arXiv subjects

Jianqing Gao

Publications and source records attributed to Jianqing Gao.

At least 19 recordsLinked to original sources

arXiv2026

Dynamic Prosody Prediction in LLM-based TTS for Improving Speaker Similarity

Personalized text-to-speech (TTS) aims to clone the target speaker in the synthesized speech, imitating both the voice and speaking style. Current large language model (LLM)-based TTS methods ignore the style-specific prosodic patterns in generated speech, resulting in deficient style learning and thus limiting speaker similarity in synthesized speech. To this end, we investigate the prosody learning conditioned on the synthesized speech, and propose to predict the prosody of the current syllable based on previously predicted speech. Experimental results obtained on three datasets demonstrated the efficacy of the proposed dynamic prosody prediction method in enhancing the prosody learning capability, thereby improving the speaker similarity of the generated speech. Audio samples are available at https://muzw.github.io/dynapros/.

eess.AS↗

arXiv2026

The USTC-NERCSLIP Systems for the CHiME-9 MCoRec Challenge

This report details our submission to the CHiME-9 MCoRec Challenge on recognizing and clustering multiple concurrent natural conversations within indoor social settings. Unlike conventional meetings centered on a single shared topic, this scenario contains multiple parallel dialogues--up to eight speakers across up to four simultaneous conversations--with a speech overlap rate exceeding 90%. To tackle this, we propose a multimodal cascaded system that leverages per-speaker visual streams extracted from synchronized 360 degree video together with single-channel audio. Our system improves three components of the pipeline by leveraging enhanced audio-visual pretrained models: Active Speaker Detection (ASD), Audio-Visual Target Speech Extraction (AVTSE), and Audio-Visual Speech Recognition (AVSR). The AVSR module further incorporates Whisper and LLM techniques to boost transcription accuracy. Our best single cascaded system achieves a Speaker Word Error Rate (WER) of 32.44% on the development set. By further applying ROVER to fuse outputs from diverse front-end and back-end variants, we reduce Speaker WER to 31.40%. Notably, our LLM-based zero-shot conversational clustering achieves a speaker clustering F1 score of 1.0, yielding a final Joint ASR-Clustering Error Rate (JACER) of 15.70%.

eess.AS↗

arXiv2026

Adapting Speech Foundation Models for Unified Multimodal Speech Recognition with Large Language Models

While speech foundation models (SFMs) have demonstrated remarkable performance in audio-only tasks, their adaptation to multimodal scenarios remains underexplored. This work presents UASR-LLM, a novel framework that adapts frozen SFMs to unified visual speech recognition (VSR), automatic speech recognition (ASR), and audio-visual speech recognition (AVSR) by leveraging large language models (LLMs) as text decoders. Visual representations are injected into multiple SFM layers via visual injection modules, enabling multimodal fusion and unified representation learning. The augmented SFMs are connected to decoder-only LLMs through a feed-forward adaptor, where concatenated representations and instruction prompts guide transcription. We propose a two-stage training strategy consisting of visual injection pretraining followed by speech recognition finetuning. The pretraining stage aligns audio, visual, and audio-visual representations within the frozen SFM backbone, while the finetuning stage integrates LLMs for unified optimization across speech recognition tasks. Experimental results demonstrate superior performance over state-of-the-art baselines across VSR, ASR, and AVSR under both clean and noisy conditions. Ablation studies further confirm generalization across various SFMs and LLMs, validating the effectiveness of the proposed training strategy.

eess.AS↗

arXiv2026

THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

Large Language Models (LLMs) have made remarkable progress in mathematical reasoning, but still continue to struggle with high-precision tasks like numerical computation and formal symbolic manipulation. Integrating external tools has emerged as a promising approach to bridge this gap. Despite recent advances, existing methods struggle with three key challenges: constructing tool-integrated reasoning data, performing fine-grained optimization, and enhancing inference. To overcome these limitations, we propose THOR (Tool-Integrated Hierarchical Optimization via RL). First, we introduce TIRGen, a multi-agent based pipeline for constructing high-quality datasets of tool-integrated reasoning paths, aligning with the policy and generalizing well across diverse models. Second, to perform fine-grained hierarchical optimization, we introduce an RL strategy that jointly optimizes for both episode-level problem solving and step-level code generation. This is motivated by our key insight that the success of an intermediate tool call is a strong predictor of the final answer's correctness. Finally, THOR incorporates a self-correction mechanism that leverages immediate tool feedback to dynamically revise erroneous reasoning paths during inference. Our approach demonstrates strong generalization across diverse models, performing effectively in both reasoning and non-reasoning models. It further achieves state-of-the-art performance for models of a similar scale on multiple mathematical benchmarks, while also delivering consistent improvements on code benchmarks. Our code will be publicly available at https://github.com/JingMog/THOR.

