Searcharxiv⌕ Search

arXiv subjects

Junan Zhang

Publications and source records attributed to Junan Zhang.

At least 19 recordsLinked to original sources
arXiv2026

AnyEdit: A Unified Framework for Speech and Singing Voice Editing with Real-World Environmental Consistency

We present AnyEdit, a unified, separation-free framework for speech and singing voice editing that preserves real-world acoustic environments, including noise, reverberation, and background music. Recent unified generative models already achieve strong speech and singing generation in clean conditions, but real-world vocal editing remains challenging because the model must revise content while simultaneously preserving speaker identity, prosody, and the surrounding acoustic scene. Directly modeling noisy audio end-to-end entangles semantic editing with environmental acoustics, weakening the core vocal generation capability. We therefore adopt a two-stage design that preserves clean-domain editing ability while deferring acoustic rendering to a separate stage: an instruction-guided autoregressive editor first predicts clean prosody and content-style tokens, supported by a teacher-student noise-robust prosody tokenizer that distills clean prosodic tokens from degraded recordings; a flow-matching acoustic model then performs in-context rendering conditioned on the source acoustic context, so the edited segment inherits surrounding noise, reverberation, and background sound while maintaining consistent speaker timbre. To stabilize unedited regions, we introduce unmodified-area-aware supervision; after pre-training, we further apply direct preference optimization on mined real-to-real singing pairs. We also release AnyEditBench, a benchmark covering both speech and singing voice editing under clean, simulated, and in-the-wild acoustic conditions. Experiments on Chinese and English speech and singing datasets showed that AnyEdit consistently outperforms strong baselines in content accuracy, subjective quality, and background consistency under noisy and reverberant conditions. Demo: https://any-edit.github.io/. AnyEditBench: https://huggingface.co/datasets/Ririiiii/anyeditbench.

cs.SD↗
arXiv2026

What Matters in Preference Post-Training of Continuous Autoregressive Speech Language Models

Continuous autoregressive speech language models combine an autoregressive (AR) backbone with a diffusion or flow-matching head. Preference post-training requires choosing how to construct pairs and which modules to update. Controlled interventions show that a perturbed acoustic patch changes subsequent backbone states, yet larger representation changes do not necessarily reduce speech quality. We construct preference pairs through noise or inference-configuration perturbations and formulate a preference update based on reference-relative flow-matching errors. Updating the backbone with a fixed head yields stronger reward improvements than head-only adaptation in our evaluated setting. Across flow-time and module ablations, the lowest training loss does not consistently produce the best speech. These findings support preference post-training that considers both acoustic sampling and autoregressive conditioning, with training choices validated on generated utterances.

cs.SD↗
arXiv2026

DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration

Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, while search, reasoning, and coding are handled through asynchronous delegation. A duplex model supports continuous listening and speaking, but complex reasoning and tool use may exceed its capabilities. A coding agent can plan and execute extended tasks, but its sequential interface is a poor fit for live conversation. Combining them requires a harness that coordinates task acceptance, progress, cancellation, replacement, and result delivery while keeping the conversation responsive. Existing harnesses often rely on coupled heuristics, making them difficult to improve systematically from evidence. We present DuplexAgent, a full-duplex collaboration system whose harness expresses this workflow as six editable modules, and Duplex-Harness-RSI, a closed loop that revises them from interaction traces. A simulator automatically generates timed test conversations, runs the system, and produces failure traces that identify the collaboration modules requiring repair. Reasoning LLMs and coding agents in the delegation pool also serve the improvement loop: the Exam Planner selects the next tests from observed weaknesses and the repair archive, and the Harness Editor proposes targeted module changes. The capabilities that serve the user thus also improve the system's coordination. Experiments on intelligence, agentic, and duplex benchmarks show that DuplexAgent combines continuous interaction with difficult reasoning and complex task execution, achieving stronger spoken-knowledge and executable-tool scores than the compared delegated systems while maintaining strong interruption response. A harness ablation further shows that this modular, verifiable loop outperforms the initial harness and repeated editing that lacks its diagnosis and repair archive.

cs.AI↗
arXiv2026

AutoSynth: Learning to Generate Editable Synthesizer Programs from Audio and Text

