication on resource-constrained edge devices remains challenging due to stringent computational, memory, and bandwidth constraints. We present TinyCall, a lightweight neural audio codec designed for real-time speech communication on low-power platforms such as the ESP32 microcontroller and Raspberry Pi. The proposed system targets emergency communication and other bandwidth-limited scenarios while preserving speech intelligibility, speaker identity, and vocal expressiveness. To enable efficient deployment, we propose a minimal neural audio codec architecture together with a framework for converting a causally trained codec into a truly streamable codec through pseudo-lookahead decoding and decoder-input caching. We further replace conventional residual vector quantization (RVQ) with Residual Finite Scalar Quantization (RFSQ) to reduce inference complexity on edge processors and employ a progressive three-stage training strategy for stable optimization under latent quantization. An MFCC-based perceptual loss encourages preservation of speaker characteristics, including harmonic structure and vocal timbre. Experimental results demonstrate real-time operation on a Raspberry Pi 3 while achieving intelligible speech reconstruction at bitrates as low as 2.3 kbps. The proposed approach demonstrates that practical neural speech communication is feasible on highly resource-constrained edge devices.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25379
PDF
-
Automated Assessment of L2 Speech Rhythm Using Low-Frequency Amplitude Modulations
Abstract
Automated Speaking Assessment of non-native speech must effectively evaluate prosody, including speech rhythm, to align with human perception. However, commonly employed rhythm metrics rely on segmental duration, requiring an additional alignment step, which is error-prone in non-native speech containing disfluencies and mispronunciations. We propose an acoustics-based assessment approach that employs a convolutional neural network to extract rhythm features directly from the speech amplitude envelope, motivated by evidence linking low-frequency modulations to rhythm perception. The proposed models are trained on a proficiency score regression task using the speechocean762 dataset and compared against duration-based models. Our results show that a model using the amplitude envelope's first derivative achieves the highest correlation with human-assigned scores on the Fluency and Prosody dimensions, producing significantly lower errors than one using segment durations among less fluent speakers. The findings support acoustic envelope features as robust, alignment-free alternatives for L2 rhythm assessment. Code is released publicly.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24818
PDF
-
Fast Time-Varying Exponentiated Convolution Methods for Generative Direction Dependent Reverberation
Abstract
Spherical harmonic encoded acoustic sound-fields capture directional characteristics of room impulse responses that are useful for accurate spatial audio reproduction. However, high costs of multi-microphone measurements and numerical simulations motivate alternative data-set augmentation and synthetic data generation methods that supplement small collections. This paper introduces time-varying exponentiated convolution methods that transform both Gaussian noise and impulse responses into reverberation and modified spectral-decay fields respectively. We derive two recursive and fast convolution algorithms that extend into the spherical harmonic domain, model smooth reverberation time distributions with non-stationary Gaussian processes, and realize an optimal filter design. Experiments evaluate computational performance, and validate out-of-distribution generated impulse responses.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24809
PDF
-
CycleSpeech: Reciprocal Alignment for Instruction-Controlled Speech Synthesis and Paralinguistic Understanding
2026-09-21 15:38:31Huan Liao, Haonan Han, Xingwen Han, Dekun Chen, Yuancheng Wang, Zhizheng WuAbstract
Instruction-controlled speech synthesis and paralinguistic understanding are often trained independently, leaving reciprocal feedback between the two tasks underexplored. We introduce CycleSpeech, a framework that connects generation and understanding through a shared, structured voice profile that serves as a common target for supervision and reciprocal feedback. The forward cycle assesses whether synthesized speech expresses the intended attributes by comparing recovered and target profiles. The backward cycle evaluates whether profiles inferred from real speech can guide reconstruction of the source speaking style. To support both directions, we construct a bilingual dataset of 20,046 examples pairing instructions, target speech, speaker references, and structured profiles. Building on joint supervised fine-tuning, CycleGRPO alternates policy updates using reciprocal rewards grounded in profile consistency and speaking-style reconstruction. Fixed target profiles anchor feedback from the evolving counterpart. This procedure requires neither human preference annotations nor an additional preference-trained reward model. Evaluations on Chinese and English benchmarks show improved instruction adherence and profile recovery while maintaining competitive synthesis quality. Compared with Step-Audio-2-mini, CycleSpeech improves instruction-match accuracy by 4.50 and 10.06 percentage points in Chinese and English, respectively. Controlled ablations further support the contribution of cycle feedback to generation control. These results support structured voice profiles as an interface for reciprocal training between speech generation and paralinguistic understanding. An online demo is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24771
