Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of image information during understanding task, due to either image discretization or diffusion de-noising steps. To address this issue, we propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework. Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss in an efficient way. Differing from diffusion-based approaches, we disentangle the diffusion process from auto-regressive backbone model by employing a lightweight diffusion head on top each auto-regressed image patch embedding. In this way, when the model transits from image generation to understanding through text generation, the backbone model’s hidden representation of the image is not limited to the last denoising step. To successfully train our method, we also propose a theoretically proven technique that addresses the numerical stability issue and a training strategy that balances the generation and understanding task goals. Extensive evaluations on 18 image understanding benchmarks show that MMAR significantly outperforms most of the existing joint multi-modal models, surpassing the method that employs pre-trained CLIP vision encoder. Meanwhile, MMAR is able to generate high quality images. We also show that our method is scalable with larger data and model size.

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-JOJ and 377.40 on MSR-VTT.

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.

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient descent algorithms. Instead of concentrating solely on the generalization error of the DNN post-training, we present a novel perspective for analyzing generalization error by investigating the contribution of each update step to the change in generalization error. This perspective enable a more direct comprehension of how the learning trajectory influences generalization error. Building upon this analysis, we propose a new generalization bound that incorporates more extensive trajectory information. Our proposed generalization bound depends on the complexity of learning trajectory and the ratio between the bias and diversity of training set. Experimental observations reveal that our method effectively captures the generalization error throughout the training process. Furthermore, our approach can also track changes in generalization error when adjustments are made to learning rates and label noise levels. These results demonstrate that learning trajectory information is a valuable indicator of a model's generalization capabilities.

This paper proposes a new "decompose-and-edit" paradigm for the text-based speech insertion task that facilitates arbitrarylength 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/.

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.

Time-frequency (T-F) domain masking is a mainstream approach for single-channel speech enhancement. Recently, focuses have been put to phase prediction in addition to amplitude prediction. In this paper, we propose a phase-and-harmonics-aware deep neural network (DNN), named PHASEN, for this task. Unlike previous methods which directly use a complex ideal ratio mask to supervise the DNN learning, we design a two-stream network, where amplitude stream and phase stream are dedicated to amplitude and phase prediction. We discover that the two streams should communicate with each other, and this is crucial to phase prediction. In addition, we propose frequency transformation blocks to catch long-range correlations along the frequency axis. Visualization shows that the learned transformation matrix implicitly captures the harmonic correlation, which has been proven to be helpful for T-F spectrogram reconstruction. With these two innovations, PHASEN acquires the ability to handle detailed phase patterns and to utilize harmonic patterns, getting 1.76dB SDR improvement on AVSpeech + AudioSet dataset. It also achieves significant gains over Google's network on this dataset. On Voice Bank + DEMAND dataset, PHASEN outperforms previous methods by a large margin on four metrics.