Audio generation models can translate natural-language descriptions into sound, but their outputs are typically waveforms. Their audio quality is constrained by audio compression, and their outputs do not readily support direct edits to notes, timbral parameters, or modulation relationships. We present AutoSynth, which represents MIDI performance events, fixed synthesizer parameters, and variable-length modulation routes as a unified sequence for a synthesizer, and learns their dependencies with an audio-conditioned autoregressive model. A single model supports both tasks. Given reference audio, the model directly predicts a synthesizer program; given text, it uses a pretrained audio generation model and converts the generated audio into a program. Training consists of two stages: supervised learning on large-scale audio-program pairs automatically constructed from a small set of native presets, followed by group-relative policy optimization with a mixed reward combining semantic similarity, pitch-related features, acoustic similarity, and sound usefulness. The pipeline requires neither paired text-target-program annotations nor a differentiable synthesizer. Experiments show that AutoSynth produces complete, editable synthesizer programs and achieves competitive results in both synthesizer inversion and text-driven generation. Audio demos and source code are available at https://auto-synth.github.io/.

cs.SD↗
arXiv2026

AuraSE: Low-Hallucination Generative Speech Enhancement via Multimodal Flow Matching and Inference Policy Optimization

Generative speech enhancement models can produce cleaner and more natural-sounding speech than conventional discriminative approaches, but may hallucinate by changing speech content or speaker identity, even with transcript conditioning. We present AuraSE, a flow-matching framework that addresses hallucination through complementary modality and inference designs. First, a double-stream-to-single-stream multimodal Diffusion Transformer (MMDiT) allows transcript and acoustic representations to interact while preserving a dedicated pathway for the degraded input. Second, we find that the best decoder configuration, governed by guidance scale, sampling temperature, and step count, varies substantially across utterances. This observation motivates Inference Policy Optimization (IPO), an online, on-policy preference optimization method. IPO generates multiple candidates from the current model under different inference configurations, ranks them with a multi-objective reward, and learns from their relative preferences. AuraSE-IPO ranks first on 11 of 12 metrics across the synthetic test sets and obtains the highest DNSMOS and blind-listening scores among the evaluated systems on the real DNS blind test set. At deployment, it uses a fixed $10$-step ODE decoder without classifier-free guidance (CFG) or per-utterance configuration search.

cs.SD↗
arXiv2026

Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

Hosted retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora, raising two competing demands: to hide each query and chosen result, yet reveal only the documents that the user is authorized to receive. Existing cryptographic approaches either make this costly by processing the entire corpus for every query, or sacrifice quality for efficiency by scanning a few clusters. We repurpose learned deep hashing as a private filter: a randomized binary code points the provider to a short candidate list, while encrypted reranking and oblivious key transfer protect the precise query and final selection. This shortlist short-circuits full-corpus cryptographic search without sacrificing retrieval quality: with 200-500 candidates, it closely matches full-corpus retrieval across five zero-shot corpora spanning 25K to 5.4M documents. On the full 2.68M-passage NQ corpus over a 10-Gbps link, our protocol only adds 0.73 seconds, or 10 percent, to a 128-token Qwen3-32B RAG pipeline. The released code satisfies directional metric differential privacy (DP) and substantially reduces embedding-inversion and property-inference leakage, demonstrating that a carefully learned shortlist can make private dense retrieval both accurate and practical.

cs.CR↗
arXiv2026

CPR: Combining global composing, local performing and full-sequence refining in piano rendering with continuous autoregressive modelling

Prompt-conditioned piano MIDI-to-Music rendering aims to faithfully render target notes while reproducing the timbre of a reference recording. Existing approaches primarily follow two paradigms: autoregressive (AR) modeling and flow matching (or diffusion). Discrete-codec AR models provide causal temporal modeling, but quantization can discard acoustic detail. Flow matching better preserves acoustic structure in the cost of full-sequence attention costs and worse semantic structure. Continuous autoregressive models operate directly on continuous representations. It not only combines the condition-following ability of AR models and distribution-modeling capacity of flow matching but also bypasses the quantization bottleneck with lower computational costs. Building on this principle, we present Composer--Performer--Refiner (CPR) framework. Composer autoregressively predicts continuous hidden states, Performer generates 24kHz acoustic latents through local flow matching and Refiner then upsamples the waveform to 48 kHz. We further introduce Bottlenecked Representation Alignment (BREPA) and Modality--Time RoPE (MT-RoPE) to strengthen musical semantic structure in Composer hidden states and temporal alignments across modalities. Codes are available at https://github.com/FEAfeatherTHER/CPR_official

