Pengfei Cai

Yuejiao Wang, Zihao Ji, Pengfei Cai et al.

Recent advances in neural song generation have enabled high-quality synthesis from lyrics and global textual prompts. However, most systems fail to model temporally varying attributes of songs, severely limiting fine-grained control over musical structure and dynamics. To address this, we propose SegTune, a Diffusion Transformer-based framework enabling structured and fine-grained controllability by allowing users or large language models (LLMs) to specify local musical descriptions aligned to song segments. These segment prompts are temporally broadcast to corresponding time windows, while global prompts ensure stylistic coherence. To support precise lyric-to-music alignment, we introduce an LLM-based duration predictor that autoregressively generates sentence-level timestamps in LyRiCs format. We further construct a large-scale data pipeline for high-quality song collection with aligned lyrics and prompts, and propose new metrics to evaluate segment alignment and vocal consistency. Experiments demonstrate that SegTune outperforms existing baselines in both musicality and controllability. Visit our project page (https://github.com/KlingAIResearch/SegTune) for codes and more generated songs.

Pengfei Cai, Joanna Wang, Haorui Zheng et al.

Recent advancements in song generation have shown promising results in generating songs from lyrics and/or global text prompts. However, most existing systems lack the ability to model the temporally varying attributes of songs, limiting fine-grained control over musical structure and dynamics. In this paper, we propose SegTune, a non-autoregressive framework for structured and controllable song generation. SegTune enables segment-level control by allowing users or large language models to specify local musical descriptions aligned to song sections.The segmental prompts are injected into the model by temporally broadcasting them to corresponding time windows, while global prompts influence the whole song to ensure stylistic coherence. To obtain accurate segment durations and enable precise lyric-to-music alignment, we introduce an LLM-based duration predictor that autoregressively generates sentence-level timestamped lyrics in LRC format. We further construct a large-scale data pipeline for collecting high-quality songs with aligned lyrics and prompts, and propose new evaluation metrics to assess segment-level alignment and vocal attribute consistency. Experimental results show that SegTune achieves superior controllability and musical coherence compared to existing baselines. See https://cai525.github.io/SegTune_demo for demos of our work.

Pengfei Cai, Yan Song, Kang Li et al.

Sound event detection (SED) methods that leverage a large pre-trained Transformer encoder network have shown promising performance in recent DCASE challenges. However, they still rely on an RNN-based context network to model temporal dependencies, largely due to the scarcity of labeled data. In this work, we propose a pure Transformer-based SED model with masked-reconstruction based pre-training, termed MAT-SED. Specifically, a Transformer with relative positional encoding is first designed as the context network, pre-trained by the masked-reconstruction task on all available target data in a self-supervised way. Both the encoder and the context network are jointly fine-tuned in a semi-supervised manner. Furthermore, a global-local feature fusion strategy is proposed to enhance the localization capability. Evaluation of MAT-SED on DCASE2023 task4 surpasses state-of-the-art performance, achieving 0.587/0.896 PSDS1/PSDS2 respectively.

Pengfei Cai, Yan Song, Nan Jiang et al.

A significant challenge in sound event detection (SED) is the effective utilization of unlabeled data, given the limited availability of labeled data due to high annotation costs. Semi-supervised algorithms rely on labeled data to learn from unlabeled data, and the performance is constrained by the quality and size of the former. In this paper, we introduce the Prototype based Masked Audio Model~(PMAM) algorithm for self-supervised representation learning in SED, to better exploit unlabeled data. Specifically, semantically rich frame-level pseudo labels are constructed from a Gaussian mixture model (GMM) based prototypical distribution modeling. These pseudo labels supervise the learning of a Transformer-based masked audio model, in which binary cross-entropy loss is employed instead of the widely used InfoNCE loss, to provide independent loss contributions from different prototypes, which is important in real scenarios in which multiple labels may apply to unsupervised data frames. A final stage of fine-tuning with just a small amount of labeled data yields a very high performing SED model. On like-for-like tests using the DESED task, our method achieves a PSDS1 score of 62.5\%, surpassing current state-of-the-art models and demonstrating the superiority of the proposed technique.