cs.AI↗

arXiv2026

Rethinking Practical and Efficient Quantization Calibration for Vision-Language Models

Post-training quantization (PTQ) is a primary approach for deploying large language models without fine-tuning, and the quantized performance is often strongly affected by the calibration in PTQ. By contrast, in vision-language models (VLMs), substantial differences between visual and text tokens in their activation distributions and sensitivities to quantization error pose significant challenges for effective calibration during PTQ. In this work, we rethink what PTQ calibration should align with in VLMs and propose the Token-level Importance-aware Layer-wise Quantization framework (TLQ). Guided by gradient information, we design a token-level importance integration mechanism for quantization error, and use it to construct a token-level calibration set, enabling a more fine-grained calibration strategy. Furthermore, TLQ introduces a multi-GPU, quantization-exposed layer-wise calibration scheme. This scheme keeps the layer-wise calibration procedure consistent with the true quantized inference path and distributes the complex layer-wise calibration workload across multiple RTX3090 GPUs, thereby reducing reliance on the large memory of A100 GPUs. TLQ is evaluated across two models, three model scales, and two quantization settings, consistently achieving performance improvements across all settings, indicating its strong quantization stability. The code will be released publicly.

cs.CV↗

arXiv2026

Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization

Recent advances have demonstrated the potential of decoderonly large language models (LLMs) for automatic speech recognition (ASR). However, enabling streaming recognition within this framework remains a challenge. In this work, we propose a novel streaming ASR approach that integrates a read/write policy network with monotonic chunkwise attention (MoChA) to dynamically segment speech embeddings. These segments are interleaved with label sequences during training, enabling seamless integration with the LLM. During inference, the audio stream is buffered until the MoChA module triggers a read signal, at which point the buffered segment together with the previous token is fed into the LLM for the next token prediction. We also introduce a minimal-latency training objective to guide the policy network toward accurate segmentation boundaries. Furthermore, we adopt a joint training strategy in which a non-streaming LLM-ASR model and our streaming model share parameters. Experiments on the AISHELL-1 and AISHELL-2 Mandarin benchmarks demonstrate that our method consistently outperforms recent streaming ASR baselines, achieving character error rates of 5.1% and 5.5%, respectively. The latency optimization results in a 62.5% reduction in average token generation delay with negligible impact on recognition accuracy

eess.AS↗

arXiv2026

SLM-SS: Speech Language Model for Generative Speech Separation

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals, which can negatively affect the performance of downstream tasks such as speech recognition. In this work, we propose SLM-SS, a novel approach that applies speech language models to SS, aiming to enhance the intelligibility and coherence of the separated signals. We frame SS as discrete multi-codebook sequence generation, using Encoder-Decoder models to map quantized speech mixtures to target tokens. In addition to the autoregressive modeling strategy, we introduce a non-autoregressive model to improve decoding efficiency for residual tokens. Experimental results on the LibriMix dataset demonstrate that our approach shows significantly better preservation of speech intelligibility, leading to improved linguistic consistency in a variety of downstream tasks compared to existing approaches.

cs.SD↗

arXiv2025

Hallucination as a Computational Boundary: A Hierarchy of Inevitability and the Oracle Escape