cs.SD↗
arXiv2026

Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis

Evaluating live streaming speech synthesis (TTS) requires assessing fine-grained, highly expressive prosody such as emotion, intonation, and energy which traditional MOS predictors fail to capture. While proprietary Large Language Models (LLMs) like Gemini can evaluate these aspects, they are too costly for massive inference and reinforcement learning feedback. To address this, we first introduce Live-ProsodyJudge (LPJ), a cost-effective pairwise evaluator distilled from Gemini into Qwen3-Omni. However, we identify a critical flaw in standard multi-dimensional evaluation: verdict coupling. The judge tends to lazily align all individual dimension scores with its overall preference, collapsing a rich multi-dimensional rubric into a single preference bit. To resolve this, we further propose Decoupled-Live-ProsodyJudge (D-LPJ). D-LPJ eliminates the overall verdict target to prevent blind following, masks uncertain pair-dimensions during Supervised Fine-Tuning(SFT), and introduces a novel span-local GRPO strategy that applies normalized advantages strictly to their corresponding rationale spans. Evaluated on highly curated human-annotated test sets, 10 sample balanced-order LPJ achieves higher point accuracy than a single Gemini call, while D-LPJ successfully produces independent,decoupled dimension judgments. Furthermore, in a Best-of-8 TTS candidate selection tournament, the LPJ-selected utterance falls within the human top-3 in 85.29% of high-confidence cases, demonstrating its efficacy for fine-grained TTS preference optimization.

cs.SD↗
arXiv2026

Frequency-Aware Self-Supervised Music Representation Learning

Self-supervised learning (SSL) has emerged as an essential paradigm for music information retrieval (MIR). While current SSL models achieve state-of-the-art performance across various MIR tasks, they typically treat audio as 1D sequences, either operating on time-domain waveforms or on flattened time-frequency-domain spectrograms. This discards the rich spatial and structural information in time-frequency representations and overlooks a fundamental intuition in music production. In particular, music is naturally represented as time-frequency grids in MIDI-based workflows, a structure that tightly corresponds to 2D spectrograms and inherently makes many MIR tasks trivial. Motivated by this intuition, we propose PupuM2D, a musical Masked Modeling Duo (M2D) model that is trained directly on 2D music spectrograms. Instead of applying masked language modeling (MLM) to 1D sequences, PupuM2D learns robust representations by predicting the latent embeddings of masked 2D music spectrogram patches from unmasked contexts. To optimally adapt such a framework to music signals, we also apply domain-specific modifications to model architecture, training scheme, and inference paradigm, with comprehensive ablation studies showing their effectiveness. Evaluations on the MARBLEv2 benchmark show that PupuM2D outperforms the sequence-based SSL models across multiple MIR tasks in linear probing. Additionally, case studies of the attention maps also confirm that PupuM2D captures musically meaningful patterns within the 2D time-frequency domain. Codes and checkpoints are available at: https://www.yichenggu.com/PupuM2D/.

cs.SD↗
arXiv2026

P-MUSE: Prompt-MIDI-Optional Model for Unified Instrumental Music Synthesis and Editing

MIDI-to-Music system renders the melody and rhythm of a target MIDI sequence into musical segment while cloning instrument timbre from a prompt recording. Existing systems typically adopt one of two distinct paradigms: conditional generation with prompt audio alone, which remains applicable when aligned prompt MIDI is unavailable, and In-Context Learning with paired prompt audio and MIDI, which exploits cross-modal alignment for stronger control on MIDI following and timbre similarity. We introduce P-MUSE, an instrumental MIDI-to-Music framework that unifies both paradigms via a multi-stage Curriculum-Learning supporting prompt-MIDI-optional inputs. P-MUSE further unifies music generation and local editing through a shared fill-in-the-middle formulation. Grounded in theoretical analysis and empirical study, we propose a phase-aware classifier-free guidance scheduling principle for Transcription-to-Audio systems, alongside a Tail-Drop strategy. Finally, to advance research in this field, we establish the first comprehensive benchmark, covering various prompt modes, generation/editing tasks, and four representative instruments: piano, guitar, bass, and drums. Demos are available at https://p-muse.github.io/.

cs.SD↗
arXiv2026

DDSynth-RL: Audio Synthesizer Inversion via Discrete Diffusion with Reinforcement Learning

Synthesizer inversion is challenging for two main reasons: 1) Distinct parameter configurations can produce perceptually similar sounds. 2) Parameter-space losses often fail to reflect rendered audio similarity, while the synthesizer being a non-differentiable black box prevents simple audio-domain supervision. To address the one-to-many mapping induced by the first challenge, we formulate synthesizer inversion as conditional generation over discrete synthesizer parameters and use masked discrete diffusion as the generator. This treatment additionally avoids the fixed-order assumption of autoregressive models and the continuous-relaxation mismatch of flow matching when modeling categorical synthesizer controls. To address the second challenge, we further fine-tune the model with GRPO-style audio-domain rewards computed from rendered outputs. Experiments on Dexed show that, after supervised training, the discrete diffusion model is competitive with autoregressive and flow-matching baselines, and reward-based fine-tuning further improves out-of-domain audio matching performance. Code and demos are available at: https://github.com/DDSynth-RL/DDSynthRL.

