HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition

Audio-Visual Emotion Recognition (AVER) has garnered increasing attention in recent years for its critical role in creating emotion-ware intelligent machines. Previous efforts in this area are dominated by the supervised learning paradigm. Despite significant progress, supervised learning is meeting its bottleneck due to the longstanding data scarcity issue in AVER. Motivated by recent advances in self-supervised learning, we propose Hierarchical Contrastive Masked Autoencoder (HiCMAE), a novel self-supervised framework that leverages large-scale self-supervised pre-training on vast unlabeled audio-visual data to promote the advancement of AVER. Following prior arts in self-supervised audio-visual representation learning, HiCMAE adopts two primary forms of self-supervision for pre-training, namely masked data modeling and contrastive learning. Unlike them which focus exclusively on top-layer representations while neglecting explicit guidance of intermediate layers, HiCMAE develops a three-pronged strategy to foster hierarchical audio-visual feature learning and improve the overall quality of learned representations. To verify the effectiveness of HiCMAE, we conduct extensive experiments on 9 datasets covering both categorical and dimensional AVER tasks. Experimental results show that our method significantly outperforms state-of-the-art supervised and self-supervised audio-visual methods, which indicates that HiCMAE is a powerful audio-visual emotion representation learner. Codes and models will be publicly available at https://github.com/sunlicai/HiCMAE.

SVFAP: Self-supervised Video Facial Affect Perceiver

Video-based facial affect analysis has recently attracted increasing attention owing to its critical role in human-computer interaction. Previous studies mainly focus on developing various deep learning architectures and training them in a fully supervised manner. Although significant progress has been achieved by these supervised methods, the longstanding lack of large-scale high-quality labeled data severely hinders their further improvements. Motivated by the recent success of self-supervised learning in computer vision, this paper introduces a self-supervised approach, termed Self-supervised Video Facial Affect Perceiver (SVFAP), to address the dilemma faced by supervised methods. Specifically, SVFAP leverages masked facial video autoencoding to perform self-supervised pre-training on massive unlabeled facial videos. Considering that large spatiotemporal redundancy exists in facial videos, we propose a novel temporal pyramid and spatial bottleneck Transformer as the encoder of SVFAP, which not only enjoys low computational cost but also achieves excellent performance. To verify the effectiveness of our method, we conduct experiments on nine datasets spanning three downstream tasks, including dynamic facial expression recognition, dimensional emotion recognition, and personality recognition. Comprehensive results demonstrate that SVFAP can learn powerful affect-related representations via large-scale self-supervised pre-training and it significantly outperforms previous state-of-the-art methods on all datasets. Codes will be available at https://github.com/sunlicai/SVFAP.

What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection

The rapid evolution of speech synthesis and voice conversion has raised substantial concerns due to the potential misuse of such technology, prompting a pressing need for effective audio deepfake detection mechanisms. Existing detection models have shown remarkable success in discriminating known deepfake audio, but struggle when encountering new attack types. To address this challenge, one of the emergent effective approaches is continual learning. In this paper, we propose a continual learning approach called Radian Weight Modification (RWM) for audio deepfake detection. The fundamental concept underlying RWM involves categorizing all classes into two groups: those with compact feature distributions across tasks, such as genuine audio, and those with more spread-out distributions, like various types of fake audio. These distinctions are quantified by means of the in-class cosine distance, which subsequently serves as the basis for RWM to introduce a trainable gradient modification direction for distinct data types. Experimental evaluations against mainstream continual learning methods reveal the superiority of RWM in terms of knowledge acquisition and mitigating forgetting in audio deepfake detection. Furthermore, RWM's applicability extends beyond audio deepfake detection, demonstrating its potential significance in diverse machine learning domains such as image recognition.

GPT-4V with Emotion: A Zero-shot Benchmark for Multimodal Emotion Understanding

Recently, GPT-4 with Vision (GPT-4V) has shown remarkable performance across various multimodal tasks. However, its efficacy in emotion recognition remains a question. This paper quantitatively evaluates GPT-4V's capabilities in multimodal emotion understanding, encompassing tasks such as facial emotion recognition, visual sentiment analysis, micro-expression recognition, dynamic facial emotion recognition, and multimodal emotion recognition. Our experiments show that GPT-4V exhibits impressive multimodal and temporal understanding capabilities, even surpassing supervised systems in some tasks. Despite these achievements, GPT-4V is currently tailored for general domains. It performs poorly in micro-expression recognition that requires specialized expertise. The main purpose of this paper is to present quantitative results of GPT-4V on emotion understanding and establish a zero-shot benchmark for future research. Code and evaluation results are available at: https://github.com/zeroQiaoba/gpt4v-emotion.

Learning to Behave Like Clean Speech: Dual-Branch Knowledge Distillation for Noise-Robust Fake Audio Detection

Most research in fake audio detection (FAD) focuses on improving performance on standard noise-free datasets. However, in actual situations, there is usually noise interference, which will cause significant performance degradation in FAD systems. To improve the noise robustness, we propose a dual-branch knowledge distillation fake audio detection (DKDFAD) method. Specifically, a parallel data flow of the clean teacher branch and the noisy student branch is designed, and interactive fusion and response-based teacher-student paradigms are proposed to guide the training of noisy data from the data distribution and decision-making perspectives. In the noise branch, speech enhancement is first introduced for denoising, which reduces the interference of strong noise. The proposed interactive fusion combines denoising features and noise features to reduce the impact of speech distortion and seek consistency with the data distribution of clean branch. The teacher-student paradigm maps the student's decision space to the teacher's decision space, making noisy speech behave as clean. In addition, a joint training method is used to optimize the two branches to achieve global optimality. Experimental results based on multiple datasets show that the proposed method performs well in noisy environments and maintains performance in cross-dataset experiments.

