Sound content is an indispensable element for multimedia works such as video games, music, and films. Recent high-quality diffusion-based sound generation models can serve as valuable tools for the creators. However, despite producing high-quality sounds, these models often suffer from slow inference speeds. This drawback burdens creators, who typically refine their sounds through trial and error to align them with their artistic intentions. To address this issue, we introduce Sound Consistency Trajectory Models (SoundCTM). Our model enables flexible transitioning between high-quality 1-step sound generation and superior sound quality through multi-step generation. This allows creators to initially control sounds with 1-step samples before refining them through multi-step generation. While CTM fundamentally achieves flexible 1-step and multi-step generation, its impressive performance heavily depends on an additional pretrained feature extractor and an adversarial loss, which are expensive to train and not always available in other domains. Thus, we reframe CTM's training framework and introduce a novel feature distance by utilizing the teacher's network for a distillation loss. Additionally, while distilling classifier-free guided trajectories, we train conditional and unconditional student models simultaneously and interpolate between these models during inference. We also propose training-free controllable frameworks for SoundCTM, leveraging its flexible sampling capability. SoundCTM achieves both promising 1-step and multi-step real-time sound generation without using any extra off-the-shelf networks. Furthermore, we demonstrate SoundCTM's capability of controllable sound generation in a training-free manner. Our codes, pretrained models, and audio samples are available at https://github.com/sony/soundctm.

To accelerate sampling, diffusion models (DMs) are often distilled into generators that directly map noise to data in a single step. In this approach, the resolution of the generator is fundamentally limited by that of the teacher DM. To overcome this limitation, we propose Progressive Growing of Diffusion Autoencoder (PaGoDA), a technique to progressively grow the resolution of the generator beyond that of the original teacher DM. Our key insight is that a pre-trained, low-resolution DM can be used to deterministically encode high-resolution data to a structured latent space by solving the PF-ODE forward in time (data-to-noise), starting from an appropriately down-sampled image. Using this frozen encoder in an auto-encoder framework, we train a decoder by progressively growing its resolution. From the nature of progressively growing decoder, PaGoDA avoids re-training teacher/student models when we upsample the student model, making the whole training pipeline much cheaper. In experiments, we used our progressively growing decoder to upsample from the pre-trained model's 64x64 resolution to generate 512x512 samples, achieving 2x faster inference compared to single-step distilled Stable Diffusion like LCM. PaGoDA also achieved state-of-the-art FIDs on ImageNet across all resolutions from 64x64 to 512x512. Additionally, we demonstrated PaGoDA's effectiveness in solving inverse problems and enabling controllable generation.

Multimodal representation learning to integrate different modalities, such as text, vision, and audio is important for real-world applications. The symmetric InfoNCE loss proposed in CLIP is a key concept in multimodal representation learning. In this work, we provide a theoretical understanding of the symmetric InfoNCE loss through the lens of the pointwise mutual information and show that encoders that achieve the optimal similarity in the pretraining provide a good representation for downstream classification tasks under mild assumptions. Based on our theoretical results, we also propose a new similarity metric for multimodal contrastive learning by utilizing a nonlinear kernel to enrich the capability. To verify the effectiveness of the proposed method, we demonstrate pretraining of multimodal representation models on the Conceptual Caption datasets and evaluate zero-shot classification and linear classification on common benchmark datasets. CLIP (Radford et al., 2021) and ALIGN (Jia et al., 2021) established one of the most common frameworks for multimodal representation learning (Guo et al., 2019). In this framework, to obtain the vision-language representation, two encoders that map inputs from different modalities onto a shared space are trained with a contrastive loss (Chopra et al., 2005). Recent studies have shown that a CLIP model pretrained on a large-scale text-image dataset provides transferable features to various downstream tasks such as linear classification (Radford et al., 2021; Jia et al., 2021), text-to-video retrieval (Lin et al., 2022), text-conditioned image generation (Ramesh et al., 2022), and manipulation (Patashnik et al., 2021). Recent works have shown that a CLIP model can be used to feed vision information to large language models (Alayrac et al., 2022). In addition to the text and vision modalities, this multimodal contrastive learning framework can be applied to other combinations of modalities such as text-audio representations (Elizalde et al., 2023).

Vector quantization (VQ) is a technique to deterministically learn features with discrete codebook representations. It is commonly performed with a variational autoencoding model, VQ-VAE, which can be further extended to hierarchical structures for making high-fidelity reconstructions. However, such hierarchical extensions of VQ-VAE often suffer from the codebook/layer collapse issue, where the codebook is not efficiently used to express the data, and hence degrades reconstruction accuracy. To mitigate this problem, we propose a novel unified framework to stochastically learn hierarchical discrete representation on the basis of the variational Bayes framework, called hierarchically quantized variational autoencoder (HQ-VAE). HQ-VAE naturally generalizes the hierarchical variants of VQ-VAE, such as VQ-VAE-2 and residual-quantized VAE (RQ-VAE), and provides them with a Bayesian training scheme. Our comprehensive experiments on image datasets show that HQ-VAE enhances codebook usage and improves reconstruction performance.

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 3.8x speed-ups with the same number of diffusion steps while maintaining high sample quality compared to the baselines.

Contrastive cross-modal models such as CLIP and CLAP aid various vision-language (VL) and audio-language (AL) tasks. However, there has been limited investigation of and improvement in their language encoder, which is the central component of encoding natural language descriptions of image/audio into vector representations. We extensively evaluate how unsupervised and supervised sentence embedding training affect language encoder quality and cross-modal task performance. In VL pretraining, we found that sentence embedding training language encoder quality and aids in cross-modal tasks, improving contrastive VL models such as CyCLIP. In contrast, AL pretraining benefits less from sentence embedding training, which may result from the limited amount of pretraining data. We analyze the representation spaces to understand the strengths of sentence embedding training, and find that it improves text-space uniformity, at the cost of decreased cross-modal alignment.

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 2.06). 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, CTM's access to the score accommodates all diffusion model inference techniques, including exact likelihood computation.

Generative adversarial network (GAN)-based vocoders have been intensively studied because they can synthesize high-fidelity audio waveforms faster than real-time. However, it has been reported that most GANs fail to obtain the optimal projection for discriminating between real and fake data in the feature space. In the literature, it has been demonstrated that slicing adversarial network (SAN), an improved GAN training framework that can find the optimal projection, is effective in the image generation task. In this paper, we investigate the effectiveness of SAN in the vocoding task. For this purpose, we propose a scheme to modify least-squares GAN, which most GAN-based vocoders adopt, so that their loss functions satisfy the requirements of SAN. Through our experiments, we demonstrate that SAN can improve the performance of GAN-based vocoders, including BigVGAN, with small modifications. Our code is available at https://github.com/sony/bigvsan.

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 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 SAN's effectiveness as compared to usual GANs. Furthermore, we also apply SAN to StyleGAN-XL, which leads to state-of-the-art FID score amongst GANs for class conditional generation on ImageNet 256$\times$256.

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 diffusion-based 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.