The illusion phenomenon of large language models (LLMs) is the core obstacle to their reliable deployment. This article formalizes the large language model as a probabilistic Turing machine by constructing a "computational necessity hierarchy", and for the first time proves the illusions are inevitable on diagonalization, incomputability, and information theory boundaries supported by the new "learner pump lemma". However, we propose two "escape routes": one is to model Retrieval Enhanced Generations (RAGs) as oracle machines, proving their absolute escape through "computational jumps", providing the first formal theory for the effectiveness of RAGs; The second is to formalize continuous learning as an "internalized oracle" mechanism and implement this path through a novel neural game theory framework. Finally, this article proposes a feasible new principle for artificial intelligence security - Computational Class Alignment (CCA), which requires strict matching between task complexity and the actual computing power of the system, providing theoretical support for the secure application of artificial intelligence.

cs.AI↗

arXiv2025

Binary-Gaussian: Compact and Progressive Representation for 3D Gaussian Segmentation

3D Gaussian Splatting (3D-GS) has emerged as an efficient 3D representation and a promising foundation for semantic tasks like segmentation. However, existing 3D-GS-based segmentation methods typically rely on high-dimensional category features, which introduce substantial memory overhead. Moreover, fine-grained segmentation remains challenging due to label space congestion and the lack of stable multi-granularity control mechanisms. To address these limitations, we propose a coarse-to-fine binary encoding scheme for per-Gaussian category representation, which compresses each feature into a single integer via the binary-to-decimal mapping, drastically reducing memory usage. We further design a progressive training strategy that decomposes panoptic segmentation into a series of independent sub-tasks, reducing inter-class conflicts and thereby enhancing fine-grained segmentation capability. Additionally, we fine-tune opacity during segmentation training to address the incompatibility between photometric rendering and semantic segmentation, which often leads to foreground-background confusion. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art segmentation performance while significantly reducing memory consumption and accelerating inference.

cs.CV↗

arXiv2025

READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation

The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely limits the practical implementation of diffusion-based talking head generation models. In this study, we propose READ, a real-time diffusion-transformer-based talking head generation framework. Our approach first learns a spatiotemporal highly compressed video latent space via a temporal VAE, significantly reducing the token count to accelerate generation. To achieve better audio-visual alignment within this compressed latent space, a pre-trained Speech Autoencoder (SpeechAE) is proposed to generate temporally compressed speech latent codes corresponding to the video latent space. These latent representations are then modeled by a carefully designed Audio-to-Video Diffusion Transformer (A2V-DiT) backbone for efficient talking head synthesis. Furthermore, to ensure temporal consistency and accelerated inference in extended generation, we propose a novel asynchronous noise scheduler (ANS) for both the training and inference processes of our framework. The ANS leverages asynchronous add-noise and asynchronous motion-guided generation in the latent space, ensuring consistency in generated video clips. Experimental results demonstrate that READ outperforms state-of-the-art methods by generating competitive talking head videos with significantly reduced runtime, achieving an optimal balance between quality and speed while maintaining robust metric stability in long-time generation.

cs.GR↗

arXiv2025

HDA-SELD: Hierarchical Cross-Modal Distillation with Multi-Level Data Augmentation for Low-Resource Audio-Visual Sound Event Localization and Detection

This work presents HDA-SELD, a unified framework that combines hierarchical cross-modal distillation (HCMD) and multi-level data augmentation to address low-resource audio-visual (AV) sound event localization and detection (SELD). An audio-only SELD model acts as the teacher, transferring knowledge to an AV student model through both output responses and intermediate feature representations. To enhance learning, data augmentation is applied by mixing features randomly selected from multiple network layers and associated loss functions tailored to the SELD task. Extensive experiments on the DCASE 2023 and 2024 Challenge SELD datasets show that the proposed method significantly improves AV SELD performance, yielding relative gains of 21%-38% in the overall metric over the baselines. Notably, our proposed HDA-SELD achieves results comparable to or better than teacher models trained on much larger datasets, surpassing state-of-the-art methods on both DCASE 2023 and 2024 Challenge SELD tasks.

cs.SD↗

arXiv2025

Improving Anomalous Sound Detection with Attribute-aware Representation from Domain-adaptive Pre-training

