Music editing is an important step in music production, which has broad applications, including game development and film production. Most existing zero-shot text-guided editing methods rely on pretrained diffusion models by involving forward-backward diffusion processes. However, these methods often struggle to preserve the musical content. Additionally, text instructions alone usually fail to accurately describe the desired music. In this paper, we propose two music editing methods that improve the consistency between the original and edited music by leveraging score distillation. The first method, SteerMusic, is a coarse-grained zero-shot editing approach using delta denoising score. The second method, SteerMusic+, enables fine-grained personalized music editing by manipulating a concept token that represents a user-defined musical style. SteerMusic+ allows for the editing of music into user-defined musical styles that cannot be achieved by the text instructions alone. Experimental results show that our methods outperform existing approaches in preserving both music content consistency and editing fidelity. User studies further validate that our methods achieve superior music editing quality.

Parameter-Efficient Fine-Tuning (PEFT) of text-to-image models has become an increasingly popular technique with many applications. Among the various PEFT methods, Low-Rank Adaptation (LoRA) and its variants have gained significant attention due to their effectiveness, enabling users to fine-tune models with limited computational resources. However, the approximation gap between the low-rank assumption and desired fine-tuning weights prevents the simultaneous acquisition of ultra-parameter-efficiency and better performance. To reduce this gap and further improve the power of LoRA, we propose a new PEFT method that combines two classes of adaptations, namely, transform and residual adaptations. In specific, we first apply a full-rank and dense transform to the pre-trained weight. This learnable transform is expected to align the pre-trained weight as closely as possible to the desired weight, thereby reducing the rank of the residual weight. Then, the residual part can be effectively approximated by more compact and parameter-efficient structures, with a smaller approximation error. To achieve ultra-parameter-efficiency in practice, we design highly flexible and effective tensor decompositions for both the transform and residual adaptations. Additionally, popular PEFT methods such as DoRA can be summarized under this transform plus residual adaptation scheme. Experiments are conducted on fine-tuning Stable Diffusion models in subject-driven and controllable generation. The results manifest that our method can achieve better performances and parameter efficiency compared to LoRA and several baselines.

Controllable generation through Stable Diffusion (SD) fine-tuning aims to improve fidelity, safety, and alignment with human guidance. Existing reinforcement learning from human feedback methods usually rely on predefined heuristic reward functions or pretrained reward models built on large-scale datasets, limiting their applicability to scenarios where collecting such data is costly or difficult. To effectively and efficiently utilize human feedback, we develop a framework, HERO, which leverages online human feedback collected on the fly during model learning. Specifically, HERO features two key mechanisms: (1) Feedback-Aligned Representation Learning, an online training method that captures human feedback and provides informative learning signals for fine-tuning, and (2) Feedback-Guided Image Generation, which involves generating images from SD's refined initialization samples, enabling faster convergence towards the evaluator's intent. We demonstrate that HERO is 4x more efficient in online feedback for body part anomaly correction compared to the best existing method. Additionally, experiments show that HERO can effectively handle tasks like reasoning, counting, personalization, and reducing NSFW content with only 0.5K online feedback. The code and project page are available at [https://hero-dm.github.io/](https://hero-dm.github.io/).

In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity structure of a huge amount of instances in the real world. For richer classes of the similarity, we propose the use of weighted point sets, namely, sets of pairs of weight and vector, as representations of instances. In this work, we theoretically show the benefit of our proposed method through a new understanding of the contrastive loss of CLIP, which we call symmetric InfoNCE. We clarify that the optimal similarity that minimizes symmetric InfoNCE is the pointwise mutual information, and show an upper bound of excess risk on downstream classification tasks of representations that achieve the optimal similarity. In addition, we show that our proposed similarity based on weighted point sets consistently achieves the optimal similarity. To verify the effectiveness of our proposed method, we demonstrate pretraining of text-image representation models and classification tasks on common benchmarks.