PDF
-
XSQ-AST: An Explainable Audio Spectrogram Transformer Framework for Localising Synthetic Speech Artifacts
2026-09-21 15:38:11Ben Heritage, Luca Resti, M\'onica Villanueva Aylagas, Timothy Mehlenbacher, Konrad Tollmar, James Alfred WalkerAbstract
Localising artifacts in synthetic speech remains challenging, as most evaluation methods yield only global quality scores. This paper presents XSQ-AST, a framework that combines the SQ-AST speech quality model with WhisperX phoneme alignment and multiple saliency methods to produce temporally localised artifact diagnostics without model retraining. Saliency maps are projected onto continuous distributions via kernel density estimation and onto phoneme boundaries via phoneme-discretised saliency maps. A 40-participant listening test validated the framework across five perceptual dimensions. Attention Rollout, Attention Flow and an adapted GradCAM produced temporal distributions that correlated with listener highlights, with different methods best suited to different artifact types. An AUC-ROC analysis confirmed discrimination above chance.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24770
PDF
-
Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion
2026-09-21 14:42:46Mathilde Abrassart, Nicolas Obin, Axel RoebelAbstract
Angular-margin speaker encoders are widely used in voice conversion, yet the geometry of their classifier prototypes remains poorly understood. We analyze ECAPA-TDNN classifier prototypes as points on the unit hypersphere and characterize their organization using rotation-invariant angular statistics together with global and local effective dimensionality measures. Our analysis shows that standard training can induce angular concentration and a substantial reduction in effective dimensionality. To address this, we investigate two geometric regularization strategies (hinged Riesz log-energy and effective-dimension maximization) applied to classifier prototypes to encourage more uniform hyperspherical coverage. The resulting prototype sets exhibit higher effective dimensionality and improved isotropy, with configuration-dependent effects on speaker-recognition performance. When the corresponding ECAPA-TDNN models are used as speaker encoders for Fast-VGAN, the regularized systems also exhibit improved robustness in zero-shot voice conversion, particularly for previously unseen speakers.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24688
PDF
-
Audio-based UAV Localization with Adaptive Temporal Correspondence via Reinforcement Learning
2026-09-21 07:34:50Haoxiang Lei, Mingzheng Feng, Daotong Wang, Shenghai YuanAbstract
Audio-based localization provides a low-cost and illumination-independent sensing solution for anti-UAV early warning. However, existing methods typically rely on a predefined fixed audio segment length, which limits temporal correspondence and creates a trade-off between sufficient acoustic evidence and timely localization. To address this issue, we propose an audio-based localization framework with adaptive temporal correspondence. A probe segment is first used to extract a compact acoustic state that characterizes the reliability and consistency of the observation. Guided by the state, a reinforcement learning controller dynamically determines the required audio window size for each localization decision. The selected audio segment is then processed by a Mamba-based localization network with adaptive temporal feature modulation for 3D position estimation. Extensive experiments demonstrate that our method achieves competitive 3D localization accuracy with substantially reduced temporal correspondence latency compared to SOTA methods and exhibits strong generalization across scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24218
PDF
-
Listen, Critique, and Refine: RL-Based Self-Refinement for Instruction-Following Speech Synthesis
2026-09-21 06:28:17Chee-En Yu, Yi-Cheng Lin, Sung-Feng Huang, Yun-Shao Tsai, Ho-Lam Chung, Xuanjun Chen, Hung-yi LeeAbstract
Large Audio Language Models (LALMs) can follow diverse instructions to synthesize speech in specified styles. However, complex instructions that require simultaneous control over pitch dynamics, speaking rate, and emotional tone often exceed what a single-pass generation can faithfully realize. While recent reasoning models have shown that intermediate "thinking" tokens improve output quality, this paradigm has been confined to the text modality. In this work, we extend reasoning to the audio token space by training a LALM with reinforcement learning to reason over its own speech output. The model first generates a draft speech as a form of audio-token reasoning, critiques its own generation by reflecting on the acoustic realization in text, and then produces a refined version conditioned on both the first-pass speech and the critique, all within a single model. After RL training, the refined two-hop outputs achieve a relative improvement of 7.15\% on the InstructTTSEval benchmark, demonstrating the model's reflective ability.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24163
PDF
-
P2Flow: Phoneme-aware Progressive Flow Matching for Extreme Speech Super-Resolution
2026-09-21 05:47:28Ningyuan Yang, Yize Li, Pu Zhao, Diego A. Cuji, Kanad Sarkar, Ryan M. Corey, Xue Lin, Andrew C. SingerAbstract
