arXiv subjects

Junjie Zheng

Publications and source records attributed to Junjie Zheng.

At least 19 recordsLinked to original sources

arXiv2026

Luna-TTS Family Technical Report

Modern text-to-speech (TTS) is dominated by autoregressive (AR) codec language models, whose left-to-right decoding brings latency that grows with utterance length, error accumulation along the committed prefix, and an artificial generation order imposed on the Residual Vector Quantization (RVQ) token grid. We propose Luna-TTS Family, diffusion-language-model-based TTS systems pretrained on 1 million hours of speech across Chinese, English, Japanese, and Korean. The family is built by progressive adaptation of a pretrained AR text LLM, from causal to bidirectional and finally to block-causal attention, and comprises two variants sharing a single tokenizer, data pipeline, and 0.6B backbone lineage. Luna-TTS is fully non-autoregressive: it generates the entire RVQ token grid in a fixed number of parallel refinement steps, with zero-shot voice cloning and speech editing arising natively as infilling. Luna-TTS Realtime, derived by continual training, is autoregressive over blocks of 32 codec frames (1.28s) while denoising each block in parallel; it supports KV-cached blockwise generation and incremental audio delivery, achieving an end-to-end RTF of 0.0240 and 41.6 ms local first-block latency under the warmed serving protocol. An annealed fine-tuning stage adds explicit control over emotion and non-verbal vocalizations (NVVs), and a reinforcement-learning stage applies GRPO with policy ratios computed over the realized denoising trajectory. On Seed-TTS-Eval, Luna-TTS achieves the best results on all four metrics among compared open-source and commercial systems (0.73 CER / 79.7 SIM on test-zh, 1.49 WER / 76.8 SIM on test-en); on the harder in-the-wild CV3-Eval, it posts the lowest Mandarin and English error rates in our comparison. Against leading commercial systems, it achieves the best results on most objective, model-based, and human-rated metrics for NVV and emotion control.

cs.SD↗

arXiv2026

YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance

Regenerating singing voices with altered lyrics while preserving melody consistency remains challenging, as existing methods either offer limited controllability or require laborious manual alignment. We propose YingMusic-Singer, a fully diffusion-based model enabling melody-controllable singing voice synthesis with flexible lyric manipulation. The model takes three inputs: an optional timbre reference, a melody-providing singing clip, and modified lyrics, without manual alignment. Trained with curriculum learning and Group Relative Policy Optimization, YingMusic-Singer achieves stronger melody preservation and lyric adherence than Vevo2, the most comparable baseline supporting melody control without manual alignment. We also introduce LyricEditBench, the first benchmark for melody-preserving lyric modification evaluation. The code, weights, benchmark, and demos are publicly available at https://github.com/ASLP-lab/YingMusic-Singer-Plus.

eess.AS↗

arXiv2026

UniVoice: A Unified Model for Speech and Singing Voice Generation

Text-to-speech (TTS) and singing voice synthesis (SVS) both aim to generate human vocal audio from symbolic inputs, but they impose different requirements on the generation process. Speech generation relies on flexible, language-driven prosody, whereas singing generation requires explicit melody control and accurate rhythmic alignment. This mismatch makes it challenging to train a single model that can generate both natural speech and controllable singing, since melody-related conditions should strongly constrain singing but should not restrict speech prosody. We present UniVoice, a unified speech and singing voice generation framework based on conditional flow matching. Instead of using a single undifferentiated conditioning representation, UniVoice factorizes the condition into content, melody, and timbre, which are encoded by modality-appropriate encoders and consumed by a shared Diffusion Transformer (DiT) backbone. For singing, the melody condition is represented by MIDI note sequences; for speech, it is replaced with a learned null melody token, allowing the model to infer prosody from linguistic and acoustic context. This design preserves explicit melody control for singing while avoiding the need to impose melody constraints on speech. We further analyze the null melody token as an approximation to melody marginalization in the conditional flow. Trained on 30k hours of speech and 35k hours of singing data, UniVoice achieves a speech PER of 5.26\%, comparable to dedicated TTS systems such as F5-TTS (5.21\%) and CosyVoice3 (5.30\%). On singing generation, UniVoice achieves a PER of 16.22\%, outperforming the unified baseline Vevo1.5 (24.72\%).