By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion methods rely on fixed pretrained embeddings, limiting the benefits of joint training with the diffusion model. While jointly learning the embedding (via reconstruction loss) and the latent diffusion model (via score matching loss) could enhance performance, end-to-end training risks embedding collapse, degrading generation quality. To mitigate this issue, we introduce VQ-LCMD, a continuous-space latent diffusion framework within the embedding space that stabilizes training. VQ-LCMD uses a novel training objective combining the joint embedding-diffusion variational lower bound with a consistency-matching (CM) loss, alongside a shifted cosine noise schedule and random dropping strategy. Experiments on several benchmarks show that the proposed VQ-LCMD yields superior results on FFHQ, LSUN Churches, and LSUN Bedrooms compared to discrete-state latent diffusion models. In particular, VQ-LCMD achieves an FID of 6.81 for class-conditional image generation on ImageNet with 50 steps.

Restoring degraded music signals is essential to enhance audio quality for downstream music manipulation. Recent diffusion-based music restoration methods have demonstrated impressive performance, and among them, diffusion posterior sampling (DPS) stands out given its intrinsic properties, making it versatile across various restoration tasks. In this paper, we identify that there are potential issues which will degrade current DPS-based methods’ performance and introduce the way to mitigate the issues inspired by diverse diffusion guidance techniques including the RePaint (RP) strategy and the Pseudoinverse-Guided Diffusion Models (ΠGDM). We demonstrate our methods for the vocal declipping and bandwidth extension tasks under various levels of distortion and cutoff frequency, respectively. In both tasks, our methods outperform the current DPS-based music restoration benchmarks. We refer to http://carlosholivan.github.io/demos/audio-restoration-2023.html for examples of the restored audio samples.

Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training. In this paper, we propose Manifold Preserving Guided Diffusion (MPGD), a training-free conditional generation framework that leverages pretrained diffusion models and off-the-shelf neural networks with minimal additional inference cost for a broad range of tasks. Specifically, we leverage the manifold hypothesis to refine the guided diffusion steps and introduce a shortcut algorithm in the process. We then propose two methods for on-manifold training-free guidance using pre-trained autoencoders and demonstrate that our shortcut inherently preserves the manifolds when applied to latent diffusion models. Our experiments show that MPGD is efficient and effective for solving a variety of conditional generation applications in low-compute settings, and can consistently offer up to 3.8× speed-ups with the same number of diffusion steps while maintaining high sample quality compared to the baselines.

Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the cost of sample quality but lack a natural way to trade-off quality for speed. To address this limitation, we propose Consistency Trajectory Model (CTM), a generalization encompassing CM and score-based models as special cases. CTM trains a single neural network that can -- in a single forward pass -- output scores (i.e., gradients of log-density) and enables unrestricted traversal between any initial and final time along the Probability Flow Ordinary Differential Equation (ODE) in a diffusion process. CTM enables the efficient combination of adversarial training and denoising score matching loss to enhance performance and achieves new state-of-the-art FIDs for single-step diffusion model sampling on CIFAR-10 (FID 1.73) and ImageNet at 64X64 resolution (FID 1.92). CTM also enables a new family of sampling schemes, both deterministic and stochastic, involving long jumps along the ODE solution trajectories. It consistently improves sample quality as computational budgets increase, avoiding the degradation seen in CM. Furthermore, unlike CM, CTM's access to the score function can streamline the adoption of established controllable/conditional generation methods from the diffusion community. This access also enables the computation of likelihood. The code is available at https://github.com/sony/ctm.

Generative adversarial networks (GANs) learn a target probability distribution by optimizing a generator and a discriminator with minimax objectives. This paper addresses the question of whether such optimization actually provides the generator with gradients that make its distribution close to the target distribution. We derive *metrizable conditions*, sufficient conditions for the discriminator to serve as the distance between the distributions, by connecting the GAN formulation with the concept of sliced optimal transport. Furthermore, by leveraging these theoretical results, we propose a novel GAN training scheme called the Slicing Adversarial Network (SAN). With only simple modifications, a broad class of existing GANs can be converted to SANs. Experiments on synthetic and image datasets support our theoretical results and the effectiveness of SAN as compared to the usual GANs. We also apply SAN to StyleGAN-XL, which leads to a state-of-the-art FID score amongst GANs for class conditional generation on CIFAR10 and ImageNet 256$\times$256. The code is available at https://github.com/sony/san.

