Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation

Diffusion models have achieved remarkable success in text-to-speech (TTS), even in zero-shot scenarios. Recent efforts aim to address the trade-off between inference speed and sound quality, often considered the primary drawback of diffusion models. However, we find a critical mispronunciation issue is being overlooked. Our preliminary study reveals the unstable pronunciation resulting from the diffusion process. Based on this observation, we introduce StableForm-TTS, a novel zero-shot speech synthesis framework designed to produce robust pronunciation while maintaining the advantages of diffusion modeling. By pioneering the adoption of source-filter theory in diffusion TTS, we propose an elaborate architecture for stable formant generation. Experimental results on unseen speakers show that our model outperforms the state-of-the-art method in terms of pronunciation accuracy and naturalness, with comparable speaker similarity. Moreover, our model demonstrates effective scalability as both data and model sizes increase.

Learning to Generate Conditional Tri-plane for 3D-aware Expression Controllable Portrait Animation

In this paper, we present Export3D, a one-shot 3D-aware portrait animation method that is able to control the facial expression and camera view of a given portrait image. To achieve this, we introduce a tri-plane generator that directly generates a tri-plane of 3D prior by transferring the expression parameter of 3DMM into the source image. The tri-plane is then decoded into the image of different view through a differentiable volume rendering. Existing portrait animation methods heavily rely on image warping to transfer the expression in the motion space, challenging on disentanglement of appearance and expression. In contrast, we propose a contrastive pre-training framework for appearance-free expression parameter, eliminating undesirable appearance swap when transferring a cross-identity expression. Extensive experiments show that our pre-training framework can learn the appearance-free expression representation hidden in 3DMM, and our model can generate 3D-aware expression controllable portrait image without appearance swap in the cross-identity manner.

DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions

For realistic talking head generation, creating natural head motion while maintaining accurate lip synchronization is essential. To fulfill this challenging task, we propose DisCoHead, a novel method to disentangle and control head pose and facial expressions without supervision. DisCoHead uses a single geometric transformation as a bottleneck to isolate and extract head motion from a head-driving video. Either an affine or a thin-plate spline transformation can be used and both work well as geometric bottlenecks. We enhance the efficiency of DisCoHead by integrating a dense motion estimator and the encoder of a generator which are originally separate modules. Taking a step further, we also propose a neural mix approach where dense motion is estimated and applied implicitly by the encoder. After applying the disentangled head motion to a source identity, DisCoHead controls the mouth region according to speech audio, and it blinks eyes and moves eyebrows following a separate driving video of the eye region, via the weight modulation of convolutional neural networks. The experiments using multiple datasets show that DisCoHead successfully generates realistic audio-and-video-driven talking heads and outperforms state-of-the-art methods. Project page: https://deepbrainai-research.github.io/discohead/

Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion

Most Chinese Grapheme-to-Phoneme (G2P) systems employ a three-stage framework that first transforms input sequences into character embeddings, obtains linguistic information using language models, and then predicts the phonemes based on global context about the entire input sequence. However, linguistic knowledge alone is often inadequate. Language models frequently encode overly general structures of a sentence and fail to cover specific cases needed to use phonetic knowledge. Also, a handcrafted post-processing system is needed to address the problems relevant to the tone of the characters. However, the system exhibits inconsistency in the segmentation of word boundaries which consequently degrades the performance of the G2P system. To address these issues, we propose the Reinforcer that provides strong inductive bias for language models by emphasizing the phonological information between neighboring characters to help disambiguate pronunciations. Experimental results show that the Reinforcer boosts the cutting-edge architectures by a large margin. We also combine the Reinforcer with a large-scale pre-trained model and demonstrate the validity of using neighboring context in knowledge transfer scenarios.

PriorityCut: Occlusion-guided Regularization for Warp-based Image Animation

Image animation generates a video of a source image following the motion of a driving video. State-of-the-art self-supervised image animation approaches warp the source image according to the motion of the driving video and recover the warping artifacts by inpainting. These approaches mostly use vanilla convolution for inpainting, and vanilla convolution does not distinguish between valid and invalid pixels. As a result, visual artifacts are still noticeable after inpainting. CutMix is a state-of-the-art regularization strategy that cuts and mixes patches of images and is widely studied in different computer vision tasks. Among the remaining computer vision tasks, warp-based image animation is one of the fields that the effects of CutMix have yet to be studied. This paper first presents a preliminary study on the effects of CutMix on warp-based image animation. We observed in our study that CutMix helps improve only pixel values, but disturbs the spatial relationships between pixels. Based on such observation, we propose PriorityCut, a novel augmentation approach that uses the top-k percent occluded pixels of the foreground to regularize warp-based image animation. By leveraging the domain knowledge in warp-based image animation, PriorityCut significantly reduces the warping artifacts in state-of-the-art warp-based image animation models on diverse datasets.

KoDF: A Large-scale Korean DeepFake Detection Dataset

A variety of effective face-swap and face-reenactment methods have been publicized in recent years, democratizing the face synthesis technology to a great extent. Videos generated as such have come to be collectively called deepfakes with a negative connotation, for various social problems they have caused. Facing the emerging threat of deepfakes, we have built the Korean DeepFake Detection Dataset (KoDF), a large-scale collection of synthesized and real videos focused on Korean subjects. In this paper, we provide a detailed description of methods used to construct the dataset, experimentally show the discrepancy between the distributions of KoDF and existing deepfake detection datasets, and underline the importance of using multiple datasets for real-world generalization. KoDF is publicly available at https://moneybrain-research.github.io/kodf in its entirety (i.e. real clips, synthesized clips, clips with additive noise, and their corresponding metadata).

GAN Vocoder: Multi-Resolution Discriminator Is All You Need

Several of the latest GAN-based vocoders show remarkable achievements, outperforming autoregressive and flow-based competitors in both qualitative and quantitative measures while synthesizing orders of magnitude faster. In this work, we hypothesize that the common factor underlying their success is the multi-resolution discriminating framework, not the minute details in architecture, loss function, or training strategy. We experimentally test the hypothesis by evaluating six different generators paired with one shared multi-resolution discriminating framework. For all evaluative measures with respect to text-to-speech syntheses and for all perceptual metrics, their performances are not distinguishable from one another, which supports our hypothesis.

Axial Residual Networks for CycleGAN-based Voice Conversion

We propose a novel architecture and improved training objectives for non-parallel voice conversion. Our proposed CycleGAN-based model performs a shape-preserving transformation directly on a high frequency-resolution magnitude spectrogram, converting its style (i.e. speaker identity) while preserving the speech content. Throughout the entire conversion process, the model does not resort to compressed intermediate representations of any sort (e.g. mel spectrogram, low resolution spectrogram, decomposed network feature). We propose an efficient axial residual block architecture to support this expensive procedure and various modifications to the CycleGAN losses to stabilize the training process. We demonstrate via experiments that our proposed model outperforms Scyclone and shows a comparable or better performance to that of CycleGAN-VC2 even without employing a neural vocoder.