cs.SD↗

arXiv2026

Towards Scalable Lightweight GUI Agents via Multi-role Orchestration

Autonomous Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) enable digital automation on end-user devices. While scaling both parameters and data has yielded substantial gains, advanced methods still suffer from prohibitive deployment costs on resource-constrained devices. When facing complex in-the-wild scenarios, lightweight GUI agents are bottlenecked by limited capacity and poor task scalability under end-to-end episodic learning, impeding adaptation to multi-agent systems (MAS), while training multiple skill-specific experts remains costly. Can we strike an effective trade-off in this cost-scalability dilemma, enabling lightweight MLLMs to participate in realistic GUI workflows? To address these challenges, we propose the LAMO framework, which endows a lightweight MLLM with GUI-specific knowledge and task scalability, allowing multi-role orchestration to expand its capability boundary for GUI automation. LAMO combines role-oriented data synthesis with a two-stage training recipe: (i) supervised fine-tuning with Perplexity-Weighted Cross-Entropy optimization for knowledge distillation and visual perception enhancement, and (ii) reinforcement learning for role-oriented cooperative exploration. With LAMO, we develop a task-scalable native GUI agent, LAMO-3B, supporting monolithic execution and MAS-style orchestration. When paired with advanced planners as a plug-and-play policy executor, LAMO-3B can continuously benefit from planner advances, enabling a higher performance ceiling. Extensive static and online evaluations validate the effectiveness of our design.

cs.AI↗

arXiv2025

YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidance

Singing Voice Synthesis (SVS) remains constrained in practical deployment due to its strong dependence on accurate phoneme-level alignment and manually annotated melody contours, requirements that are resource-intensive and hinder scalability. To overcome these limitations, we propose a melody-driven SVS framework capable of synthesizing arbitrary lyrics following any reference melody, without relying on phoneme-level alignment. Our method builds on a Diffusion Transformer (DiT) architecture, enhanced with a dedicated melody extraction module that derives melody representations directly from reference audio. To ensure robust melody encoding, we employ a teacher model to guide the optimization of the melody extractor, alongside an implicit alignment mechanism that enforces similarity distribution constraints for improved melodic stability and coherence. Additionally, we refine duration modeling using weakly annotated song data and introduce a Flow-GRPO reinforcement learning strategy with a multi-objective reward function to jointly enhance pronunciation clarity and melodic fidelity. Experiments show that our model achieves superior performance over existing approaches in both objective measures and subjective listening tests, especially in zero-shot and lyric adaptation settings, while maintaining high audio quality without manual annotation. This work offers a practical and scalable solution for advancing data-efficient singing voice synthesis. To support reproducibility, we release our inference code and model checkpoints.

cs.SD↗

arXiv2025

YingMusic-SVC: Real-World Robust Zero-Shot Singing Voice Conversion with Flow-GRPO and Singing-Specific Inductive Biases

Singing voice conversion (SVC) aims to render the target singer's timbre while preserving melody and lyrics. However, existing zero-shot SVC systems remain fragile in real songs due to harmony interference, F0 errors, and the lack of inductive biases for singing. We propose YingMusic-SVC, a robust zero-shot framework that unifies continuous pre-training, robust supervised fine-tuning, and Flow-GRPO reinforcement learning. Our model introduces a singing-trained RVC timbre shifter for timbre-content disentanglement, an F0-aware timbre adaptor for dynamic vocal expression, and an energy-balanced rectified flow matching loss to enhance high-frequency fidelity. Experiments on a graded multi-track benchmark show that YingMusic-SVC achieves consistent improvements over strong open-source baselines in timbre similarity, intelligibility, and perceptual naturalness, especially under accompanied and harmony-contaminated conditions, demonstrating its effectiveness for real-world SVC deployment.