Generative models have recently demonstrated considerable promise in speech super-resolution (SSR). Nevertheless, the majority of existing work has concentrated on standard or versatile SSR configurations, leaving the extreme setting with severely limited spectral inputs largely unexplored. In this regime, current approaches exhibit marked performance degradation, underscoring the need for dedicated solutions. To bridge this gap, we introduce P2Flow, a phoneme-aware progressive flow matching (FM) framework designed for extreme SSR with three main strategies. First, our model leverages phonetic information to reconstruct missing spectral components. Furthermore, it employs a progressive architectural design that hierarchically restores distinct frequency regions. Finally, we incorporate post-training of the vocoder to enhance overall waveform fidelity. Extensive experiments are conducted on the TIMIT and VCTK datasets under both 1 kHz to 16 kHz and 2 kHz to 16 kHz settings, demonstrating that P2Flow yields state-of-the-art results across multiple evaluation metrics.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24138
PDF
-
MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification
2026-09-21 03:38:34Yu Zheng, Jinghan Peng, ChangHao Zhang, Jian Liu, Weiqiang WangAbstract
In this paper, we propose MECT, a speaker verification model that integrates the Mixture-of-Experts (MoE) mechanism into a CNN-Transformer backbone with optimized block structure and stacking scheme. Specifically, we investigated four MoE variants that span utterance-level and frame-level granularity with dense and sparse routing strategies. The MoE mechanism proves to be effective over the baseline without MoE with only a small increase in parameters. We further scale MECT to a series of model sizes, all maintaining compact parameters and low computational complexity. In particular, MECT-B2 achieves state-of-the-art performance on VoxCeleb1 and delivers strong results on CN-Celeb, demonstrating its effectiveness across diverse datasets. In addition, we establish a streaming inference paradigm through causal retraining, which maintains strong performance at a chunk size of 100ms.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24061
PDF
-
ART-NAD: An Articulatory Inversion-based Neural Acoustic Distance for Pathological Speech Intelligibility Assessment
2026-09-21 03:17:50Bence Mark Halpern, Thomas Tienkamp, Defne Abur, Tomoki TodaAbstract
Speech assessment tools for speakers with speech pathology must be both accurate and interpretable if they are to be adopted in clinical practice. Existing reference-audio measures such as the Neural Acoustic Distance (NAD) reach high speaker-level correlations with listener intelligibility scores but operate on self-supervised features that are hard to interpret, providing only frame-level explanations. We propose ART-NAD, a reference-audio intelligibility metric that replaces the \texttt{wav2vec2} features of NAD with vocal-tract constriction variables (tract variables, TVs) predicted from audio by a speaker-independent acoustic-to-articulatory inversion model trained on the same \texttt{wav2vec2} features. ART-NAD is computed as the multivariate Dynamic Time Warping distance between the nine-channel quasi-TV trajectories of the test and one or more references. Across 20 reference-audio protocols spanning six pathological-speech datasets and five languages, ART-NAD with silence trimming (ART-NAD-FA) reaches the same average speaker-level Pearson correlation as NAD-FA (both $r=0.71$) on the same self-supervised backbone, with no significant per-protocol difference (Wilcoxon $p=0.18$), and is the strongest reference-audio metric on 6 of the 20 protocols. Beside the score itself, each TV channel visualizes which constriction deviates from the reference over time, providing interpretable information as to where articulation breaks down.
Abstract (translated)
URL
https://arxiv.org/abs/2609.24046
PDF
-
TTS-Guard: Black-Box Ownership Verification of Text-to-Speech Models via Adaptive Adversarial Speaker-Pair Fingerprints
2026-09-20 16:13:11Xubin Yue, Zhenhua Xu, Zhebo Wang, Mengting Li, Zijie Zhou, Wenpeng Xing, Dezhang Kong, Meng HanAbstract
The rapid maturation of zero-shot Text-to-Speech (TTS) models has turned high-quality voice cloning into a widely available capability, raising acute concerns over unauthorised replication, fine-tuning and resale of proprietary speech models. Yet ownership verification for TTS remains largely open: speech is a continuous waveform whose perturbations are easily destroyed by routine signal processing, and the human auditory system imposes a much tighter perceptual budget than vision. We present \textbf{TTS-Guard}, a black-box ownership verification framework for TTS models built on \emph{adversarial speaker-pair fingerprints}. TTS-Guard(i) selects key speaker pairs in a \emph{dual} embedding space for architecture-agnostic stealth;(ii) optimises a perturbation through an \emph{adaptive curriculum} of shadow models covering fine-tuning, pruning, quantisation and distillation; and (iii) aggregates black-box queries into a calibrated \emph{Verification Confidence Score}. On five mainstream TTS systems, TTS-Guard reaches an average Fingerprint Success Rate of $96.4\%$ at a False Positive Rate of $5.8\%$, while preserving intelligibility and naturalness. The fingerprint remains effective against ten audio attacks, six model modifications, and two state-of-the-art adversarial purifiers.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23729
PDF
-
Entropy-aware logistic regression for fusion of large-scale speaker recognition systems
2026-09-20 16:08:39Pierre-Michel Bousquet, Mickael RouvierAbstract