Controllable Residual Speaker Representation for Voice Conversion

Recently, there have been significant advancements in voice conversion, resulting in high-quality performance. However, there are still two critical challenges in this field. Firstly, current voice conversion methods have limited robustness when encountering unseen speakers. Secondly, they also have limited ability to control timbre representation. To address these challenges, this paper presents a novel approach leverages tokens of multi-layer residual approximations to enhance robustness when dealing with unseen speakers, called the residual speaker module. The introduction of multi-layer approximations facilitates the separation of information from the timbre, enabling effective control over timbre in voice conversion. The proposed method outperforms baselines in both subjective and objective evaluations, demonstrating superior performance and increased robustness. Our demo page is publicly available.

Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveforms

Recent strides in neural speech synthesis technologies, while enjoying widespread applications, have nonetheless introduced a series of challenges, spurring interest in the defence against the threat of misuse and abuse. Notably, source attribution of synthesized speech has value in forensics and intellectual property protection, but prior work in this area has certain limitations in scope. To address the gaps, we present our findings concerning the identification of the sources of synthesized speech in this paper. We investigate the existence of speech synthesis model fingerprints in the generated speech waveforms, with a focus on the acoustic model and the vocoder, and study the influence of each component on the fingerprint in the overall speech waveforms. Our research, conducted using the multi-speaker LibriTTS dataset, demonstrates two key insights: (1) vocoders and acoustic models impart distinct, model-specific fingerprints on the waveforms they generate, and (2) vocoder fingerprints are the more dominant of the two, and may mask the fingerprints from the acoustic model. These findings strongly suggest the existence of model-specific fingerprints for both the acoustic model and the vocoder, highlighting their potential utility in source identification applications.

DGSD: Dynamical Graph Self-Distillation for EEG-Based Auditory Spatial Attention Detection

Auditory Attention Detection (AAD) aims to detect target speaker from brain signals in a multi-speaker environment. Although EEG-based AAD methods have shown promising results in recent years, current approaches primarily rely on traditional convolutional neural network designed for processing Euclidean data like images. This makes it challenging to handle EEG signals, which possess non-Euclidean characteristics. In order to address this problem, this paper proposes a dynamical graph self-distillation (DGSD) approach for AAD, which does not require speech stimuli as input. Specifically, to effectively represent the non-Euclidean properties of EEG signals, dynamical graph convolutional networks are applied to represent the graph structure of EEG signals, which can also extract crucial features related to auditory spatial attention in EEG signals. In addition, to further improve AAD detection performance, self-distillation, consisting of feature distillation and hierarchical distillation strategies at each layer, is integrated. These strategies leverage features and classification results from the deepest network layers to guide the learning of shallow layers. Our experiments are conducted on two publicly available datasets, KUL and DTU. Under a 1-second time window, we achieve results of 90.0\% and 79.6\% accuracy on KUL and DTU, respectively. We compare our DGSD method with competitive baselines, and the experimental results indicate that the detection performance of our proposed DGSD method is not only superior to the best reproducible baseline but also significantly reduces the number of trainable parameters by approximately 100 times.

Audio Deepfake Detection: A Survey

Audio deepfake detection is an emerging active topic. A growing number of literatures have aimed to study deepfake detection algorithms and achieved effective performance, the problem of which is far from being solved. Although there are some review literatures, 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 across various types of deepfake audio, then outline and analyse competitions, datasets, features, classifications, and evaluation of state-of-the-art approaches. For each aspect, the basic techniques, advanced developments and major challenges are discussed. In addition, we perform a unified comparison of representative features and classifiers on ASVspoof 2021, ADD 2023 and In-the-Wild datasets for audio deepfake detection, respectively. The survey shows that future research should address the lack of large scale datasets in the wild, poor generalization of existing detection methods to unknown fake attacks, as well as interpretability of detection results.

Spatial Reconstructed Local Attention Res2Net with F0 Subband for Fake Speech Detection

The rhythm of synthetic speech is usually too smooth, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real speech. It is expected that the F0 feature contains the discriminative information for the fake speech detection (FSD) task. In this paper, we propose a novel F0 subband for FSD. In addition, to effectively model the F0 subband so as to improve the performance of FSD, the spatial reconstructed local attention Res2Net (SR-LA Res2Net) is proposed. Specifically, Res2Net is used as a backbone network to obtain multiscale information, and enhanced with a spatial reconstruction mechanism to avoid losing important information when the channel group is constantly superimposed. In addition, local attention is designed to make the model focus on the local information of the F0 subband. Experimental results on the ASVspoof 2019 LA dataset show that our proposed method obtains an equal error rate (EER) of 0.47% and a minimum tandem detection cost function (min t-DCF) of 0.0159, achieving the state-of-the-art performance among all of the single systems.