cs.SD↗

arXiv2025

Lifecycle-Aware code generation: Leveraging Software Engineering Phases in LLMs

Recent progress in large language models (LLMs) has advanced automatic code generation, yet most approaches rely on direct, single-step translation from problem descriptions to code, disregarding structured software engineering practices. We introduce a lifecycle-aware framework that systematically incorporates intermediate artifacts such as requirements analysis, state machine modeling, and pseudocode into both the training and inference stages. This design aligns code generation with standard software development phases and enables more structured reasoning. Experiments show that lifecycle-level fine-tuning improves code correctness by up to 75% over the same model before fine-tuning, with performance gains compounding across intermediate stages. Multi-step inference consistently surpasses single-step generation, demonstrating the effectiveness of intermediate scaffolding. Notably, open-source LLMs, once fine-tuned under our framework, match or slightly outperform models pretrained on code. When applied to DeepSeek-Coder-1.3B, our framework yields relative CodeBLEU improvements of 34.3%, 20.0%, 11.2%, and 22.3% over ChatGPT-3.5, ChatGPT-4o-mini, DeepSeek-R1, and LLaMA-8B, respectively. Our pipeline also proves robust with up to 80\% less training data, confirming its resilience. Ablation studies further reveal that each intermediate artifact contributes distinctly to final code quality, with state machine modeling yielding the most substantial impact. Our source code and detailed experimental data are available at https://anonymous.4open.science/r/Lifecycle-Aware-3CCB.

cs.SE↗

arXiv2025

R2-SVC: Towards Real-World Robust and Expressive Zero-shot Singing Voice Conversion

In real-world singing voice conversion (SVC) applications, environmental noise and the demand for expressive output pose significant challenges. Conventional methods, however, are typically designed without accounting for real deployment scenarios, as both training and inference usually rely on clean data. This mismatch hinders practical use, given the inevitable presence of diverse noise sources and artifacts from music separation. To tackle these issues, we propose R2-SVC, a robust and expressive SVC framework. First, we introduce simulation-based robustness enhancement through random fundamental frequency ($F_0$) perturbations and music separation artifact simulations (e.g., reverberation, echo), substantially improving performance under noisy conditions. Second, we enrich speaker representation using domain-specific singing data: alongside clean vocals, we incorporate DNSMOS-filtered separated vocals and public singing corpora, enabling the model to preserve speaker timbre while capturing singing style nuances. Third, we integrate the Neural Source-Filter (NSF) model to explicitly represent harmonic and noise components, enhancing the naturalness and controllability of converted singing. R2-SVC achieves state-of-the-art results on multiple SVC benchmarks under both clean and noisy conditions.

cs.SD↗

arXiv2025

Thermofield Theory of Large $N$ Matrix Models

We develop analytical and numerical methods for the matrix thermofield in the large $N$ limit. Through the double collective representation on the Schwinger-Keldysh contour, it provides thermodynamical properties and finite temperature correlation functions, for large $N$ matrix quantum systems.

hep-th↗

arXiv2025

DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis

While recent video-to-audio (V2A) models can generate realistic background audio from visual input, they largely overlook speech, an essential part of many video soundtracks. This paper proposes a new task, video-to-soundtrack (V2ST) generation, which aims to jointly produce synchronized background audio and speech within a unified framework. To tackle V2ST, we introduce DualDub, a unified framework built on a multimodal language model that integrates a multimodal encoder, a cross-modal aligner, and dual decoding heads for simultaneous background audio and speech generation. Specifically, our proposed cross-modal aligner employs causal and non-causal attention mechanisms to improve synchronization and acoustic harmony. Besides, to handle data scarcity, we design a curriculum learning strategy that progressively builds the multimodal capability. Finally, we introduce DualBench, the first benchmark for V2ST evaluation with a carefully curated test set and comprehensive metrics. Experimental results demonstrate that DualDub achieves state-of-the-art performance, generating high-quality and well-synchronized soundtracks with both speech and background audio.

cs.MM↗

arXiv2025

MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing

Current movie dubbing technology can produce the desired speech using a reference voice and input video, maintaining perfect synchronization with the visuals while effectively conveying the intended emotions. However, crucial aspects of movie dubbing, including adaptation to various dubbing styles, effective handling of dialogue, narration, and monologues, as well as consideration of subtle details such as speaker age and gender, remain insufficiently explored. To tackle these challenges, we introduce a multi-modal generative framework. First, it utilizes a multi-modal large vision-language model (VLM) to analyze visual inputs, enabling the recognition of dubbing types and fine-grained attributes. Second, it produces high-quality dubbing using large speech generation models, guided by multi-modal inputs. Additionally, a movie dubbing dataset with annotations for dubbing types and subtle details is constructed to enhance movie understanding and improve dubbing quality for the proposed multi-modal framework. Experimental results across multiple benchmark datasets show superior performance compared to state-of-the-art (SOTA) methods. In details, the LSE-D, SPK-SIM, EMO-SIM, and MCD exhibit improvements of up to 1.09%, 8.80%, 19.08%, and 18.74%, respectively.

