Latent Flow Matching for Expressive Singing Voice Synthesis

Conditional variational autoencoder (cVAE)-based singing voice synthesis provides efficient inference and strong audio quality by learning a score-conditioned prior and a recording-conditioned posterior latent space. However, because synthesis relies on prior samples while training uses posterior latents inferred from real recordings, imperfect distribution matching can cause a prior-posterior mismatch that degrades fine-grained expressiveness such as vibrato and micro-prosody. We propose FM-Singer, which introduces conditional flow matching (CFM) in latent space to learn a continuous vector field transporting prior latents toward posterior latents along an optimal-transport-inspired path. At inference time, the learned latent flow refines a prior sample by solving an ordinary differential equation (ODE) before waveform generation, improving expressiveness while preserving the efficiency of parallel decoding. Experiments on Korean and Chinese singing datasets demonstrate consistent improvements over strong baselines, including lower mel-cepstral distortion and fundamental-frequency error and higher perceptual scores on the Korean dataset. Code, pretrained checkpoints, and audio demos are available at https://github.com/alsgur9368/FM-Singer

Pose-Guided Residual Refinement for Interpretable Text-to-Motion Generation and Editing

Text-based 3D motion generation aims to automatically synthesize diverse motions from natural-language descriptions to extend user creativity, whereas motion editing modifies an existing motion sequence in response to text while preserving its overall structure. Pose-code-based frameworks such as CoMo map quantifiable pose attributes into discrete pose codes that support interpretable motion control, but their frame-wise representation struggles to capture subtle temporal dynamics and high-frequency details, often degrading reconstruction fidelity and local controllability. To address this limitation, we introduce pose-guided residual refinement for motion (PGR$^2$M), a hybrid representation that augments interpretable pose codes with residual codes learned via residual vector quantization (RVQ). A pose-guided RVQ tokenizer decomposes motion into pose latents that encode coarse global structure and residual latents that model fine-grained temporal variations. Residual dropout further discourages over-reliance on residuals, preserving the semantic alignment and editability of the pose codes. On top of this tokenizer, a base Transformer autoregressively predicts pose codes from text, and a refine Transformer predicts residual codes conditioned on text, pose codes, and quantization stage. Experiments on HumanML3D and KIT-ML show that PGR$^2$M improves Fréchet inception distance and reconstruction metrics for both generation and editing compared with CoMo and recent diffusion- and tokenization-based baselines, while user studies confirm that it enables intuitive, structure-preserving motion edits.

Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions

We introduce a new music source separation model tailored for accurate vocal isolation. Unlike Transformer-based approaches, which often fail to capture intermittently occurring vocals, our model leverages Mamba2, a recent state space model, to better capture long-range temporal dependencies. To handle long input sequences efficiently, we combine a band-splitting strategy with a dual-path architecture. Experiments show that our approach outperforms recent state-of-the-art models, achieving a cSDR of 11.03 dB-the best reported to date-and delivering substantial gains in uSDR. Moreover, the model exhibits stable and consistent performance across varying input lengths and vocal occurrence patterns. These results demonstrate the effectiveness of Mamba-based models for high-resolution audio processing and open up new directions for broader applications in audio research.

Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization

Recent progress in text-to-motion has advanced both 3D human motion generation and text-based motion control. Controllable motion generation (CoMo), which enables intuitive control, typically relies on pose code representations, but discrete pose codes alone cannot capture fine-grained motion details, limiting expressiveness. To overcome this, we propose a method that augments pose code-based latent representations with continuous motion features using residual vector quantization (RVQ). This design preserves the interpretability and manipulability of pose codes while effectively capturing subtle motion characteristics such as high-frequency details. Experiments on the HumanML3D dataset show that our model reduces Frechet inception distance (FID) from 0.041 to 0.015 and improves Top-1 R-Precision from 0.508 to 0.510. Qualitative analysis of pairwise direction similarity between pose codes further confirms the model's controllability for motion editing.

