CoDiff-VC: A Codec-Assisted Diffusion Model for Zero-shot Voice Conversion

Zero-shot voice conversion (VC) aims to convert the original speaker's timbre to any target speaker while keeping the linguistic content. Current mainstream zero-shot voice conversion approaches depend on pre-trained recognition models to disentangle linguistic content and speaker representation. This results in a timbre residue within the decoupled linguistic content and inadequacies in speaker representation modeling. In this study, we propose CoDiff-VC, an end-to-end framework for zero-shot voice conversion that integrates a speech codec and a diffusion model to produce high-fidelity waveforms. Our approach involves employing a single-codebook codec to separate linguistic content from the source speech. To enhance content disentanglement, we introduce Mix-Style layer normalization (MSLN) to perturb the original timbre. Additionally, we incorporate a multi-scale speaker timbre modeling approach to ensure timbre consistency and improve voice detail similarity. To improve speech quality and speaker similarity, we introduce dual classifier-free guidance, providing both content and timbre guidance during the generation process. Objective and subjective experiments affirm that CoDiff-VC significantly improves speaker similarity, generating natural and higher-quality speech.

Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework

Most existing studies on few-shot learning focus on unimodal settings, where models are trained to generalize on unseen data using only a small number of labeled examples from the same modality. However, real-world data are inherently multi-modal, and unimodal approaches limit the practical applications of few-shot learning. To address this gap, this paper introduces the Cross-modal Few-Shot Learning (CFSL) task, which aims to recognize instances from multiple modalities when only a few labeled examples are available. This task presents additional challenges compared to classical few-shot learning due to the distinct visual characteristics and structural properties unique to each modality. To tackle these challenges, we propose a Generative Transfer Learning (GTL) framework consisting of two stages: the first stage involves training on abundant unimodal data, and the second stage focuses on transfer learning to adapt to novel data. Our GTL framework jointly estimates the latent shared concept across modalities and in-modality disturbance in both stages, while freezing the generative module during the transfer phase to maintain the stability of the learned representations and prevent overfitting to the limited multi-modal samples. Our finds demonstrate that GTL has superior performance compared to state-of-the-art methods across four distinct multi-modal datasets: Sketchy, TU-Berlin, Mask1K, and SKSF-A. Additionally, the results suggest that the model can estimate latent concepts from vast unimodal data and generalize these concepts to unseen modalities using only a limited number of available samples, much like human cognitive processes.

Split to Merge: Unifying Separated Modalities for Unsupervised Domain Adaptation

Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet, most transfer approaches for VLMs focus on either the language or visual branches, overlooking the nuanced interplay between both modalities. In this work, we introduce a Unified Modality Separation (UniMoS) framework for unsupervised domain adaptation. Leveraging insights from modality gap studies, we craft a nimble modality separation network that distinctly disentangles CLIP's features into language-associated and vision-associated components. Our proposed Modality-Ensemble Training (MET) method fosters the exchange of modality-agnostic information while maintaining modality-specific nuances. We align features across domains using a modality discriminator. Comprehensive evaluations on three benchmarks reveal our approach sets a new state-of-the-art with minimal computational costs. Code: https://github.com/TL-UESTC/UniMoS

Learning Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition

Few-shot action recognition aims at quickly adapting a pre-trained model to the novel data with a distribution shift using only a limited number of samples. Key challenges include how to identify and leverage the transferable knowledge learned by the pre-trained model. Our central hypothesis is that temporal invariance in the dynamic system between latent variables lends itself to transferability (domain-invariance). We therefore propose DITeD, or Domain-Invariant Temporal Dynamics for knowledge transfer. To detect the temporal invariance part, we propose a generative framework with a two-stage training strategy during pre-training. Specifically, we explicitly model invariant dynamics including temporal dynamic generation and transitions, and the variant visual and domain encoders. Then we pre-train the model with the self-supervised signals to learn the representation. After that, we fix the whole representation model and tune the classifier. During adaptation, we fix the transferable temporal dynamics and update the image encoder. The efficacy of our approach is revealed by the superior accuracy of DITeD over leading alternatives across standard few-shot action recognition datasets. Moreover, we validate that the learned temporal dynamic transition and temporal dynamic generation modules possess transferable qualities.

HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition

Action recognition in videos poses a challenge due to its high computational cost, especially for Joint Space-Time video transformers (Joint VT). Despite their effectiveness, the excessive number of tokens in such architectures significantly limits their efficiency. In this paper, we propose HaltingVT, an efficient video transformer adaptively removing redundant video patch tokens, which is primarily composed of a Joint VT and a Glimpser module. Specifically, HaltingVT applies data-adaptive token reduction at each layer, resulting in a significant reduction in the overall computational cost. Besides, the Glimpser module quickly removes redundant tokens in shallow transformer layers, which may even be misleading for video recognition tasks based on our observations. To further encourage HaltingVT to focus on the key motion-related information in videos, we design an effective Motion Loss during training. HaltingVT acquires video analysis capabilities and token halting compression strategies simultaneously in a unified training process, without requiring additional training procedures or sub-networks. On the Mini-Kinetics dataset, we achieved 75.0% top-1 ACC with 24.2 GFLOPs, as well as 67.2% top-1 ACC with an extremely low 9.9 GFLOPs. The code is available at https://github.com/dun-research/HaltingVT.