cs.SD↗
arXiv2026

Anysynth:Zero-Shot Instrument Cloning via In-Context Learning and Asymmetric Hierarchical Guidance

Zero-shot instrument cloning aims to render an arbitrary [Target MIDI] sequence with the acoustic identity of an unseen instrument given only a short [Reference Audio, Reference MIDI] pair. Existing methods rely on pre-trained embeddings (e.g., CLAP) that compress the reference audio into a fixed-length vector, discarding fine-grained acoustic cues essential for faithful timbre reconstruction. We present Anysynth, an embedding-free neural synthesizer based on in-context flow matching. By conditioning a Diffusion Transformer (DiT) directly on the uncompressed reference audio and target MIDI, our model allows self-attention to dynamically retrieve acoustic details at generation time. Experiments show that AnySynth outperforms embedding-based and auto-regressive baselines in audio quality, timbre similarity, and melody adherence. Notably, the model exhibits prompt-length scaling: longer reference prompts yield steadily better timbre fidelity, a property absent in embedding-based systems. To optimize controllability, we further propose Asymmetric Hierarchical CFG, which structurally decouples MIDI and reference-timbre guidance based on their natural semantic-acoustic dependency. This asymmetric formulation avoids gradient conflicts and improves both note accuracy and timbre fidelity, pushing the boundary of expressive, zero-shot instrument cloning. Demo audios are available at https://anysynth-demo.github.io/

cs.SD↗
arXiv2026

Aliasing-Free Neural Audio Synthesis

In neural audio synthesis, neural vocoders and codecs are models that reconstruct waveforms from acoustic and latent representations, which are essential to the resulting audio quality. While current models are capable of generating perceptually natural speech, they still struggle with high-fidelity music and singing voice synthesis, as severe aliasing artifacts are introduced by non-linear activation functions and upsampling layers in existing architectures. Although various anti-aliasing techniques have been proposed in digital signal processing, their integration into neural vocoders and codecs remains under-explored. This paper incorporates differentiable anti-aliasing techniques into the activation and upsampling modules to bridge this gap, and thus presents Pupu-Vocoder and Pupu-Codec. We build a test signal benchmark to evaluate the anti-aliased modules, and validate our proposed models on speech, singing voice, music, and audio. Experimental results show that Pupu-Vocoder and Pupu-Codec outperform existing systems on singing voice, music, and audio, while achieving comparable performance on speech. Demos, codes, and checkpoints are available at: VocodexElysium.github.io/AliasingFreeNeuralAudioSynthesis/.

cs.SD↗
arXiv2026

EigeNet: Geometry-Informed Multi-Modal Learning for Few-shot Novel View RIR Prediction

Predicting spatially varying Room Impulse Response (RIR) from sparse observations is a critical but highly challenging inverse problem for immersive spatial audio rendering. In this work, we present EIGENET, a geometry-informed multi-modal framework for few-shot novel view RIR prediction. At its core is a Cross-view Alternate-attention Transformer that iteratively refines local intra-view acoustic structures and global cross-view spatial relationships. We empirically demonstrate that this architecture is capable of making full use of the multi-view multi-modal context while performing spatial-temporal reasoning for RIR prediction. Inspired by acoustic ray tracing, we design a geometry-informed modulation block to formulate the connection between geometric features and RIR power spectrum. In the mean time, an auxiliary loss is introduced to transform the single-target waveform prediction into a multi-task learning framework. Through ablation studies, we demonstrate that this design yields consistent performance gains regardless of the underlying backbone, thereby confirming its foundational utility and architecture-agnostic generalizability for RIR prediction task. Evaluated on both simulated and real-world benchmarks, EIGENET achieves both state-of-the-art performance in few-shot novel view RIR prediction and sim-to-real generalization. Codes and checkpoints are available on https://github.com/FEAfeatherTHER/EigeNet.