Anomalous Sound Detection (ASD) is often formulated as a machine attribute classification task, a strategy necessitated by the common scenario where only normal data is available for training. However, the exhaustive collection of machine attribute labels is laborious and impractical. To address the challenge of missing attribute labels, this paper proposes an agglomerative hierarchical clustering method for the assignment of pseudo-attribute labels using representations derived from a domain-adaptive pre-trained model, which are expected to capture machine attribute characteristics. We then apply model adaptation to this pre-trained model through supervised fine-tuning for machine attribute classification, resulting in a new state-of-the-art performance. Evaluation on the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge dataset demonstrates that our proposed approach yields significant performance gains, ultimately outperforming our previous top-ranking system in the challenge.

cs.SD↗

arXiv2025

Latent Swap Joint Diffusion for 2D Long-Form Latent Generation

This paper introduces Swap Forward (SaFa), a modality-agnostic and efficient method to generate seamless and coherence long spectrum and panorama through latent swap joint diffusion across multi-views. We first investigate the spectrum aliasing problem in spectrum-based audio generation caused by existing joint diffusion methods. Through a comparative analysis of the VAE latent representation of Mel-spectra and RGB images, we identify that the failure arises from excessive suppression of high-frequency components during the spectrum denoising process due to the averaging operator. To address this issue, we propose Self-Loop Latent Swap, a frame-level bidirectional swap applied to the overlapping region of adjacent views. Leveraging stepwise differentiated trajectories of adjacent subviews, this swap operator adaptively enhances high-frequency components and avoid spectrum distortion. Furthermore, to improve global cross-view consistency in non-overlapping regions, we introduce Reference-Guided Latent Swap, a unidirectional latent swap operator that provides a centralized reference trajectory to synchronize subview diffusions. By refining swap timing and intervals, we can achieve a cross-view similarity-diversity balance in a forward-only manner. Quantitative and qualitative experiments demonstrate that SaFa significantly outperforms existing joint diffusion methods and even training-based methods in audio generation using both U-Net and DiT models, along with effective longer length adaptation. It also adapts well to panorama generation, achieving comparable performance with 2 $\sim$ 20 $\times$ faster speed and greater model generalizability. More generation demos are available at https://swapforward.github.io/

cs.SD↗

arXiv2025

Dual form Complementary Masking for Domain-Adaptive Image Segmentation

Recent works have correlated Masked Image Modeling (MIM) with consistency regularization in Unsupervised Domain Adaptation (UDA). However, they merely treat masking as a special form of deformation on the input images and neglect the theoretical analysis, which leads to a superficial understanding of masked reconstruction and insufficient exploitation of its potential in enhancing feature extraction and representation learning. In this paper, we reframe masked reconstruction as a sparse signal reconstruction problem and theoretically prove that the dual form of complementary masks possesses superior capabilities in extracting domain-agnostic image features. Based on this compelling insight, we propose MaskTwins, a simple yet effective UDA framework that integrates masked reconstruction directly into the main training pipeline. MaskTwins uncovers intrinsic structural patterns that persist across disparate domains by enforcing consistency between predictions of images masked in complementary ways, enabling domain generalization in an end-to-end manner. Extensive experiments verify the superiority of MaskTwins over baseline methods in natural and biological image segmentation. These results demonstrate the significant advantages of MaskTwins in extracting domain-invariant features without the need for separate pre-training, offering a new paradigm for domain-adaptive segmentation.

cs.CV↗

arXiv2025

Quality-aware Masked Diffusion Transformer for Enhanced Music Generation

Text-to-music (TTM) generation, which converts textual descriptions into audio, opens up innovative avenues for multimedia creation. Achieving high quality and diversity in this process demands extensive, high-quality data, which are often scarce in available datasets. Most open-source datasets frequently suffer from issues like low-quality waveforms and low text-audio consistency, hindering the advancement of music generation models. To address these challenges, we propose a novel quality-aware training paradigm for generating high-quality, high-musicality music from large-scale, quality-imbalanced datasets. Additionally, by leveraging unique properties in the latent space of musical signals, we adapt and implement a masked diffusion transformer (MDT) model for the TTM task, showcasing its capacity for quality control and enhanced musicality. Furthermore, we introduce a three-stage caption refinement approach to address low-quality captions' issue. Experiments show state-of-the-art (SOTA) performance on benchmark datasets including MusicCaps and the Song-Describer Dataset with both objective and subjective metrics. Demo audio samples are available at https://qa-mdt.github.io/, code and pretrained checkpoints are open-sourced at https://github.com/ivcylc/OpenMusic.

