FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation

Diffusion-based voice conversion (VC) techniques such as VoiceGrad have attracted interest because of their high VC performance in terms of speech quality and speaker similarity. However, a notable limitation is the slow inference caused by the multi-step reverse diffusion. Therefore, we propose FastVoiceGrad, a novel one-step diffusion-based VC that reduces the number of iterations from dozens to one while inheriting the high VC performance of the multi-step diffusion-based VC. We obtain the model using adversarial conditional diffusion distillation (ACDD), leveraging the ability of generative adversarial networks and diffusion models while reconsidering the initial states in sampling. Evaluations of one-shot any-to-any VC demonstrate that FastVoiceGrad achieves VC performance superior to or comparable to that of previous multi-step diffusion-based VC while enhancing the inference speed. Audio samples are available at https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/fastvoicegrad/.

Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization

Geometry-agnostic system identification is a technique for identifying the geometry and physical properties of an object from video sequences without any geometric assumptions. Recently, physics-augmented continuum neural radiance fields (PAC-NeRF) has demonstrated promising results for this technique by utilizing a hybrid Eulerian-Lagrangian representation, in which the geometry is represented by the Eulerian grid representations of NeRF, the physics is described by a material point method (MPM), and they are connected via Lagrangian particles. However, a notable limitation of PAC-NeRF is that its performance is sensitive to the learning of the geometry from the first frames owing to its two-step optimization. First, the grid representations are optimized with the first frames of video sequences, and then the physical properties are optimized through video sequences utilizing the fixed first-frame grid representations. This limitation can be critical when learning of the geometric structure is difficult, for example, in a few-shot (sparse view) setting. To overcome this limitation, we propose Lagrangian particle optimization (LPO), in which the positions and features of particles are optimized through video sequences in Lagrangian space. This method allows for the optimization of the geometric structure across the entire video sequence within the physical constraints imposed by the MPM. The experimental results demonstrate that the LPO is useful for geometric correction and physical identification in sparse-view settings.

Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator

A generative adversarial network (GAN)-based vocoder trained with an adversarial discriminator is commonly used for speech synthesis because of its fast, lightweight, and high-quality characteristics. However, this data-driven model requires a large amount of training data incurring high data-collection costs. This fact motivates us to train a GAN-based vocoder on limited data. A promising solution is to augment the training data to avoid overfitting. However, a standard discriminator is unconditional and insensitive to distributional changes caused by data augmentation. Thus, augmented speech (which can be extraordinary) may be considered real speech. To address this issue, we propose an augmentation-conditional discriminator (AugCondD) that receives the augmentation state as input in addition to speech, thereby assessing the input speech according to the augmentation state, without inhibiting the learning of the original non-augmented distribution. Experimental results indicate that AugCondD improves speech quality under limited data conditions while achieving comparable speech quality under sufficient data conditions. Audio samples are available at https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/augcondd/.

Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training

Unsupervised intrinsic image decomposition (IID) is the process of separating a natural image into albedo and shade without these ground truths. A recent model employing light detection and ranging (LiDAR) intensity demonstrated impressive performance, though the necessity of LiDAR intensity during inference restricts its practicality. Thus, IID models employing only a single image during inference while keeping as high IID quality as the one with an image plus LiDAR intensity are highly desired. To address this challenge, we propose a novel approach that utilizes only an image during inference while utilizing an image and LiDAR intensity during training. Specifically, we introduce a partially-shared model that accepts an image and LiDAR intensity individually using a different specific encoder but processes them together in specific components to learn shared representations. In addition, to enhance IID quality, we propose albedo-alignment loss and image-LiDAR conversion (ILC) paths. Albedo-alignment loss aligns the gray-scale albedo from an image to that inferred from LiDAR intensity, thereby reducing cast shadows in albedo from an image due to the absence of cast shadows in LiDAR intensity. Furthermore, to translate the input image into albedo and shade style while keeping the image contents, the input image is separated into style code and content code by encoders. The ILC path mutually translates the image and LiDAR intensity, which share content but differ in style, contributing to the distinct differentiation of style from content. Consequently, LIET achieves comparable IID quality to the existing model with LiDAR intensity, while utilizing only an image without LiDAR intensity during inference.

MIMO-NeRF: Fast Neural Rendering with Multi-input Multi-output Neural Radiance Fields

Neural radiance fields (NeRFs) have shown impressive results for novel view synthesis. However, they depend on the repetitive use of a single-input single-output multilayer perceptron (SISO MLP) that maps 3D coordinates and view direction to the color and volume density in a sample-wise manner, which slows the rendering. We propose a multi-input multi-output NeRF (MIMO-NeRF) that reduces the number of MLPs running by replacing the SISO MLP with a MIMO MLP and conducting mappings in a group-wise manner. One notable challenge with this approach is that the color and volume density of each point can differ according to a choice of input coordinates in a group, which can lead to some notable ambiguity. We also propose a self-supervised learning method that regularizes the MIMO MLP with multiple fast reformulated MLPs to alleviate this ambiguity without using pretrained models. The results of a comprehensive experimental evaluation including comparative and ablation studies are presented to show that MIMO-NeRF obtains a good trade-off between speed and quality with a reasonable training time. We then demonstrate that MIMO-NeRF is compatible with and complementary to previous advancements in NeRFs by applying it to two representative fast NeRFs, i.e., a NeRF with sample reduction (DONeRF) and a NeRF with alternative representations (TensoRF).

iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN

The inverse short-time Fourier transform network (iSTFTNet) has garnered attention owing to its fast, lightweight, and high-fidelity speech synthesis. It obtains these characteristics using a fast and lightweight 1D CNN as the backbone and replacing some neural processes with iSTFT. Owing to the difficulty of a 1D CNN to model high-dimensional spectrograms, the frequency dimension is reduced via temporal upsampling. However, this strategy compromises the potential to enhance the speed. Therefore, we propose iSTFTNet2, an improved variant of iSTFTNet with a 1D-2D CNN that employs 1D and 2D CNNs to model temporal and spectrogram structures, respectively. We designed a 2D CNN that performs frequency upsampling after conversion in a few-frequency space. This design facilitates the modeling of high-dimensional spectrograms without compromising the speed. The results demonstrated that iSTFTNet2 made iSTFTNet faster and more lightweight with comparable speech quality. Audio samples are available at https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/istftnet2/.