Learning Socio-Temporal Graphs for Multi-Agent Trajectory Prediction

In order to predict a pedestrian's trajectory in a crowd accurately, one has to take into account her/his underlying socio-temporal interactions with other pedestrians consistently. Unlike existing work that represents the relevant information separately, partially, or implicitly, we propose a complete representation for it to be fully and explicitly captured and analyzed. In particular, we introduce a Directed Acyclic Graph-based structure, which we term Socio-Temporal Graph (STG), to explicitly capture pair-wise socio-temporal interactions among a group of people across both space and time. Our model is built on a time-varying generative process, whose latent variables determine the structure of the STGs. We design an attention-based model named STGformer that affords an end-to-end pipeline to learn the structure of the STGs for trajectory prediction. Our solution achieves overall state-of-the-art prediction accuracy in two large-scale benchmark datasets. Our analysis shows that a person's past trajectory is critical for predicting another person's future path. Our model learns this relationship with a strong notion of socio-temporal localities. Statistics show that utilizing this information explicitly for prediction yields a noticeable performance gain with respect to the trajectory-only approaches.

Enhancing Traffic Object Detection in Variable Illumination with RGB-Event Fusion

Traffic object detection under variable illumination is challenging due to the information loss caused by the limited dynamic range of conventional frame-based cameras. To address this issue, we introduce bio-inspired event cameras and propose a novel Structure-aware Fusion Network (SFNet) that extracts sharp and complete object structures from the event stream to compensate for the lost information in images through cross-modality fusion, enabling the network to obtain illumination-robust representations for traffic object detection. Specifically, to mitigate the sparsity or blurriness issues arising from diverse motion states of traffic objects in fixed-interval event sampling methods, we propose the Reliable Structure Generation Network (RSGNet) to generate Speed Invariant Frames (SIF), ensuring the integrity and sharpness of object structures. Next, we design a novel Adaptive Feature Complement Module (AFCM) which guides the adaptive fusion of two modality features to compensate for the information loss in the images by perceiving the global lightness distribution of the images, thereby generating illumination-robust representations. Finally, considering the lack of large-scale and high-quality annotations in the existing event-based object detection datasets, we build a DSEC-Det dataset, which consists of 53 sequences with 63,931 images and more than 208,000 labels for 8 classes. Extensive experimental results demonstrate that our proposed SFNet can overcome the perceptual boundaries of conventional cameras and outperform the frame-based method by 8.0% in mAP50 and 5.9% in mAP50:95. Our code and dataset will be available at https://github.com/YN-Yang/SFNet.

Multi-Speaker Expressive Speech Synthesis via Semi-supervised Contrastive Learning

This paper aims to build an expressive TTS system for multi-speakers, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfer style and emotion across speakers. Specifically, we construct positive-negative sample pairs at both utterance and category (such as emotion-happy or style-poet or speaker A) levels and leverage contrastive learning to better extract disentangled style, emotion, and speaker representations from speech. Furthermore, we introduce a semi-supervised training strategy to the proposed approach to effectively leverage multi-domain data, including style-labeled data, emotion-labeled data, and unlabeled data. We integrate the learned representations into an improved VITS model, enabling it to synthesize expressive speech with diverse styles and emotions for a target speaker. Experiments on multi-domain data demonstrate the good design of our model.

LAE-ST-MoE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-switching ASR

Recently, to mitigate the confusion between different languages in code-switching (CS) automatic speech recognition (ASR), the conditionally factorized models, such as the language-aware encoder (LAE), explicitly disregard the contextual information between different languages. However, this information may be helpful for ASR modeling. To alleviate this issue, we propose the LAE-ST-MoE framework. It incorporates speech translation (ST) tasks into LAE and utilizes ST to learn the contextual information between different languages. It introduces a task-based mixture of expert modules, employing separate feed-forward networks for the ASR and ST tasks. Experimental results on the ASRU 2019 Mandarin-English CS challenge dataset demonstrate that, compared to the LAE-based CTC, the LAE-ST-MoE model achieves a 9.26% mix error reduction on the CS test with the same decoding parameter. Moreover, the well-trained LAE-ST-MoE model can perform ST tasks from CS speech to Mandarin or English text.

Zero-Shot Emotion Transfer For Cross-Lingual Speech Synthesis

Zero-shot emotion transfer in cross-lingual speech synthesis aims to transfer emotion from an arbitrary speech reference in the source language to the synthetic speech in the target language. Building such a system faces challenges of unnatural foreign accents and difficulty in modeling the shared emotional expressions of different languages. Building on the DelightfulTTS neural architecture, this paper addresses these challenges by introducing specifically-designed modules to model the language-specific prosody features and language-shared emotional expressions separately. Specifically, the language-specific speech prosody is learned by a non-autoregressive predictive coding (NPC) module to improve the naturalness of the synthetic cross-lingual speech. The shared emotional expression between different languages is extracted from a pre-trained self-supervised model HuBERT with strong generalization capabilities. We further use hierarchical emotion modeling to capture more comprehensive emotions across different languages. Experimental results demonstrate the proposed framework's effectiveness in synthesizing bi-lingual emotional speech for the monolingual target speaker without emotional training data.