cs.MM↗

arXiv2025

Towards Film-Making Production Dialogue, Narration, Monologue Adaptive Moving Dubbing Benchmarks

Movie dubbing has advanced significantly, yet assessing the real-world effectiveness of these models remains challenging. A comprehensive evaluation benchmark is crucial for two key reasons: 1) Existing metrics fail to fully capture the complexities of dialogue, narration, monologue, and actor adaptability in movie dubbing. 2) A practical evaluation system should offer valuable insights to improve movie dubbing quality and advancement in film production. To this end, we introduce Talking Adaptive Dubbing Benchmarks (TA-Dubbing), designed to improve film production by adapting to dialogue, narration, monologue, and actors in movie dubbing. TA-Dubbing offers several key advantages: 1) Comprehensive Dimensions: TA-Dubbing covers a variety of dimensions of movie dubbing, incorporating metric evaluations for both movie understanding and speech generation. 2) Versatile Benchmarking: TA-Dubbing is designed to evaluate state-of-the-art movie dubbing models and advanced multi-modal large language models. 3) Full Open-Sourcing: We fully open-source TA-Dubbing at https://github.com/woka- 0a/DeepDubber- V1 including all video suits, evaluation methods, annotations. We also continuously integrate new movie dubbing models into the TA-Dubbing leaderboard at https://github.com/woka- 0a/DeepDubber-V1 to drive forward the field of movie dubbing.

cs.LG↗

arXiv2025

DeepDubber-V1: Towards High Quality and Dialogue, Narration, Monologue Adaptive Movie Dubbing Via Multi-Modal Chain-of-Thoughts Reasoning Guidance

Current movie dubbing technology can generate the desired voice from a given speech prompt, ensuring good synchronization between speech and visuals while accurately conveying the intended emotions. However, in movie dubbing, key aspects such as adapting to different dubbing styles, handling dialogue, narration, and monologue effectively, and understanding subtle details like the age and gender of speakers, have not been well studied. To address this challenge, we propose a framework of multi-modal large language model. First, it utilizes multimodal Chain-of-Thought (CoT) reasoning methods on visual inputs to understand dubbing styles and fine-grained attributes. Second, it generates high-quality dubbing through large speech generation models, guided by multimodal conditions. Additionally, we have developed a movie dubbing dataset with CoT annotations. The evaluation results demonstrate a performance improvement over state-of-the-art methods across multiple datasets. In particular, for the evaluation metrics, the SPK-SIM and EMO-SIM increases from 82.48% to 89.74%, 66.24% to 78.88% for dubbing setting 2.0 on V2C Animation dataset, LSE-D and MCD-SL decreases from 14.79 to 14.63, 5.24 to 4.74 for dubbing setting 2.0 on Grid dataset, SPK-SIM increases from 64.03 to 83.42 and WER decreases from 52.69% to 23.20% for initial reasoning setting on proposed CoT-Movie-Dubbing dataset in the comparison with the state-of-the art models.

cs.CV↗

arXiv2025

DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation

Currently, high-quality, synchronized audio is synthesized using various multi-modal joint learning frameworks, leveraging video and optional text inputs. In the video-to-audio benchmarks, video-to-audio quality, semantic alignment, and audio-visual synchronization are effectively achieved. However, in real-world scenarios, speech and audio often coexist in videos simultaneously, and the end-to-end generation of synchronous speech and audio given video and text conditions are not well studied. Therefore, we propose an end-to-end multi-modal generation framework that simultaneously produces speech and audio based on video and text conditions. Furthermore, the advantages of video-to-audio (V2A) models for generating speech from videos remain unclear. The proposed framework, DeepAudio, consists of a video-to-audio (V2A) module, a text-to-speech (TTS) module, and a dynamic mixture of modality fusion (MoF) module. In the evaluation, the proposed end-to-end framework achieves state-of-the-art performance on the video-audio benchmark, video-speech benchmark, and text-speech benchmark. In detail, our framework achieves comparable results in the comparison with state-of-the-art models for the video-audio and text-speech benchmarks, and surpassing state-of-the-art models in the video-speech benchmark, with WER 16.57% to 3.15% (+80.99%), SPK-SIM 78.30% to 89.38% (+14.15%), EMO-SIM 66.24% to 75.56% (+14.07%), MCD 8.59 to 7.98 (+7.10%), MCD SL 11.05 to 9.40 (+14.93%) across a variety of dubbing settings.