Unsupervised Intrinsic Image Decomposition with LiDAR Intensity

Intrinsic image decomposition (IID) is the task that decomposes a natural image into albedo and shade. While IID is typically solved through supervised learning methods, it is not ideal due to the difficulty in observing ground truth albedo and shade in general scenes. Conversely, unsupervised learning methods are currently underperforming supervised learning methods since there are no criteria for solving the ill-posed problems. Recently, light detection and ranging (LiDAR) is widely used due to its ability to make highly precise distance measurements. Thus, we have focused on the utilization of LiDAR, especially LiDAR intensity, to address this issue. In this paper, we propose unsupervised intrinsic image decomposition with LiDAR intensity (IID-LI). Since the conventional unsupervised learning methods consist of image-to-image transformations, simply inputting LiDAR intensity is not an effective approach. Therefore, we design an intensity consistency loss that computes the error between LiDAR intensity and gray-scaled albedo to provide a criterion for the ill-posed problem. In addition, LiDAR intensity is difficult to handle due to its sparsity and occlusion, hence, a LiDAR intensity densification module is proposed. We verified the estimating quality using our own dataset, which include RGB images, LiDAR intensity and human judged annotations. As a result, we achieved an estimation accuracy that outperforms conventional unsupervised learning methods. Dataset link : (https://github.com/ntthilab-cv/NTT-intrinsic-dataset).

Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis

In speech synthesis, a generative adversarial network (GAN), training a generator (speech synthesizer) and a discriminator in a min-max game, is widely used to improve speech quality. An ensemble of discriminators is commonly used in recent neural vocoders (e.g., HiFi-GAN) and end-to-end text-to-speech (TTS) systems (e.g., VITS) to scrutinize waveforms from multiple perspectives. Such discriminators allow synthesized speech to adequately approach real speech; however, they require an increase in the model size and computation time according to the increase in the number of discriminators. Alternatively, this study proposes a Wave-U-Net discriminator, which is a single but expressive discriminator with Wave-U-Net architecture. This discriminator is unique; it can assess a waveform in a sample-wise manner with the same resolution as the input signal, while extracting multilevel features via an encoder and decoder with skip connections. This architecture provides a generator with sufficiently rich information for the synthesized speech to be closely matched to the real speech. During the experiments, the proposed ideas were applied to a representative neural vocoder (HiFi-GAN) and an end-to-end TTS system (VITS). The results demonstrate that the proposed models can achieve comparable speech quality with a 2.31 times faster and 14.5 times more lightweight discriminator when used in HiFi-GAN and a 1.90 times faster and 9.62 times more lightweight discriminator when used in VITS. Audio samples are available at https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/waveunetd/.

AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fields

Fully unsupervised 3D representation learning has gained attention owing to its advantages in data collection. A successful approach involves a viewpoint-aware approach that learns an image distribution based on generative models (e.g., generative adversarial networks (GANs)) while generating various view images based on 3D-aware models (e.g., neural radiance fields (NeRFs)). However, they require images with various views for training, and consequently, their application to datasets with few or limited viewpoints remains a challenge. As a complementary approach, an aperture rendering GAN (AR-GAN) that employs a defocus cue was proposed. However, an AR-GAN is a CNN-based model and represents a defocus independently from a viewpoint change despite its high correlation, which is one of the reasons for its performance. As an alternative to an AR-GAN, we propose an aperture rendering NeRF (AR-NeRF), which can utilize viewpoint and defocus cues in a unified manner by representing both factors in a common ray-tracing framework. Moreover, to learn defocus-aware and defocus-independent representations in a disentangled manner, we propose aperture randomized training, for which we learn to generate images while randomizing the aperture size and latent codes independently. During our experiments, we applied AR-NeRF to various natural image datasets, including flower, bird, and face images, the results of which demonstrate the utility of AR-NeRF for unsupervised learning of the depth and defocus effects.

iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform

In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vocoder is increasing. A mel-spectrogram vocoder must solve three inverse problems: recovery of the original-scale magnitude spectrogram, phase reconstruction, and frequency-to-time conversion. A typical convolutional mel-spectrogram vocoder solves these problems jointly and implicitly using a convolutional neural network, including temporal upsampling layers, when directly calculating a raw waveform. Such an approach allows skipping redundant processes during waveform synthesis (e.g., the direct reconstruction of high-dimensional original-scale spectrograms). By contrast, the approach solves all problems in a black box and cannot effectively employ the time-frequency structures existing in a mel-spectrogram. We thus propose iSTFTNet, which replaces some output-side layers of the mel-spectrogram vocoder with the inverse short-time Fourier transform (iSTFT) after sufficiently reducing the frequency dimension using upsampling layers, reducing the computational cost from black-box modeling and avoiding redundant estimations of high-dimensional spectrograms. During our experiments, we applied our ideas to three HiFi-GAN variants and made the models faster and more lightweight with a reasonable speech quality. Audio samples are available at https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/istftnet/.