Better-supervised models might have better performance. In this paper, we first clarify what makes for good supervision for a classification problem, and then explain two existing label refining methods, label smoothing and knowledge distillation, in terms of our proposed criterion. To further answer why and how better supervision emerges, we observe the learning path, i.e., the trajectory of the model's predictions during training, for each training sample. We find that the model can spontaneously refine "bad" labels through a "zig-zag" learning path, which occurs on both toy and real datasets. Observing the learning path not only provides a new perspective for understanding knowledge distillation, overfitting, and learning dynamics, but also reveals that the supervisory signal of a teacher network can be very unstable near the best points in training on real tasks. Inspired by this, we propose a new knowledge distillation scheme, Filter-KD, which improves downstream classification performance in various settings.
We are interested in a novel task, singing voice beautifying (SVB). Given the singing voice of an amateur singer, SVB aims to improve the intonation and vocal tone of the voice, while keeping the content and vocal timbre. Current automatic pitch correction techniques are immature, and most of them are restricted to intonation but ignore the overall aesthetic quality. Hence, we introduce Neural Singing Voice Beautifier (NSVB), the first generative model to solve the SVB task, which adopts a conditional variational autoencoder as the backbone and learns the latent representations of vocal tone. In NSVB, we propose a novel time-warping approach for pitch correction: Shape-Aware Dynamic Time Warping (SADTW), which ameliorates the robustness of existing time-warping approaches, to synchronize the amateur recording with the template pitch curve. Furthermore, we propose a latent-mapping algorithm in the latent space to convert the amateur vocal tone to the professional one. To achieve this, we also propose a new dataset containing parallel singing recordings of both amateur and professional versions. Extensive experiments on both Chinese and English songs demonstrate the effectiveness of our methods in terms of both objective and subjective metrics. Audio samples are available at~\url{https://neuralsvb.github.io}. Codes: \url{https://github.com/MoonInTheRiver/NeuralSVB}.
Non-autoregressive text to speech (NAR-TTS) models have attracted much attention from both academia and industry due to their fast generation speed. One limitation of NAR-TTS models is that they ignore the correlation in time and frequency domains while generating speech mel-spectrograms, and thus cause blurry and over-smoothed results. In this work, we revisit this over-smoothing problem from a novel perspective: the degree of over-smoothness is determined by the gap between the complexity of data distributions and the capability of modeling methods. Both simplifying data distributions and improving modeling methods can alleviate the problem. Accordingly, we first study methods reducing the complexity of data distributions. Then we conduct a comprehensive study on NAR-TTS models that use some advanced modeling methods. Based on these studies, we find that 1) methods that provide additional condition inputs reduce the complexity of data distributions to model, thus alleviating the over-smoothing problem and achieving better voice quality. 2) Among advanced modeling methods, Laplacian mixture loss performs well at modeling multimodal distributions and enjoys its simplicity, while GAN and Glow achieve the best voice quality while suffering from increased training or model complexity. 3) The two categories of methods can be combined to further alleviate the over-smoothness and improve the voice quality. 4) Our experiments on the multi-speaker dataset lead to similar conclusions as above and providing more variance information can reduce the difficulty of modeling the target data distribution and alleviate the requirements for model capacity.
Denoising Diffusion Probabilistic Models (DDPMs) can generate high-quality samples such as image and audio samples. However, DDPMs require hundreds to thousands of iterations to produce final samples. Several prior works have successfully accelerated DDPMs through adjusting the variance schedule (e.g., Improved Denoising Diffusion Probabilistic Models) or the denoising equation (e.g., Denoising Diffusion Implicit Models (DDIMs)). However, these acceleration methods cannot maintain the quality of samples and even introduce new noise at a high speedup rate, which limit their practicability. To accelerate the inference process while keeping the sample quality, we provide a fresh perspective that DDPMs should be treated as solving differential equations on manifolds. Under such a perspective, we propose pseudo numerical methods for diffusion models (PNDMs). Specifically, we figure out how to solve differential equations on manifolds and show that DDIMs are simple cases of pseudo numerical methods. We change several classical numerical methods to corresponding pseudo numerical methods and find that the pseudo linear multi-step method is the best in most situations. According to our experiments, by directly using pre-trained models on Cifar10, CelebA and LSUN, PNDMs can generate higher quality synthetic images with only 50 steps compared with 1000-step DDIMs (20x speedup), significantly outperform DDIMs with 250 steps (by around 0.4 in FID) and have good generalization on different variance schedules. Our implementation is available at https://github.com/luping-liu/PNDM.
Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a solution for model attribution, i.e., the classification of synthetic contents by their source models via watermarks embedded in the contents. Building on past success of model attribution in the image domain, we discuss algorithmic improvements for generating user-end speech models that empirically achieve high attribution accuracy, while maintaining high generation quality. We show the trade off between attributability and generation quality under a variety of attacks on generated speech signals attempting to remove the watermarks, and the feasibility of learning robust watermarks against these attacks.
The training of deep neural networks (DNNs) is currently predominantly done using first-order methods. Some of these methods (e.g., Adam, AdaGrad, and RMSprop, and their variants) incorporate a small amount of curvature information by using a diagonal matrix to precondition the stochastic gradient. Recently, effective second-order methods, such as KFAC, K-BFGS, Shampoo, and TNT, have been developed for training DNNs, by preconditioning the stochastic gradient by layer-wise block-diagonal matrices. Here we propose and analyze the convergence of an approximate natural gradient method, mini-block Fisher (MBF), that lies in between these two classes of methods. Specifically, our method uses a block-diagonal approximation to the Fisher matrix, where for each layer in the DNN, whether it is convolutional or feed-forward and fully connected, the associated diagonal block is also block-diagonal and is composed of a large number of mini-blocks of modest size. Our novel approach utilizes the parallelism of GPUs to efficiently perform computations on the large number of matrices in each layer. Consequently, MBF's per-iteration computational cost is only slightly higher than it is for first-order methods. Finally, the performance of our proposed method is compared to that of several baseline methods, on both Auto-encoder and CNN problems, to validate its effectiveness both in terms of time efficiency and generalization power.
Unlike the conventional facial expressions, micro-expressions are involuntary and transient facial expressions capable of revealing the genuine emotions that people attempt to hide. Therefore, they can provide important information in a broad range of applications such as lie detection, criminal detection, etc. Since micro-expressions are transient and of low intensity, however, their detection and recognition is difficult and relies heavily on expert experiences. Due to its intrinsic particularity and complexity, video-based micro-expression analysis is attractive but challenging, and has recently become an active area of research. Although there have been numerous developments in this area, thus far there has been no comprehensive survey that provides researchers with a systematic overview of these developments with a unified evaluation. Accordingly, in this survey paper, we first highlight the key differences between macro- and micro-expressions, then use these differences to guide our research survey of video-based micro-expression analysis in a cascaded structure, encompassing the neuropsychological basis, datasets, features, spotting algorithms, recognition algorithms, applications and evaluation of state-of-the-art approaches. For each aspect, the basic techniques, advanced developments and major challenges are addressed and discussed. Furthermore, after considering the limitations of existing micro-expression datasets, we present and release a new dataset - called micro-and-macro expression warehouse (MMEW) - containing more video samples and more labeled emotion types. We then perform a unified comparison of representative methods on CAS(ME)2 for spotting, and on MMEW and SAMM for recognition, respectively. Finally, some potential future research directions are explored and outlined.
Expressive text-to-speech (TTS) has become a hot research topic recently, mainly focusing on modeling prosody in speech. Prosody modeling has several challenges: 1) the extracted pitch used in previous prosody modeling works have inevitable errors, which hurts the prosody modeling; 2) different attributes of prosody (e.g., pitch, duration and energy) are dependent on each other and produce the natural prosody together; and 3) due to high variability of prosody and the limited amount of high-quality data for TTS training, the distribution of prosody cannot be fully shaped. To tackle these issues, we propose ProsoSpeech, which enhances the prosody using quantized latent vectors pre-trained on large-scale unpaired and low-quality text and speech data. Specifically, we first introduce a word-level prosody encoder, which quantizes the low-frequency band of the speech and compresses prosody attributes in the latent prosody vector (LPV). Then we introduce an LPV predictor, which predicts LPV given word sequence. We pre-train the LPV predictor on large-scale text and low-quality speech data and fine-tune it on the high-quality TTS dataset. Finally, our model can generate expressive speech conditioned on the predicted LPV. Experimental results show that ProsoSpeech can generate speech with richer prosody compared with baseline methods.