cs.CV↗

arXiv2024

YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls

Generating sound effects for product-level videos, where only a small amount of labeled data is available for diverse scenes, requires the production of high-quality sounds in few-shot settings. To tackle the challenge of limited labeled data in real-world scenes, we introduce YingSound, a foundation model designed for video-guided sound generation that supports high-quality audio generation in few-shot settings. Specifically, YingSound consists of two major modules. The first module uses a conditional flow matching transformer to achieve effective semantic alignment in sound generation across audio and visual modalities. This module aims to build a learnable audio-visual aggregator (AVA) that integrates high-resolution visual features with corresponding audio features at multiple stages. The second module is developed with a proposed multi-modal visual-audio chain-of-thought (CoT) approach to generate finer sound effects in few-shot settings. Finally, an industry-standard video-to-audio (V2A) dataset that encompasses various real-world scenarios is presented. We show that YingSound effectively generates high-quality synchronized sounds across diverse conditional inputs through automated evaluations and human studies. Project Page: \url{https://giantailab.github.io/yingsound/}

cs.SD↗

arXiv2024

Bailing-TTS: Chinese Dialectal Speech Synthesis Towards Human-like Spontaneous Representation

Large-scale text-to-speech (TTS) models have made significant progress recently.However, they still fall short in the generation of Chinese dialectal speech. Toaddress this, we propose Bailing-TTS, a family of large-scale TTS models capable of generating high-quality Chinese dialectal speech. Bailing-TTS serves as a foundation model for Chinese dialectal speech generation. First, continual semi-supervised learning is proposed to facilitate the alignment of text tokens and speech tokens. Second, the Chinese dialectal representation learning is developed using a specific transformer architecture and multi-stage training processes. With the proposed design of novel network architecture and corresponding strategy, Bailing-TTS is able to generate Chinese dialectal speech from text effectively and efficiently. Experiments demonstrate that Bailing-TTS generates Chinese dialectal speech towards human-like spontaneous representation. Readers are encouraged to listen to demos at \url{https://c9412600.github.io/bltts_tech_report/index.html}.

cs.CL↗

arXiv2024

Sybil-Proof Mechanism for Information Propagation with Budgets

This paper examines the problem of distributing rewards on social networks to improve the efficiency of crowdsourcing tasks for sponsors. To complete the tasks efficiently, we aim to design reward mechanisms that incentivize early-joining agents to invite more participants to the tasks. Nonetheless, participants could potentially engage in strategic behaviors, e.g., not inviting others to the tasks, misreporting their capacity for the tasks, or creaking fake identities (aka Sybil attacks), to maximize their own rewards. The focus of this study is to address the challenge outlined above by designing effective reward mechanisms. To this end, we propose a novel reward mechanism, called Propagation Reward Distribution Mechanism (PRDM), for the general information propagation model with limited budgets. It is proved that the PRDM can not only incentivize all agents to contribute their full efforts to the tasks and share the task information to all their neighbors in the social networks, but can also prevent them from Sybil attacks.

cs.GT↗

arXiv2023

Symmetries and the Hilbert Space of Large $N$ Extended States

We discuss the large $N$ expansion in backgrounds of extended states with focus on implementation of Goldstone symmetries and the construction of the associated Hilbert space. The formulation is given in the general framework of collective field theory. Case of translational symmetry is described first, as the basic example. The large $N$ thermofield represents the main topics, with the emergent dynamics of Left-Right bulk fields and collective symmetry coordinates. These give the basis for a $1/N$ expansion.

hep-th↗