RingFormer: A Neural Vocoder with Ring Attention and Convolution-Augmented Transformer

While transformers demonstrate outstanding performance across various audio tasks, their application to neural vocoders remains challenging. Neural vocoders require the generation of long audio signals at the sample level, which demands high temporal resolution. This results in significant computational costs for attention map generation and limits their ability to efficiently process both global and local information. Additionally, the sequential nature of sample generation in neural vocoders poses difficulties for real-time processing, making the direct adoption of transformers impractical. To address these challenges, we propose RingFormer, a neural vocoder that incorporates the ring attention mechanism into a lightweight transformer variant, the convolution-augmented transformer (Conformer). Ring attention effectively captures local details while integrating global information, making it well-suited for processing long sequences and enabling real-time audio generation. RingFormer is trained using adversarial training with two discriminators. The proposed model is applied to the decoder of the text-to-speech model VITS and compared with state-of-the-art vocoders such as HiFi-GAN, iSTFT-Net, and BigVGAN under identical conditions using various objective and subjective metrics. Experimental results show that RingFormer achieves comparable or superior performance to existing models, particularly excelling in real-time audio generation. Our code and audio samples are available on GitHub.

Synergistic Formulaic Alpha Generation for Quantitative Trading based on Reinforcement Learning

Mining of formulaic alpha factors refers to the process of discovering and developing specific factors or indicators (referred to as alpha factors) for quantitative trading in stock market. To efficiently discover alpha factors in vast search space, reinforcement learning (RL) is commonly employed. This paper proposes a method to enhance existing alpha factor mining approaches by expanding a search space and utilizing pretrained formulaic alpha set as initial seed values to generate synergistic formulaic alpha. We employ information coefficient (IC) and rank information coefficient (Rank IC) as performance evaluation metrics for the model. Using CSI300 market data, we conducted real investment simulations and observed significant performance improvement compared to existing techniques.

Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS

The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this limitation, recent models such as denoising diffusion implicit models (DDIM) focus on generating samples without directly modeling the probability distribution, while models like denoising diffusion generative adversarial networks (GAN) combine diffusion processes with GANs. In the field of speech synthesis, a recent diffusion speech synthesis model called DiffGAN-TTS, utilizing the structure of GANs, has been introduced and demonstrates superior performance in both speech quality and generation speed. In this paper, to further enhance the performance of DiffGAN-TTS, we propose a speech synthesis model with two discriminators: a diffusion discriminator for learning the distribution of the reverse process and a spectrogram discriminator for learning the distribution of the generated data. Objective metrics such as structural similarity index measure (SSIM), mel-cepstral distortion (MCD), F0 root mean squared error (F0 RMSE), short-time objective intelligibility (STOI), perceptual evaluation of speech quality (PESQ), as well as subjective metrics like mean opinion score (MOS), are used to evaluate the performance of the proposed model. The evaluation results show that the proposed model outperforms recent state-of-the-art models such as FastSpeech2 and DiffGAN-TTS in various metrics. Our implementation and audio samples are located on GitHub.

SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer

Expressive speech synthesis models are trained by adding corpora with diverse speakers, various emotions, and different speaking styles to the dataset, in order to control various characteristics of speech and generate the desired voice. In this paper, we propose a style control (SC) VALL-E model based on the neural codec language model (called VALL-E), which follows the structure of the generative pretrained transformer 3 (GPT-3). The proposed SC VALL-E takes input from text sentences and prompt audio and is designed to generate controllable speech by not simply mimicking the characteristics of the prompt audio but by controlling the attributes to produce diverse voices. We identify tokens in the style embedding matrix of the newly designed style network that represent attributes such as emotion, speaking rate, pitch, and voice intensity, and design a model that can control these attributes. To evaluate the performance of SC VALL-E, we conduct comparative experiments with three representative expressive speech synthesis models: global style token (GST) Tacotron2, variational autoencoder (VAE) Tacotron2, and original VALL-E. We measure word error rate (WER), F0 voiced error (FVE), and F0 gross pitch error (F0GPE) as evaluation metrics to assess the accuracy of generated sentences. For comparing the quality of synthesized speech, we measure comparative mean option score (CMOS) and similarity mean option score (SMOS). To evaluate the style control ability of the generated speech, we observe the changes in F0 and mel-spectrogram by modifying the trained tokens. When using prompt audio that is not present in the training data, SC VALL-E generates a variety of expressive sounds and demonstrates competitive performance compared to the existing models. Our implementation, pretrained models, and audio samples are located on GitHub.