ART$\boldsymbol{\cdot}$V: Auto-Regressive Text-to-Video Generation with Diffusion Models

We present ART$\boldsymbol{\cdot}$V, an efficient framework for auto-regressive video generation with diffusion models. Unlike existing methods that generate entire videos in one-shot, ART$\boldsymbol{\cdot}$V generates a single frame at a time, conditioned on the previous ones. The framework offers three distinct advantages. First, it only learns simple continual motions between adjacent frames, therefore avoiding modeling complex long-range motions that require huge training data. Second, it preserves the high-fidelity generation ability of the pre-trained image diffusion models by making only minimal network modifications. Third, it can generate arbitrarily long videos conditioned on a variety of prompts such as text, image or their combinations, making it highly versatile and flexible. To combat the common drifting issue in AR models, we propose masked diffusion model which implicitly learns which information can be drawn from reference images rather than network predictions, in order to reduce the risk of generating inconsistent appearances that cause drifting. Moreover, we further enhance generation coherence by conditioning it on the initial frame, which typically contains minimal noise. This is particularly useful for long video generation. When trained for only two weeks on four GPUs, ART$\boldsymbol{\cdot}$V already can generate videos with natural motions, rich details and a high level of aesthetic quality. Besides, it enables various appealing applications, e.g., composing a long video from multiple text prompts.

MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation

We present MicroCinema, a straightforward yet effective framework for high-quality and coherent text-to-video generation. Unlike existing approaches that align text prompts with video directly, MicroCinema introduces a Divide-and-Conquer strategy which divides the text-to-video into a two-stage process: text-to-image generation and image\&text-to-video generation. This strategy offers two significant advantages. a) It allows us to take full advantage of the recent advances in text-to-image models, such as Stable Diffusion, Midjourney, and DALLE, to generate photorealistic and highly detailed images. b) Leveraging the generated image, the model can allocate less focus to fine-grained appearance details, prioritizing the efficient learning of motion dynamics. To implement this strategy effectively, we introduce two core designs. First, we propose the Appearance Injection Network, enhancing the preservation of the appearance of the given image. Second, we introduce the Appearance Noise Prior, a novel mechanism aimed at maintaining the capabilities of pre-trained 2D diffusion models. These design elements empower MicroCinema to generate high-quality videos with precise motion, guided by the provided text prompts. Extensive experiments demonstrate the superiority of the proposed framework. Concretely, MicroCinema achieves SOTA zero-shot FVD of 342.86 on UCF-101 and 377.40 on MSR-VTT. See https://wangyanhui666.github.io/MicroCinema.github.io/ for video samples.

Learning Trajectories are Generalization Indicators

The aim of this paper is to investigate the connection between learning trajectories of the Deep Neural Networks (DNNs) and their corresponding generalization capabilities when being optimized with broadly used gradient descent and stochastic gradient descent algorithms. In this paper, we construct Linear Approximation Function to model the trajectory information and we propose a new generalization bound with richer trajectory information based on it. Our proposed generalization bound relies on the complexity of learning trajectory and the ratio between the bias and diversity of training set. Experimental results indicate that the proposed method effectively captures the generalization trend across various training steps, learning rates, and label noise levels.

Filler Word Detection with Hard Category Mining and Inter-Category Focal Loss

Filler words like ``um" or ``uh" are common in spontaneous speech. It is desirable to automatically detect and remove them in recordings, as they affect the fluency, confidence, and professionalism of speech. Previous studies and our preliminary experiments reveal that the biggest challenge in filler word detection is that fillers can be easily confused with other hard categories like ``a" or ``I". In this paper, we propose a novel filler word detection method that effectively addresses this challenge by adding auxiliary categories dynamically and applying an additional inter-category focal loss. The auxiliary categories force the model to explicitly model the confusing words by mining hard categories. In addition, inter-category focal loss adaptively adjusts the penalty weight between ``filler" and ``non-filler" categories to deal with other confusing words left in the ``non-filler" category. Our system achieves the best results, with a huge improvement compared to other methods on the PodcastFillers dataset.