The diffusion model performs remarkable in generating high-dimensional content but is computationally intensive, especially during training. We propose Progressive Growing of Diffusion Autoencoder (PaGoDA), a novel pipeline that reduces the training costs through three stages: training diffusion on downsampled data, distilling the pretrained diffusion, and progressive super-resolution. With the proposed pipeline, PaGoDA achieves a $64\times$ reduced cost in training its diffusion model on $8\times$ downsampled data; while at the inference, with the single-step, it performs state-of-the-art on ImageNet across all resolutions from $64\times64$ to $512\times512$, and text-to-image. PaGoDA's pipeline can be applied directly in the latent space, adding compression alongside the pre-trained autoencoder in Latent Diffusion Models (e.g., Stable Diffusion). The code is available at https://github.com/sony/pagoda.

Generating novel views from a single image remains a challenging task due to the complexity of 3D scenes and the limited diversity in the existing multi-view datasets to train a model on. Recent research combining large-scale text-to-image (T2I) models with monocular depth estimation (MDE) has shown promise in handling in-the-wild images. In these methods, an input view is geometrically warped to novel views with estimated depth maps, then the warped image is inpainted by T2I models. However, they struggle with noisy depth maps and loss of semantic details when warping an input view to novel viewpoints. In this paper, we propose a novel approach for single-shot novel view synthesis, a semantic-preserving generative warping framework that enables T2I generative models to learn where to warp and where to generate, through augmenting cross-view attention with self-attention. Our approach addresses the limitations of existing methods by conditioning the generative model on source view images and incorporating geometric warping signals. Qualitative and quantitative evaluations demonstrate that our model outperforms existing methods in both in-domain and out-of-domain scenarios. Project page is available at https://GenWarp-NVS.github.io.

In this paper we propose a novel generative approach, DiffRoll, to tackle automatic music transcription (AMT). Instead of treating AMT as a discriminative task in which the model is trained to convert spectrograms into piano rolls, we think of it as a conditional generative task where we train our model to generate realistic looking piano rolls from pure Gaussian noise conditioned on spectrograms. This new AMT formulation enables DiffRoll to transcribe, generate and even inpaint music. Due to the classifier-free nature, DiffRoll is also able to be trained on unpaired datasets where only piano rolls are available. Our experiments show that DiffRoll outperforms its discriminative counterpart by 19 percentage points (ppt.) and our ablation studies also indicate that it outperforms similar existing methods by 4.8 ppt.Source code and demonstration are available at https://sony.github.io/DiffRoll/.

Removing reverb from reverberant music is a necessary technique to clean up audio for downstream music manipulations. Reverberation of music contains two categories, natural reverb, and artificial reverb. Artificial reverb has a wider diversity than natural reverb due to its various parameter setups and reverberation types. However, recent supervised dereverberation methods may fail because they rely on sufficiently diverse and numerous pairs of reverberant observations and retrieved data for training in order to be generalizable to unseen observations during inference. To resolve these problems, we propose an unsupervised method that can remove a general kind of artificial reverb for music without requiring pairs of data for training. The proposed method is based on diffusion models, where it initializes the unknown reverberation operator with a conventional signal processing technique and simultaneously refines the estimate with the help of diffusion models. We show through objective and perceptual evaluations that our method outperforms the current leading vocal dereverberation benchmarks.

Score-based generative models (SGMs) learn a family of noise-conditional score functions corresponding to the data density perturbed with increasingly large amounts of noise. These perturbed data densities are linked together by the Fokker-Planck equation (FPE), a partial differential equation (PDE) governing the spatial-temporal evolution of a density undergoing a diffusion process. In this work, we derive a corresponding equation called the score FPE that characterizes the noise-conditional scores of the perturbed data densities (i.e., their gradients). Surprisingly, despite the impressive empirical performance, we observe that scores learned through denoising score matching (DSM) fail to fulfill the underlying score FPE, which is an inherent self-consistency property of the ground truth score. We prove that satisfying the score FPE is desirable as it improves the likelihood and the degree of conservativity. Hence, we propose to regularize the DSM objective to enforce satisfaction of the score FPE, and we show the effectiveness of this approach across various datasets.