Score-level fusion based on logistic regression is widely used in speaker recognition to combine complementary systems. However, conventional approaches assign fixed system-dependent coefficients and do not explicitly account for variations in the reliability of individual enrollment and test utterances. Drawing on recent research on the entropy of deep learning-based speaker recognition models, this study incorporates an uncertainty component into the fusion process. By exploiting both system-level complementarity and utterance-dependent uncertainty, the method achieves robust performance in large-scale speaker recognition tasks that involve highly variable characteristics of the speech signal. These results demonstrate that model-entropy information provides a valuable complementary cue in large-scale scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23727
PDF
-
Which Constraints Are Missing? Ask the Verifier: Graded Rewards for Constraint-Following Music Generation
2026-09-20 14:22:10Haoyue Liu, Ye Chen, Zhichao Wang, Xiaoyu Ma, Haoran Shou, Xiaoying TangAbstract
Constraint-following music generation asks a score to satisfy several user-specified properties at once, each checkable programmatically (key, meter, length, range, final note, rhythm, motion and form), yet no existing benchmark isolates this capability. We construct MusicConstraintBench, 2,180 items over eight constraint families, on which current models fail once a few constraints are combined. The natural remedy is reinforcement learning with these verifiers as reward, yet we observe that a reward paid only when every property holds leaves most training groups without a learning signal: over the first 50 updates, 0.550 of rollout groups score identically and receive no gradient, even though a failing score typically misses only one requested property. Under the joint criterion, rollouts for a prompt tend to fail together, so a binary reward cannot separate a nearly correct score from a malformed one. We therefore introduce MusicRLVR, which pays graded per-property credit behind a hard validation gate that rejects malformed outputs, plus a joint-satisfaction bonus, requiring no human annotation, learned reward model, or music-domain fine-tuning. On MusicConstraintBench, MusicRLVR lifts Qwen3-4B-Instruct from 0.160 to 0.807 on mixed constraints and leads every zero-shot baseline including Llama-3.1-70B at 0.380. It also generalises to property combinations unseen in training and to out-of-range parameter values, showing that verifiable rewards need not presuppose a target output.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23665
PDF
-
Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models
2026-09-20 12:12:20Jiaheng Dong, Xiaofeng Yu, Jean Honorio, Abhirup Ghosh, Hong Jia, Ting DangAbstract
Large audio-language models (LALMs) are increasingly used for a broader range of audio reasoning tasks. These models typically incorporate audio representations into a large language model (LLM) backbone to enable multimodal reasoning. Recent test-time reinforcement learning (TTRL) methods further improve LLM reasoning capability by leveraging unlabelled test data after pre-training. However, the importance of the perceptual capability of LALMs remains underexplored, particularly how much acoustic evidence is integrated and relied upon during reasoning, and how this contributes to final task performance. This gap limits the development of effective post-training methods like TTRL for audio reasoning. In this work, we first analyse how audio information is integrated and utilised during reasoning process. We quantify layer-wise perceptual reliance and show that stronger acoustic reliance is associated with higher accuracy and a larger performance gain attributable to the audio input. Building on this, we propose Perception-Grounded TTRL (PG-TTRL), which aligns label-free test-time optimisation with perceptually grounded reasoning, encouraging the model to structure its reasoning more strongly on the audio input. Experiments across LALMs and benchmarks show that PG-TTRL consistently improves reasoning performance over both the base models and standard TTRL, showing the value of perceptual-grounding optimisation for test-time audio reasoning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23589
PDF
-
ArtifactBench: Lineage-Aware Evaluation of AI-Generated Music Detectors under Distribution Shift
2026-09-20 11:03:39Heewon OhAbstract
AI-generated music detectors are commonly compared using aggregate scores on benchmarks whose training overlap, generator lineage, source provenance, and audio-transformation history are only partially observable. This paper introduces ArtifactBench, a lineage-aware evaluation suite for measuring detector behavior across generator families and versions, real-music domains, collection-cohort shift, and inference coverage. The benchmark groups source recordings and their derived variants by content identity, separates calibration from final testing, records inference failures independently from classification errors, and reports source-level performance with uncertainty in addition to aggregate metrics. We evaluate multiple publicly available detectors under a version-pinned common protocol and examine how leakage control, cohort availability, threshold policy, and model-specific missingness alter measured performance and model ranking. On the 562-track common-success test intersection, ArtifactNet obtains 0.982 AUROC and 0.918 balanced accuracy, compared with 0.761/0.776 for the public Deezer detector; SpecTTTra and CLAM fall below 0.30 AUROC under this shifted cohort. These results also expose substantial generator- and real-domain shifts that aggregate scores alone conceal.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23550
PDF