cs.SD↗
arXiv2026

Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation

Controllable human voice generation, particularly for expressive domains like singing, remains a significant challenge. This paper introduces Vevo2, a unified framework for controllable speech and singing voice generation. To tackle issues like the scarcity of annotated singing data and to enable flexible controllability, Vevo2 introduces two audio tokenizers: (1) a unified music-notation-free prosody tokenizer that captures prosody and melody from speech, singing, and even instrumental sounds, and (2) a unified content-style tokenizer that encodes linguistic content, prosody, and style for both speech and singing, while enabling timbre disentanglement. Vevo2 consists of an auto-regressive (AR) content-style modeling stage, which aims to enable controllability over text, prosody, and style, as well as a flow-matching acoustic modeling stage that allows for timbre control. Particularly, during the speech-singing joint training of the AR model, we propose both explicit and implicit prosody learning strategies to bridge speech and singing voice. Moreover, to further enhance the Vevo2's ability to follow text and prosody, we design a multi-objective post-training task that integrates both intelligibility and prosody similarity alignment. Experimental results show that the unified modeling in Vevo2 brings mutual benefits to both speech and singing voice generation. Additionally, Vevo2's effectiveness across a wide range of synthesis, conversion, and editing tasks for both speech and singing further demonstrates its strong generalization ability and versatility. Audio samples are are available at https://versasinger.github.io/.

cs.SD↗
arXiv2025

The CCF AATC 2025 Speech Restoration Challenge: A Retrospective

Real-world speech communication is rarely affected by a single type of degradation. Instead, it suffers from a complex interplay of acoustic interference, codec compression, and, increasingly, secondary artifacts introduced by upstream enhancement algorithms. To bridge the gap between academic research and these realistic scenarios, we introduced the CCF AATC 2025 Challenge. This challenge targets universal blind speech restoration, requiring a single model to handle three distinct distortion categories: acoustic degradation, codec distortion, and secondary processing artifacts. In this paper, we provide a comprehensive retrospective of the challenge, detailing the dataset construction, task design, and a systematic analysis of the 25 participating systems. We report three key findings that define the current state of the field: (1) Efficiency vs. Scale: Contrary to the trend of massive generative models, top-performing systems demonstrated that lightweight discriminative architectures (<10M parameters) can achieve state-of-the-art performance, balancing restoration quality with deployment constraints. (2) Generative Trade-off: While generative and hybrid models excel in theoretical perceptual metrics, breakdown analysis reveals they suffer from "reconstruction bias" in high-SNR codec tasks and struggle with hallucination in complex secondary artifact scenarios. (3) Metric Gap: Most critically, our rank correlation analysis exposes a strong negative correlation (\r{ho}=-0.8) between widely-used reference-free metrics (e.g., DNSMOS) and human MOS when evaluating hybrid systems. This indicates that current metrics may over-reward artificial spectral smoothness at the expense of perceptual naturalness. This paper aims to serve as a reference for future research in robust speech restoration and calls for the development of next-generation evaluation metrics sensitive to generative artifacts.

cs.SD↗
arXiv2025

Investigating training objective for flow matching-based speech enhancement

Speech enhancement(SE) aims to recover clean speech from noisy recordings. Although generative approaches such as score matching and Schrodinger bridge have shown strong effectiveness, they are often computationally expensive. Flow matching offers a more efficient alternative by directly learning a velocity field that maps noise to data. In this work, we present a systematic study of flow matching for SE under three training objectives: velocity prediction, $x_1$ prediction, and preconditioned $x_1$ prediction. We analyze their impact on training dynamics and overall performance. Moreover, by introducing perceptual(PESQ) and signal-based(SI-SDR) objectives, we further enhance convergence efficiency and speech quality, yielding substantial improvements across evaluation metrics.

cs.SD↗
arXiv2025

Multi-Metric Preference Alignment for Generative Speech Restoration

Recent generative models have significantly advanced speech restoration tasks, yet their training objectives often misalign with human perceptual preferences, resulting in suboptimal quality. While post-training alignment has proven effective in other generative domains like text and image generation, its application to generative speech restoration remains largely under-explored. This work investigates the challenges of applying preference-based post-training to this task, focusing on how to define a robust preference signal and curate high-quality data to avoid reward hacking. To address these challenges, we propose a multi-metric preference alignment strategy. We construct a new dataset, GenSR-Pref, comprising 80K preference pairs, where each chosen sample is unanimously favored by a complementary suite of metrics covering perceptual quality, signal fidelity, content consistency, and timbre preservation. This principled approach ensures a holistic preference signal. Applying Direct Preference Optimization (DPO) with our dataset, we observe consistent and significant performance gains across three diverse generative paradigms: autoregressive models (AR), masked generative models (MGM), and flow-matching models (FM) on various restoration benchmarks, in both objective and subjective evaluations. Ablation studies confirm the superiority of our multi-metric strategy over single-metric approaches in mitigating reward hacking. Furthermore, we demonstrate that our aligned models can serve as powerful ''data annotators'', generating high-quality pseudo-labels to serve as a supervision signal for traditional discriminative models in data-scarce scenarios like singing voice restoration. Demo Page:https://gensr-pref.github.io

cs.SD↗