Pre-trained diffusion models have been successfully used as priors in a variety of linear inverse problems, where the goal is to reconstruct a signal from noisy linear measurements. However, existing approaches require knowledge of the linear operator. In this paper, we propose GibbsDDRM, an extension of Denoising Diffusion Restoration Models (DDRM) to a blind setting in which the linear measurement operator is unknown. GibbsDDRM constructs a joint distribution of the data, measurements, and linear operator by using a pre-trained diffusion model for the data prior, and it solves the problem by posterior sampling with an efficient variant of a Gibbs sampler. The proposed method is problem-agnostic, meaning that a pre-trained diffusion model can be applied to various inverse problems without fine-tuning. In experiments, it achieved high performance on both blind image deblurring and vocal dereverberation tasks, despite the use of simple generic priors for the underlying linear operators.

Although deep neural network (DNN)-based speech enhancement (SE) methods outperform the previous non-DNN-based ones, they often degrade the perceptual quality of generated outputs.To tackle this problem, we introduce a DNN-based generative refiner, Diffiner, aiming to improve perceptual speech quality pre-processed by an SE method.We train a diffusionbased generative model by utilizing a dataset consisting of clean speech only.Then, our refiner effectively mixes clean parts newly generated via denoising diffusion restoration into the degraded and distorted parts caused by a preceding SE method, resulting in refined speech.Once our refiner is trained on a set of clean speech, it can be applied to various SE methods without additional training specialized for each SE module.Therefore, our refiner can be a versatile post-processing module w.r.t.SE methods and has high potential in terms of modularity.Experimental results show that our method improved perceptual speech quality regardless of the preceding SE methods used.Our code is available at https://github.com/sony/diffiner.

While deep neural network-based music source separation (MSS) is very effective and achieves high performance, its model size is often a problem for practical deployment. Deep implicit architectures such as deep equilibrium models (DEQ) were recently proposed, which can achieve higher performance than their explicit counterparts with limited depth while keeping the number of parameters small. This makes DEQ also attractive for MSS, especially as it was originally applied to sequential modeling tasks in natural language processing and thus should in principle be also suited for MSS. However, an investigation of a good architecture and training scheme for MSS with DEQ is needed as the characteristics of acoustic signals are different from those of natural language data. Hence, in this paper we propose an architecture and training scheme for MSS with DEQ. Starting with the architecture of Open-Unmix (UMX), we replace its sequence model with DEQ. We refer to our proposed method as DEQ-based UMX (DEQ-UMX). Experimental results show that DEQ-UMX performs better than the original UMX while reducing its number of parameters by 30%.

One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook, also known as codebook collapse. We hypothesize that the training scheme of VQ-VAE, which involves some carefully designed heuristics, underlies this issue. In this paper, we propose a new training scheme that extends the standard VAE via novel stochastic dequantization and quantization, called stochastically quantized variational autoencoder (SQ-VAE). In SQ-VAE, we observe a trend that the quantization is stochastic at the initial stage of the training but gradually converges toward a deterministic quantization, which we call self-annealing. Our experiments show that SQ-VAE improves codebook utilization without using common heuristics. Furthermore, we empirically show that SQ-VAE is superior to VAE and VQ-VAE in vision- and speech-related tasks.

Active noise control (ANC) over a sizeable space ideally requires uniformly distributed sensors and secondary sources, which limits the feasibility of practically realizing such systems. In this paper, we propose a direction of arrival (DOA) weighting algorithm for the adaptive filter update, which prioritizes residual error control with respect to the array geometry. Array geometries utilizing multiple horizontal rings, which are considered as more practical than spherical array geometries, are introduced into both sensors and secondary sources. Numerical simulations indicate that the proposed method using multiple-horizontal-ring arrays gives higher noise attenuation performance than the conventional method. The DOA weighting can be intuitively defined on the basis of the secondary source array geometry without any prior information of the primary noise field.

Active acoustic noise attenuation over a sizable space is a challenging problem in signal processing. The noise attenuation performance of feedforward active noise control (ANC) relies on the preciseness of a reference signal of a primary noise field. To capture the precise reference signal for controlling a sizable space, a large number of reference microphones are required, which reduces system viability. In this study, we exploit an efficient representation of the reference signal in spherical harmonic (SH) domain by utilizing the inherent sparseness of the noise field. The main contributions of this work are as follows. (1) A general reference microphone geometry can be used. The implementation difficulty in the array structure, which is recognized as the common issue of SH-domain signal processing, e.g., use of a fully surrounding spherical array, is reduced by using the fields translation based on the addition theorem. (2) The accuracy of low-frequency signal decomposition is improved. The low accuracy of low-frequency signal decomposition in compressive sensing (CS), which is commonly reported in the literature, is improved by applying signal representation in SH domain. (3) System robustness is increased. The robustness of the system is increased by considering a noise source spatial distribution of both the interior and exterior sound fields, which is not possible in the case of a general signal representation in SH domain. Experimental results indicate that the noise attenuation performance of our proposed method exceeds that of existing solutions. The flexibility of the array structure is also increased, which leads to a more feasible practical system setup.