TridentSE: Guiding Speech Enhancement with 32 Global Tokens

In this paper, we present TridentSE, a novel architecture for speech enhancement, which is capable of efficiently capturing both global information and local details. TridentSE maintains T-F bin level representation to capture details, and uses a small number of global tokens to process the global information. Information is propagated between the local and the global representations through cross attention modules. To capture both inter- and intra-frame information, the global tokens are divided into two groups to process along the time and the frequency axis respectively. A metric discriminator is further employed to guide our model to achieve higher perceptual quality. Even with significantly lower computational cost, TridentSE outperforms a variety of previous speech enhancement methods, achieving a PESQ of 3.47 on VoiceBank+DEMAND dataset and a PESQ of 3.44 on DNS no-reverb test set. Visualization shows that the global tokens learn diverse and interpretable global patterns.

RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion

This paper proposes a new "decompose-and-edit" paradigm for the text-based speech insertion task that facilitates arbitrary-length speech insertion and even full sentence generation. In the proposed paradigm, global and local factors in speech are explicitly decomposed and separately manipulated to achieve high speaker similarity and continuous prosody. Specifically, we proposed to represent the global factors by multiple tokens, which are extracted by cross-attention operation and then injected back by link-attention operation. Due to the rich representation of global factors, we manage to achieve high speaker similarity in a zero-shot manner. In addition, we introduce a prosody smoothing task to make the local prosody factor context-aware and therefore achieve satisfactory prosody continuity. We further achieve high voice quality with an adversarial training stage. In the subjective test, our method achieves state-of-the-art performance in both naturalness and similarity. Audio samples can be found at https://ydcustc.github.io/retrieverTTS-demo/.

Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

This paper addresses the unsupervised learning of content-style decomposed representation. We first give a definition of style and then model the content-style representation as a token-level bipartite graph. An unsupervised framework, named Retriever, is proposed to learn such representations. First, a cross-attention module is employed to retrieve permutation invariant (P.I.) information, defined as style, from the input data. Second, a vector quantization (VQ) module is used, together with man-induced constraints, to produce interpretable content tokens. Last, an innovative link attention module serves as the decoder to reconstruct data from the decomposed content and style, with the help of the linking keys. Being modal-agnostic, the proposed Retriever is evaluated in both speech and image domains. The state-of-the-art zero-shot voice conversion performance confirms the disentangling ability of our framework. Top performance is also achieved in the part discovery task for images, verifying the interpretability of our representation. In addition, the vivid part-based style transfer quality demonstrates the potential of Retriever to support various fascinating generative tasks. Project page at https://ydcustc.github.io/retriever-demo/.

Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration

Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the input text using a generic text-to-speech (TTS) engine and then transform the voice to the desired voice using voice conversion (VC). A major problem of this framework is that VC is a challenging problem which usually needs a moderate amount of parallel training data to work satisfactorily. In this paper, we propose a one-stage context-aware framework to generate natural and coherent target speech without any training data of the target speaker. In particular, we manage to perform accurate zero-shot duration prediction for the inserted text. The predicted duration is used to regulate both text embedding and speech embedding. Then, based on the aligned cross-modality input, we directly generate the mel-spectrogram of the edited speech with a transformer-based decoder. Subjective listening tests show that despite the lack of training data for the speaker, our method has achieved satisfactory results. It outperforms a recent zero-shot TTS engine by a large margin.

General-Purpose Speech Representation Learning through a Self-Supervised Multi-Granularity Framework

This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. In the design of MGF, speech hierarchy is taken into consideration. Specifically, we propose to use generative learning approaches to capture fine-grained information at small time scales and use discriminative learning approaches to distill coarse-grained or semantic information at large time scales. For phoneme-scale learning, we borrow idea from the masked language model but tailor it for the continuous speech signal by replacing classification loss with a contrastive loss. We corroborate our design by evaluating MGF representation on various downstream tasks, including phoneme classification, speaker classification, speech recognition, and emotion classification. Experiments verify that training at different time scales needs different training targets and loss functions, which in general complement each other and lead to a better performance.