Yihao Chen, Haochen Wu, Nan Jiang et al.

This paper describes the USTC-KXDIGIT system submitted to the ASVspoof5 Challenge for Track 1 (speech deepfake detection) and Track 2 (spoofing-robust automatic speaker verification, SASV). Track 1 showcases a diverse range of technical qualities from potential processing algorithms and includes both open and closed conditions. For these conditions, our system consists of a cascade of a frontend feature extractor and a back-end classifier. We focus on extensive embedding engineering and enhancing the generalization of the back-end classifier model. Specifically, the embedding engineering is based on hand-crafted features and speech representations from a self-supervised model, used for closed and open conditions, respectively. To detect spoof attacks under various adversarial conditions, we trained multiple systems on an augmented training set. Additionally, we used voice conversion technology to synthesize fake audio from genuine audio in the training set to enrich the synthesis algorithms. To leverage the complementary information learned by different model architectures, we employed activation ensemble and fused scores from different systems to obtain the final decision score for spoof detection. During the evaluation phase, the proposed methods achieved 0.3948 minDCF and 14.33% EER in the close condition, and 0.0750 minDCF and 2.59% EER in the open condition, demonstrating the robustness of our submitted systems under adversarial conditions. In Track 2, we continued using the CM system from Track 1 and fused it with a CNN-based ASV system. This approach achieved 0.2814 min-aDCF in the closed condition and 0.0756 min-aDCF in the open condition, showcasing superior performance in the SASV system.

Jun Wang, Xijuan Zeng, Chunyu Qiang et al.

We propose Kling-Foley, a large-scale multimodal Video-to-Audio generation model that synthesizes high-quality audio synchronized with video content. In Kling-Foley, we introduce multimodal diffusion transformers to model the interactions between video, audio, and text modalities, and combine it with a visual semantic representation module and an audio-visual synchronization module to enhance alignment capabilities. Specifically, these modules align video conditions with latent audio elements at the frame level, thereby improving semantic alignment and audio-visual synchronization. Together with text conditions, this integrated approach enables precise generation of video-matching sound effects. In addition, we propose a universal latent audio codec that can achieve high-quality modeling in various scenarios such as sound effects, speech, singing, and music. We employ a stereo rendering method that imbues synthesized audio with a spatial presence. At the same time, in order to make up for the incomplete types and annotations of the open-source benchmark, we also open-source an industrial-level benchmark Kling-Audio-Eval. Our experiments show that Kling-Foley trained with the flow matching objective achieves new audio-visual SOTA performance among public models in terms of distribution matching, semantic alignment, temporal alignment and audio quality.

Yanfeng Shi, Pengfei Cai, Jun Liu et al.

Large Audio-Language Models (LALMs) enable general audio understanding and demonstrate remarkable performance across various audio tasks. However, these models still face challenges in temporal perception (e.g., inferring event onset and offset), leading to limited utility in fine-grained scenarios. To address this issue, we propose Audio-Side Time Prompt and leverage Reinforcement Learning (RL) to develop the TimePro-RL framework for fine-grained temporal perception. Specifically, we encode timestamps as embeddings and interleave them within the audio feature sequence as temporal coordinates to prompt the model. Furthermore, we introduce RL following Supervised Fine-Tuning (SFT) to directly optimize temporal alignment performance. Experiments demonstrate that TimePro-RL achieves significant performance gains across a range of audio temporal tasks, such as audio grounding, sound event detection, and dense audio captioning, validating its robust effectiveness.

Ian McLoughlin, Lam Pham, Yan Song et al.