The aim of spatial active noise control (ANC) is to attenuate noise over a certain space. Although a large-scale system is required to achieve spatial ANC, mode-domain signal processing makes it possible to reduce the computational cost and improve the performance. A higher-order source (HOS) has an advantage in sound field control due to its controllable directivity patterns. An array of HOS can suppress an undesired exterior sound propagation while occupying a smaller physical space than a conventional omnidirectional loudspeaker array. In this paper, we propose two types of adaptive algorithm for spatial ANC using HOSs, which provide a trade-off between efficiency and error robustness against loudspeaker placements. Numerical simulations in a reverberant environment show the efficacy of the proposed algorithms compared with the conventional multipoint adaptive spatial ANC algorithm.

We present an interactive sound handling system called SoundPond, in which a sound unit is treated as a virtual sound object. A short recorded sound is visualized as an oval shape that can be changed by the user, leading to modification of characteristics of the sound. Interactions between other sound objects and drawn objects are implemented. Each sound object is also affected by the pond in which it is placed. The proposed system attempts to provide intuitive and versatile interactions for rich sound handling. In the prototype system, basic functions are implemented using a multi-touch display, a microphone, and a pair of stereo speakers. Possible future application areas using SoundPond are graphical sound composition, sound performance, and a sound playground. We believe that SoundPond has the potential to be used for sound expression based on the creativity of the user.

We propose a sound field decomposition method that takes into consideration spatio-temporal sparsity. It has been proved that sparse representation of a sound field is effective in reducing errors originating from spatial aliasing artifacts compared with conventional plane wave decomposition. In most current methods of sparse sound field decomposition, the spatial sparsity of the sound source distribution is only assumed. However, it is known that the temporal structure of the source signal to be decomposed can also be sparse in the time-frequency domain. We formulate an objective function for sparse sound field decomposition by using the ℓp,q-norm to simultaneously induce sparsity in the space and time domains. An optimization algorithm on the auxiliary function method is derived to solve it. Numerical simulations of acoustic holography indicate that the reconstruction accuracy can be improved by controlling the parameter of temporal sparsity. We also demonstrate that a statistical measure of the source signals can be used as an indicator to determine a nearly optimal parameter.

A sparse sound field decomposition method using prior information on source signals in the time-frequency domain is proposed. Sparse sound field decomposition has been proved to be effective for various acoustic signal processing applications. Current methods for sparse decomposition are based only on the spatial sparsity of the source distribution. However, it can be assumed that possible source signals to be decomposed are approximately known in advance. To exploit this prior information, we incorporated the complex nonnegative factorization model into sparse sound field decomposition. Since the magnitude spectrum of the possible source signals can be trained in advance, accuracy of the sparse decomposition can be improved even when the source signals are highly correlated and the sources are in a highly noisy environment. In addition, the proposed decomposition algorithm is derived using the auxiliary function method. Numerical experiments indicated that the sparse decomposition performance was significantly improved using the proposed method.

A method for achieving super-resolution of sound field recording and reproduction is proposed. To obtain driving signals of loudspeakers for reproduction from received signals of microphones, sparse signal decomposition makes it possible to reduce spatial aliasing artifacts when the number of microphones is less than that of loudspeakers. For more accurate and robust signal decomposition, we propose three types of group sparse signal model based on the physical properties of a sound field. In addition, a decomposition algorithm is derived to address these signal models as an extension of M-FOCUSS. In the simulation experiments, the accuracy of the sparse decomposition was significantly improved compared with that of M-FOCUSS. Furthermore, the accuracy of sound field reproduction using our proposed method was higher than that using current methods, especially at frequencies above the spatial Nyquist frequency.