cs.SD↗

arXiv2025

Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural Integration

Recent advances in Multimodal Large Language Models (MLLMs) have achieved remarkable progress in general domains and demonstrated promise in multimodal mathematical reasoning. However, applying MLLMs to geometry problem solving (GPS) remains challenging due to lack of accurate step-by-step solution data and severe hallucinations during reasoning. In this paper, we propose GeoGen, a pipeline that can automatically generates step-wise reasoning paths for geometry diagrams. By leveraging the precise symbolic reasoning, \textbf{GeoGen} produces large-scale, high-quality question-answer pairs. To further enhance the logical reasoning ability of MLLMs, we train \textbf{GeoLogic}, a Large Language Model (LLM) using synthetic data generated by GeoGen. Serving as a bridge between natural language and symbolic systems, GeoLogic enables symbolic tools to help verifying MLLM outputs, making the reasoning process more rigorous and alleviating hallucinations. Experimental results show that our approach consistently improves the performance of MLLMs, achieving remarkable results on benchmarks for geometric reasoning tasks. This improvement stems from our integration of the strengths of LLMs and symbolic systems, which enables a more reliable and interpretable approach for the GPS task. Codes are available at https://github.com/ycpNotFound/GeoGen.

cs.CL↗

arXiv2025

MMC: Iterative Refinement of VLM Reasoning via MCTS-based Multimodal Critique

Visual language models (VLMs) have demonstrated strong performance across diverse multimodal reasoning tasks but still face challenges such as hallucinations, resulting in incorrect reasoning outcomes. Inspired by recent research on external feedback mechanisms in large language models (LLMs), we propose a multimodal actor-critic framework to enhance VLM reasoning capabilities. Specifically, the actor model generates step-by-step reasoning paths based on image and text inputs, while the critic model evaluates these reasoning paths and provides corrective feedback. The actor model iteratively refines its reasoning based on the feedback until the reasoning outcome is deemed satisfactory by the critic model. To reduce reliance on costly manual annotations, we introduce an automated method for constructing multimodal critique datasets. By leveraging Monte Carlo Tree Search (MCTS), we systematically guide the actor model to explore diverse reasoning paths. To obtain critique data for correcting erroneous reasoning steps, we prompt an annotator model to compare pairs of reasoning paths diverging from a shared ancestor node - one leading to a correct conclusion and the other to an incorrect one. This approach enables us to construct the MMC (MCTS-based Multimodal Critique) dataset, upon which we further develop a comprehensive training and inference pipeline. Extensive experiments conducted on several public benchmark datasets and mainstream VLMs demonstrate that our approach significantly improves the performance of VLM on complex multimodal reasoning tasks, underscoring its effectiveness and wide applicability.

cs.MM↗

arXiv2025

PRM-BAS: Enhancing Multimodal Reasoning through PRM-guided Beam Annealing Search

Recent work increasingly focuses on improving the reasoning capabilities of Multimodal Large Language Models (MLLMs). Among existing methods, Process Reward Models (PRMs) stand out for offering dense, step-wise supervision to guide intermediate reasoning. However, how to effectively integrate PRMs into search strategies remains an open question. In this paper, we introduce PRM-BAS (PRM-Guided Beam Annealing Search), a lightweight approach for PRM-guided reasoning that dynamically adjusts beam size -- starting with a broader search space and gradually narrowing it as contextual information accumulates, thereby balancing performance and efficiency. We further propose a unified framework for data construction and PRM training. Specifically, we construct the PRM-BAS-300k dataset by selecting 300k questions from existing datasets and performing rollouts at each step to estimate the probability of reaching a correct final answer. The PRM is then trained using a combination of value loss for absolute action quality and rank loss for relative action quality. Extensive experiments on challenging multimodal reasoning benchmarks demonstrate that PRM-BAS significantly improves reasoning performance while maintaining low computational cost. Moreover, it generalizes well across different model scales and architectures, showcasing strong robustness and plug-and-play capability.

cs.MM↗