Spectrogram-based representations have grown to dominate the feature space for deep learning audio analysis systems, and are often adopted for speech analysis also. Initially, the primary motivator for spectrogram-based representations was their ability to present sound as a two dimensional signal in the time-frequency plane, which not only provides an interpretable physical basis for analysing sound, but also unlocks the use of a wide range of machine learning techniques such as convolutional neural networks, that had been developed for image processing. A spectrogram is a matrix characterised by the resolution and span of its two dimensions, as well as by the representation and scaling of each element. Many possibilities for these three characteristics have been explored by researchers across numerous application areas, with different settings showing affinity for various tasks. This paper reviews the use of spectrogram-based representations and surveys the state-of-the-art to question how front-end feature representation choice allies with back-end classifier architecture for different tasks.

Utkarsh Utkarsh, Pengfei Cai, Alan Edelman et al.

Deep generative models have recently been applied to physical systems governed by partial differential equations (PDEs), offering scalable simulation and uncertainty-aware inference. However, enforcing physical constraints, such as conservation laws (linear and nonlinear) and physical consistencies, remains challenging. Existing methods often rely on soft penalties or architectural biases that fail to guarantee hard constraints. In this work, we propose Physics-Constrained Flow Matching (PCFM), a zero-shot inference framework that enforces arbitrary nonlinear constraints in pretrained flow-based generative models. PCFM continuously guides the sampling process through physics-based corrections applied to intermediate solution states, while remaining aligned with the learned flow and satisfying physical constraints. Empirically, PCFM outperforms both unconstrained and constrained baselines on a range of PDEs, including those with shocks, discontinuities, and sharp features, while ensuring exact constraint satisfaction at the final solution. Our method provides a general framework for enforcing hard constraints in both scientific and general-purpose generative models, especially in applications where constraint satisfaction is essential.

Qibang Liu, Pengfei Cai, Diab Abueidda et al.

Under some initial and boundary conditions, the rapid reaction-thermal diffusion process taking place during frontal polymerization (FP) destabilizes the planar mode of front propagation, leading to spatially varying, complex hierarchical patterns in thermoset polymeric materials. Although modern reaction-diffusion models can predict the patterns resulting from unstable FP, the inverse design of patterns, which aims to retrieve process conditions that produce a desired pattern, remains an open challenge due to the non-unique and non-intuitive mapping between process conditions and manufactured patterns. In this work, we propose a probabilistic generative model named univariate conditional variational autoencoder (UcVAE) for the inverse design of hierarchical patterns in FP-based manufacturing. Unlike the cVAE, which encodes both the design space and the design target, the UcVAE encodes only the design space. In the encoder of the UcVAE, the number of training parameters is significantly reduced compared to the cVAE, resulting in a shorter training time while maintaining comparable performance. Given desired pattern images, the trained UcVAE can generate multiple process condition solutions that produce high-fidelity hierarchical patterns.

Pengfei Cai, Yan Song, Qing Gu et al.

Most existing sound event detection~(SED) algorithms operate under a closed-set assumption, restricting their detection capabilities to predefined classes. While recent efforts have explored language-driven zero-shot SED by exploiting audio-language models, their performance is still far from satisfactory due to the lack of fine-grained alignment and cross-modal feature fusion. In this work, we propose the Detect Any Sound Model (DASM), a query-based framework for open-vocabulary SED guided by multi-modal queries. DASM formulates SED as a frame-level retrieval task, where audio features are matched against query vectors derived from text or audio prompts. To support this formulation, DASM introduces a dual-stream decoder that explicitly decouples event recognition and temporal localization: a cross-modality event decoder performs query-feature fusion and determines the presence of sound events at the clip-level, while a context network models temporal dependencies for frame-level localization. Additionally, an inference-time attention masking strategy is proposed to leverage semantic relations between base and novel classes, substantially enhancing generalization to novel classes. Experiments on the AudioSet Strong dataset demonstrate that DASM effectively balances localization accuracy with generalization to novel classes, outperforming CLAP-based methods in open-vocabulary setting (+ 7.8 PSDS) and the baseline in the closed-set setting (+ 6.9 PSDS). Furthermore, in cross-dataset zero-shot evaluation on DESED, DASM achieves a PSDS1 score of 42.2, even exceeding the supervised CRNN baseline. The project page is available at https://cai525.github.io/Transformer4SED/demo_page/DASM/.